{
  "data": {
    "a": {
      "slug": "gemini-enterprise",
      "name": "Gemini Enterprise",
      "vendor": "Google",
      "vendorUrl": "https://cloud.google.com/gemini-enterprise",
      "company": "google.com",
      "kind": "http-api",
      "category": "company-knowledge",
      "summary": "Google Cloud's enterprise assistant, which searches and acts across a company's connected apps and data. Developers call the assistant through the StreamAssist method of the Discovery Engine API, and agents registered in it over A2A.",
      "url": "https://www.anchorterminal.com/tools/gemini-enterprise",
      "markdownUrl": "https://www.anchorterminal.com/tools/gemini-enterprise.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-enterprise.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-enterprise.json",
      "dns": "gemini-enterprise.grade.anchorterminal.com",
      "license": "Proprietary service under the Google Cloud terms. The client libraries are Apache-2.0",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "google-cloud-discoveryengine"
        },
        {
          "registry": "npm",
          "name": "@google-cloud/discoveryengine"
        }
      ],
      "auth": "oauth",
      "authNotes": "Calls take an OAuth 2.0 bearer token, sent in the `Authorization` header in every Gemini Enterprise example, from user credentials, a service account, service account impersonation or workforce identity federation. StreamAssist accepts the `cloud-platform`, `discoveryengine.assist.readwrite`, `discoveryengine.readwrite` or `discoveryengine.serving.readwrite` scope and needs the `discoveryengine.assistants.assist` permission on the assistant. Users get the Gemini Enterprise User role (`roles/discoveryengine.agentspaceUser`) on a project or on single apps, and need a licence. With Application Default Credentials, send `X-Goog-User-Project`. No API key flow is documented. Google's OAuth guide also documents an `access_token` query parameter, which the API reads, so keep tokens out of URLs. Refresh tokens can be bound to a client key with DPoP from 15 October 2026.",
      "pricing": "paid",
      "pricingNotes": "No seat prices on the Google pages read (product, editions, licences and quotas pages, checked 2026-10-10). Editions are Business, Standard, Plus, Frontline and Pay-as-you-go. The product page points to sales or a 30-day Plus trial without sales, through the Google Cloud Free Trial, which asks for a card. Pay-as-you-go and overages bill storage over quota at $5 per GiB a month and assistant queries at Agent Platform prices, and need an invoiced Cloud Billing account (https://docs.cloud.google.com/gemini/enterprise/docs/quotas).",
      "priceSummary": "Paid",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the StreamAssist guide and reference, the A2A guide, the quotas and overages page or the product page (checked 2026-10-10).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": 138716,
        "pypiWeekly": 1207443,
        "asOf": "2026-10-10"
      },
      "docsUrl": "https://docs.cloud.google.com/gemini/enterprise/docs/developer-guide",
      "openapi": "https://discoveryengine.googleapis.com/$discovery/rest?version=v1",
      "capabilities": [
        "knowledge.search",
        "agent.multi-agent",
        "agent.mcp-client",
        "web.search"
      ],
      "tags": [
        "official",
        "hosted",
        "enterprise",
        "closed-source",
        "oauth",
        "openapi",
        "a2a",
        "sales-led",
        "card-required",
        "status-page",
        "sla",
        "soc2",
        "python",
        "typescript",
        "java",
        "go",
        "eu"
      ],
      "lastRelease": "2026-10-30",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 67,
        "grade": "B",
        "agentReady": false,
        "rank": 463,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 3,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 48,
          "maintenance": 80,
          "payments": 15,
          "reliability": 85,
          "schema": 78,
          "security": 77,
          "transparency": 82
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": 0,
        "verdict": "The assistant is callable through a GA v1 method with a 99.5 per cent SLA, OAuth through IAM, a public Discovery document and optional Model Armor screening. Seat prices weren't found on Google's pages, onboarding needs a billing account and a person, and the API also reads OAuth tokens from a URL query parameter.",
        "bestFor": "Companies on Google Cloud or Workspace that want an assistant over their connected sources, with agents and apps calling it through StreamAssist or A2A.",
        "strengths": [
          "StreamAssist is a GA v1 method with a 99.5 per cent monthly uptime SLA and service credits",
          "OAuth 2.0 through IAM, with a narrow `discoveryengine.assist.readwrite` scope and per-app user roles",
          "A public Discovery document (revision 20261022, 278 methods) and client libraries in seven languages",
          "Model Armor can screen the assistant's prompts and responses on every edition at no extra cost",
          "Agents registered in Gemini Enterprise answer A2A `message:send` and `message:stream` through a Google endpoint"
        ],
        "weaknesses": [
          "No seat prices on the Google pages read, and pay-as-you-go needs an invoiced Cloud Billing account",
          "The 30-day Plus trial goes through the Google Cloud Free Trial, which asks for a card or other payment method",
          "No retry, backoff or idempotency guidance for StreamAssist was found, and each call writes to a session",
          "Google's OAuth guide documents an `access_token` query parameter, and the API reads a token sent that way",
          "Assistant use is capped per licence, 160 queries a day on Standard and 200 on Plus, pooled per project"
        ],
        "agentNotes": [
          "Create a Gemini Enterprise app first. StreamAssist needs its APP_ID, and the caller needs `discoveryengine.assistants.assist`",
          "Send `X-Goog-User-Project` with your project ID when calling with Application Default Credentials",
          "Pass the `session` name from the final stream message on the next call to keep context. Leaving it empty starts a new session",
          "Read `connectorAuthErrors` in the response. A connector that failed sign-in is skipped and the answer comes from the rest",
          "Use the A2A URL returned by Agent Registry verbatim. It takes the project number, not the project ID",
          "Send the token in the `Authorization: Bearer` header, not as `?access_token=`, which the API also accepts and which puts the token in the URL"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 2.8,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 67
          }
        ],
        "editorialScores": {
          "ergonomics": 48,
          "maintenance": 80,
          "payments": 15,
          "reliability": 85,
          "schema": 78,
          "security": 77,
          "transparency": 64
        },
        "provenanceScore": 99,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install google-cloud-discoveryengine   # or: npm install @google-cloud/discoveryengine",
        "http": "curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" \"https://ENDPOINT_LOCATION-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/collections/default_collection/engines/APP_ID/assistants/default_assistant:streamAssist\" -d '{\"query\": {\"text\": \"QUERY_TEXT\"}}'"
      },
      "letme": {
        "capability": "https://letme.dev/knowledge.search",
        "tool": "https://letme.dev/gemini-enterprise"
      },
      "sameCompany": [
        "gemini-4-carbon",
        "gemini-4-hydrogen",
        "gemini-api",
        "vertex-ai",
        "embeddinggemma-2",
        "embeddinggemma-300m",
        "gemini-embedding",
        "vertex-ai-tuning",
        "cloud-run-gpus",
        "google-model-armor",
        "shieldgemma",
        "google-imagen",
        "gemini-omni-1-2-flash",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "google-cloud-tts",
        "gemini-live",
        "google-adk",
        "google-memory-bank",
        "google-secret-manager",
        "google-cloud-document-ai",
        "google-weather-api",
        "chrome-devtools-mcp",
        "puppeteer",
        "mcp-toolbox-databases",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "firebase-cloud-messaging",
        "google-cloud-storage",
        "google-drive-api",
        "gemini-decision-1",
        "antigravity-cli",
        "gemini-cli",
        "harness2",
        "jules",
        "gemini-spark",
        "google-search-console",
        "google-ads-api",
        "google-forms",
        "google-sheets-api",
        "gmail-api",
        "google-people-api",
        "diffusiongemma-26b-a4b-it",
        "gemma-4-12b-it",
        "gemma-4-26b-a4b-it",
        "gemma-4-31b-it",
        "gemma-4-e2b-it",
        "gemma-4-e4b-it",
        "virustotal"
      ],
      "area": "business",
      "unitPrices": [
        {
          "item": "Storage and data indexing over quota (per GiB)",
          "unit": "gb-month",
          "usd": 5
        }
      ],
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "google.com",
        "domainRegistered": "1997-09-15",
        "domainNote": "The API is on googleapis.com, Google's API domain. Docs are on docs.cloud.google.com.",
        "endpointOnVendorDomain": true,
        "terms": "https://cloud.google.com/terms",
        "privacy": "https://cloud.google.com/terms/cloud-privacy-notice",
        "statusPage": "https://status.cloud.google.com",
        "changelog": "https://docs.cloud.google.com/gemini/enterprise/docs/release-notes",
        "securityTxt": "valid",
        "checked": "2026-11-01",
        "notes": [
          "https://www.google.com/.well-known/security.txt shows Expires 2030-04-01 and points to the vulnerability reward programme (read 1 November 2026).",
          "The legal entity, terms, privacy notice and domain registration date (RDAP, 1997-09-15) are taken from the 9 October check of the Google Cloud Document AI listing, not re-read on 1 November.",
          "The Google Cloud status page lists Gemini Enterprise and 'Financial Research agent in Gemini Enterprise' as products (https://status.cloud.google.com/products.json, re-read 1 November 2026). Its incident feed was re-read on 1 November.",
          "Release notes re-read on 1 November 2026, newest entry 30 October."
        ],
        "score": 99
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-enterprise.json",
      "live": {
        "slug": "gemini-enterprise",
        "vendorStatus": {
          "page": "https://status.cloud.google.com",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-06T21:47:40.968105742Z"
        },
        "versions": [
          {
            "registry": "npm",
            "name": "@google-cloud/discoveryengine",
            "version": "3.5.0",
            "seenAt": "2026-11-18T17:49:55.792143438Z"
          },
          {
            "registry": "pypi",
            "name": "google-cloud-discoveryengine",
            "version": "0.20.7",
            "released": "2026-11-12",
            "seenAt": "2026-11-18T17:49:55.558962842Z"
          }
        ],
        "npmWeekly": 161089,
        "pypiWeekly": 1411319,
        "securityTxt": {
          "url": "https://google.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2030-04-01T00:00:00z",
          "checkedAt": "2026-11-18T16:31:15.950099081Z"
        },
        "domain": {
          "domain": "google.com",
          "registered": "1997-09-15",
          "source": "https://rdap.verisign.com/com/v1/domain/google.com",
          "checkedAt": "2026-11-15T15:15:24.267716809Z"
        },
        "pages": [
          {
            "url": "https://docs.cloud.google.com/gemini/enterprise/docs/release-notes",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:39:36.712533367Z",
            "changedAt": "2026-11-17T20:58:28.289143385Z",
            "fingerprint": "75394e58739f"
          },
          {
            "url": "https://cloud.google.com/terms/cloud-privacy-notice",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-06T13:24:11.796492564Z",
            "changedAt": "2026-11-03T07:43:24.319773868Z",
            "fingerprint": "b62369d64ac6"
          },
          {
            "url": "https://cloud.google.com/terms",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-06T13:24:10.104460657Z",
            "changedAt": "2026-11-03T07:43:22.480965239Z",
            "fingerprint": "b9ec671a2caf"
          }
        ],
        "updatedAt": "2026-11-18T21:39:36.712533367Z"
      }
    },
    "answer": "Gemini Enterprise scores 67 (B) on agent readiness against Microsoft MCP Server for Enterprise's 54.1 (C), and leads in 4 of 7 scored categories. Microsoft MCP Server for Enterprise leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.",
    "b": {
      "slug": "microsoft-mcp-server-enterprise",
      "name": "Microsoft MCP Server for Enterprise",
      "vendor": "Microsoft",
      "vendorUrl": "https://www.microsoft.com",
      "company": "microsoft.com",
      "kind": "mcp",
      "category": "company-knowledge",
      "summary": "Microsoft MCP Server for Enterprise is a hosted MCP server that lets AI agents query a Microsoft Entra tenant's users, groups, applications and devices in natural language, through read-only Microsoft Graph calls.",
      "url": "https://www.anchorterminal.com/tools/microsoft-mcp-server-enterprise",
      "markdownUrl": "https://www.anchorterminal.com/tools/microsoft-mcp-server-enterprise.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/microsoft-mcp-server-enterprise.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/microsoft-mcp-server-enterprise.json",
      "dns": "microsoft-mcp-server-enterprise.grade.anchorterminal.com",
      "license": "Closed service under the Microsoft APIs Terms of Use",
      "transports": [
        "streamable-http"
      ],
      "remoteUrl": "https://mcp.svc.cloud.microsoft/enterprise",
      "packages": [],
      "auth": "oauth",
      "authNotes": "Microsoft Entra delegated OAuth. An administrator provisions the server once per tenant (Entra PowerShell) and grants each MCP client its permissions; calls run with the signed-in user's privileges and the client's granted scopes.",
      "pricing": "free",
      "pricingNotes": "No additional cost or separate licence to enable it, per the overview (checked 18 November 2026). Data behind some queries needs its own licence, such as Entra ID P2 or ID Governance for Privileged Identity Management.",
      "priceSummary": "Free",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402; the server is free and authenticated with Entra (checked 2026-11-18).",
        "endpoints": []
      },
      "toolCount": 3,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://learn.microsoft.com/en-us/graph/mcp-server/overview",
      "capabilities": [
        "knowledge.search"
      ],
      "tags": [
        "official",
        "mcp",
        "hosted",
        "oauth",
        "entra-id",
        "enterprise",
        "read-only",
        "free",
        "new"
      ],
      "lastRelease": "2026-11-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 54.1,
        "grade": "C",
        "agentReady": false,
        "rank": 1026,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 12,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 55,
          "maintenance": 43,
          "payments": 50,
          "reliability": 53,
          "schema": 29,
          "security": 85,
          "transparency": 57
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "A free, read-only MCP server over a Microsoft Entra tenant's directory, with Entra-scoped access and every call in Graph's activity logs. It needs an administrator to provision it per tenant, and its tool schemas, errors and changelog aren't public.",
        "bestFor": "Admins and support agents who ask questions about users, groups, apps, devices and licences in an Entra tenant.",
        "strengths": [
          "Free to enable, with no separate licence",
          "Read-only Graph calls that run with the user's own privileges and the client's granted scopes",
          "Every request logged in Microsoft Graph activity logs, with a query to filter the server",
          "Three tools, so a small tool list in context",
          "100 calls a minute per user, published"
        ],
        "weaknesses": [
          "An administrator has to provision it per tenant with PowerShell and grant each client",
          "Tool schemas can't be read without a tenant, and no error responses are documented",
          "Pages still say preview the day after Microsoft announced general availability",
          "No changelog, version history or deprecation policy found",
          "Some data needs its own Entra licence, such as ID P2 for PIM"
        ],
        "agentNotes": [
          "Connect to https://mcp.svc.cloud.microsoft/enterprise with an Entra token for a client your administrator has granted",
          "Call microsoft_graph_suggest_queries first to find the Graph call, then microsoft_graph_get to run it",
          "Expect only reads; it can't change anything in the tenant",
          "Stay under 100 calls a minute per user"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 54.1
          }
        ],
        "editorialScores": {
          "ergonomics": 55,
          "maintenance": 43,
          "payments": 50,
          "reliability": 53,
          "schema": 29,
          "security": 85,
          "transparency": 35
        },
        "provenanceScore": 79,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "https://mcp.svc.cloud.microsoft/enterprise"
      },
      "letme": {
        "capability": "https://letme.dev/knowledge.search",
        "tool": "https://letme.dev/microsoft-mcp-server-enterprise"
      },
      "sameCompany": [
        "azure-openai",
        "azure-foundry-fine-tuning",
        "azure-ai-content-safety",
        "azure-speech-to-text",
        "azure-text-to-speech",
        "microsoft-agent-framework",
        "microsoft-execution-containers",
        "microsoft-entra-agent-id",
        "azure-key-vault",
        "bing-grounding",
        "azure-document-intelligence",
        "azure-devops-mcp",
        "microsoft-learn-mcp",
        "tokeneconomizer",
        "playwright-mcp",
        "azure-mcp",
        "azure-maps",
        "azure-translator",
        "microsoft-graph-calendar",
        "azure-blob-storage",
        "onedrive-sharepoint",
        "microsoft-teams",
        "dynamics-365-sales",
        "copilot-studio-mcp",
        "power-automate",
        "foundry-local",
        "microsoft-decision-1",
        "microsoft-decision-1-1",
        "microsoft-advertising-api",
        "microsoft-excel-graph",
        "outlook-mail-graph",
        "microsoft-graph-people",
        "fara1-5-27b",
        "fara1-5-4b",
        "fara1-5-9b",
        "mage-vl-cowork"
      ],
      "area": "business",
      "provenance": {
        "legalEntity": "Microsoft Corporation",
        "domain": "microsoft.com",
        "domainRegistered": "1991-05-02",
        "domainNote": "The endpoint is https://mcp.svc.cloud.microsoft/enterprise, a Microsoft domain, and it calls Microsoft Graph. microsoft.com's security.txt had passed its Expires date per the Copilot Studio MCP listing of 17 October.",
        "endpointOnVendorDomain": true,
        "terms": "https://learn.microsoft.com/en-us/legal/microsoft-apis/terms-of-use",
        "privacy": "https://www.microsoft.com/en-us/privacy/privacystatement",
        "statusPage": "https://status.cloud.microsoft",
        "changelog": "",
        "securityTxt": "expired",
        "checked": "2026-11-18",
        "notes": [
          "learn.microsoft.com allowed our reader on 18 November. The endpoint needs a Microsoft Entra tenant with the server provisioned and a client granted permissions, so tools/list wasn't read and nothing was called.",
          "Microsoft's Ignite 2026 Book of News lists it as generally available on 17 November 2026, while the overview page read the next day still says preview."
        ],
        "score": 79
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-mcp-server-enterprise.json",
      "live": {
        "slug": "microsoft-mcp-server-enterprise",
        "probe": {
          "target": "https://mcp.svc.cloud.microsoft/enterprise",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T23:01:41.227157773Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 132,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 76,
          "p95ms24h": 275,
          "samples24h": 221,
          "samples30d": 221,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 221,
              "ok": 221
            }
          ],
          "since": "2026-11-18T00:59:30.176367545Z"
        },
        "securityTxt": {
          "url": "https://microsoft.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2027-10-27T16:00:00.000Z",
          "checkedAt": "2026-11-18T16:29:47.885824675Z"
        },
        "mcpTools": {
          "url": "https://mcp.svc.cloud.microsoft/enterprise",
          "checkedAt": "2026-11-18T04:25:59.220245332Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-11-18T04:25:59.220245332Z"
        },
        "updatedAt": "2026-11-18T23:01:41.227157773Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "edges": [
      {
        "by": 49,
        "category": "schema",
        "leads": "gemini-enterprise",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "A public Discovery document for v1, revision 20261022 on 1 November, with 278 methods and 993 schemas, StreamAssist and the A2A methods among them (25). docs.cloud.google.com/llms.txt answers 404 (1 November). A page address with `.md.txt` added answers as Markdown, as the release notes, quotas and compliance pages did on 1 November, which no page we read links, so half (5 of 10). StreamAssist's description is one line, while the guide says when to use the API rather than the web app and what sessions and files do (12 of 20). 3,421 of 3,448 properties carry a description and 245 are enums, counted on revision 20261004. Required and optional are stated in each description, and `inputVariables` for workflow agents is a free Struct (11 of 15). The guide has a curl request with a full streamed response and the reference covers seven client libraries. No Gemini Enterprise page listing error codes was found (10 of 15). v1, v1beta and v1alpha versions and dated release notes, the newest on 30 October 2026 (15).",
          "b": "The three tools (microsoft_graph_suggest_queries, microsoft_graph_get, microsoft_graph_list_properties) are described in prose on the overview. Their schemas need an Entra tenant to list, so no contract was read (0 of 25). learn.microsoft.com serves Markdown to agents, as for the other Microsoft listings (10). The overview says what each tool does and the workflow they follow, but not when not to use them (12 of 20). Input types weren't readable (0 of 15). A sample prompts page and a Kusto query for its logs, but no documented error responses (7 of 15). No version or changelog found (0). 0 + 10 + 12 + 0 + 7 + 0 = 29."
        },
        "scores": {
          "a": 78,
          "b": 29
        }
      },
      {
        "by": 37,
        "category": "maintenance",
        "leads": "gemini-enterprise",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Read as a closed service with official client libraries. Newest release notes dated 30 October 2026 (Gemini Notebook Enterprise refresh, GA, and the S\u0026P Global data store in Preview), after the Brazil region on 28 October, VPC connectivity for custom MCP servers on 27 October and single-user quota limits on 22 October (30). Dozens of dated release note entries since August, 14 dates between 1 and 30 October alone (20). Dated release notes, Google Cloud support and public issue trackers for the client libraries. We didn't test support (10 of 15). Official client libraries, npm `@google-cloud/discoveryengine` 3.4.0 on 12 October 2026 and the Python library's tag `google-cloud-discoveryengine-v0.20.5`, per the 17 October check, not re-read on 1 November (15). The Python library is still below 1.0 and declares Python 3.10 or later, per the 10 October check. CI results weren't checked (5 of 10).",
          "b": "General availability announced on 17 November 2026 (30). No three dated changes in 90 days were found (0). Questions are answered on Microsoft Q\u0026A, and support goes through Microsoft's channels (8 of 15). The GitHub MCP registry shows an entry under microsoft, seen in a search only, so not counted (0, unchecked). A hosted service with no package to keep current (5 of 10). 30 + 0 + 8 + 0 + 5 = 43."
        },
        "scores": {
          "a": 80,
          "b": 43
        }
      },
      {
        "by": 35,
        "category": "payments",
        "leads": "microsoft-mcp-server-enterprise",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "Hosted rubric. No x402, MPP or L402 (0). No seat prices were found on Google's product, editions, licences or quotas pages, and the product page sends buyers to sales or a trial. Pay-as-you-go and overages are priced publicly by reference, $5 per GiB a month for storage over quota and Agent Platform prices for assistant queries, without a per-query figure. Claude models in the app, GA on 15 October, are charged pay as you go with no price on the release note. Counted as plan-level pricing that's public (10, a judgement call). A 30-day Plus trial needs no sales contact (product page re-read on 1 November), but it runs through the Google Cloud Free Trial, which asks for a credit card or other payment method (0). A person creates the project, billing account and app in the console and assigns licences (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.",
          "b": "No payment protocol (0). The overview says there's no additional cost or separate licence to enable it, published without a login (30). It's free, but it needs a Microsoft Entra tenant, and some data needs Entra ID P2 or ID Governance licences (20 of 30). An administrator provisions it with PowerShell and grants each client in the tenant (0). 0 + 30 + 20 + 0 = 50."
        },
        "scores": {
          "a": 15,
          "b": 50
        }
      },
      {
        "by": 32,
        "category": "reliability",
        "leads": "gemini-enterprise",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted reading, scored on the StreamAssist method of the Discovery Engine API. The Google Cloud status page lists Gemini Enterprise and Vertex AI Search as products (products.json, re-read on 1 November) and has a JSON incident feed (20). Re-read on 1 November, the feed has four incidents in the window from 3 August, on 20 August (27 products), 1 September (us-central1-b), 8 and 9 October (Cloud Storage) and 20 October (europe-west2, 38 products), and none names Gemini Enterprise, Vertex AI Search or another Gemini product (30). Rate quotas with numbers, 300 complete-query and 300 regional search requests a minute per project, and assistant quotas per licence, 160 queries a day on Standard and 200 on Plus, pooled per edition, project and location, re-read on 1 November (15). No retry or backoff guidance and no 429 handling on the StreamAssist guide or the quotas page (re-read on 1 November), and each call writes to a session, so a retry isn't documented as safe (0 of 15). The Gemini Enterprise SLA, last modified 22 April 2026 and still written for Google Agentspace, commits to 99.5 per cent monthly uptime for StreamAssist and 99.9 for Search, with credits from 10 to 50 per cent (10). StreamAssist is in the v1 API and its guide marks only file upload as Preview (10).",
          "b": "Hosted MCP lines. Microsoft's cloud status page at status.cloud.microsoft, as for the Copilot Studio MCP listing (20). No incident history for this service could be read, so 5 of 30 and said so. Rate limit published, 100 calls a minute per user (15). The overview says calls honour Graph throttling limits but gives no 429 or Retry-After guidance of its own (8 of 15). No SLA found for it (0). Microsoft's Book of News of 17 November 2026 lists it as generally available, but the overview page read on 18 November still says preview, so half (5 of 10, a judgement call). 20 + 5 + 15 + 8 + 0 + 5 = 53."
        },
        "scores": {
          "a": 85,
          "b": 53
        }
      },
      {
        "by": 25,
        "category": "transparency",
        "leads": "gemini-enterprise",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15 of 30). The product page says prompts, outputs and tuning are never used to train Google models or other customers' models, and the security overview says user-requested data is deleted within 60 days. The Cloud terms and Data Processing Addendum weren't re-read today, and retention for sessions and memory wasn't found (20 of 30). The Cloud terms promise 12 months' notice before a backwards-incompatible API change, per the 9 October Document AI check, not re-read on 10 October. The release notes, re-read on 1 November, gave 19 days' notice (1 to 20 October) for removing Gemini 2.5 Pro from the Canada and Japan regions, done on 20 October, and four days' notice (22 to 26 October) for the AlphaEvolve default model and price change, both in the listing's deprecations (12 of 20). Global, `us` and `eu` multi-regions with data residency limits stated, and Google Cloud's public sub-processor list per the 9 October check (17 of 20).",
          "b": "Closed service under the Microsoft APIs Terms of Use (15). Requests run through Microsoft Graph and are logged there, but no retention or data-handling statement specific to the server was found (12 of 30). No deprecation policy for it, and the pages still carry preview wording (0 of 20). The overview lists the clouds it's available in (8 of 20). 15 + 12 + 0 + 8 = 35."
        },
        "scores": {
          "a": 82,
          "b": 57
        }
      },
      {
        "by": 8,
        "category": "security",
        "leads": "microsoft-mcp-server-enterprise",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "OAuth 2.0 bearer tokens from user credentials, service accounts or workforce identity federation, with IAM permissions. StreamAssist accepts the narrow `discoveryengine.assist.readwrite` scope among four (30), less 10 because Google's OAuth 2.0 web-server guide documents sending the token as an `access_token` query parameter, the v1 Discovery document (revision 20261022) lists `access_token` and `oauth_token` as parameters, and on 1 November (as on 17 October) a made-up token sent as `?access_token=` came back 'invalid authentication credentials' where no token came back 'missing required authentication credential', so the API reads a token from the URL. The Gemini Enterprise docs send it only in the `Authorization` header, which doesn't remove the documented option. Read as the Workspace APIs were on 17 October (20). Google's OAuth platform can bind refresh tokens to a client key with DPoP from 15 October 2026, while access tokens stay bearer tokens, so the line doesn't move for it. Gemini Enterprise User can be granted per app through the Restricted User pattern, a custom role can hold only `discoveryengine.assistants.assist`, and VPC Service Controls apply. The assistant can run connector actions such as sending Outlook mail, and we didn't read how it asks for confirmation (14 of 20). Model Armor screens the assistant's prompts and responses on every edition at no extra cost, but it's off until an admin enables it and can be set to let traffic through unscreened when it's unavailable, per the 10 October check (10 of 15). Cloud Audit Logs list each method by permission type, and usage audit logs can record prompts and responses when that setting is on. Data Access logs are off by default in Google Cloud, per the 10 October check (13 of 15). google.com security.txt is valid to 1 April 2030 with the reward programme, and the compliance page lists ISO 27001, 27017 and 27018, SOC 1, 2 and 3, HIPAA, FedRAMP Moderate and High, PCI DSS and C5, both re-read on 1 November (20), the reading most Google Cloud listings in this run take. Total 77.",
          "b": "Microsoft Entra delegated OAuth: an administrator registers the server and grants each MCP client its scopes, and the server enforces the user's own privileges and those scopes (30). Read-only Graph calls only (20). It returns directory data, names and attributes that users and admins can edit, with no prompt-injection guidance found (5 of 15). Every request lands in Microsoft Graph activity logs, with a Kusto query to filter the server's app ID (15). Microsoft's security programme and certifications, but microsoft.com's security.txt had expired per the Copilot Studio MCP listing (15 of 20). 30 + 20 + 5 + 15 + 15 = 85."
        },
        "scores": {
          "a": 77,
          "b": 85
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Google",
        "b": "Microsoft",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "https://mcp.svc.cloud.microsoft/enterprise",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "OAuth",
        "b": "OAuth",
        "name": "Auth"
      },
      {
        "a": "Paid",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under the Google Cloud terms. The client libraries are Apache-2.0",
        "b": "Closed service under the Microsoft APIs Terms of Use",
        "name": "Licence"
      },
      {
        "a": "none",
        "b": "3",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-30",
        "b": "2026-11-17",
        "name": "Last release"
      },
      {
        "a": "2026-09-02",
        "b": "2025-10-01",
        "name": "Terms last updated"
      },
      {
        "a": "2026-09-28",
        "b": "2026-09-01",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "139k npm/wk, 1.2M PyPI/wk",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "2.8/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Gemini Enterprise scores 67 (B) on agent readiness against Microsoft MCP Server for Enterprise's 54.1 (C), and leads in 4 of 7 scored categories. Microsoft MCP Server for Enterprise leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.",
        "question": "Which is better for AI agents, Gemini Enterprise or Microsoft MCP Server for Enterprise?"
      },
      {
        "answer": "Both use an OAuth sign-in.",
        "question": "Do Gemini Enterprise and Microsoft MCP Server for Enterprise need an API key?"
      },
      {
        "answer": "No hosted endpoint is listed for Gemini Enterprise. Microsoft MCP Server for Enterprise has a hosted endpoint at https://mcp.svc.cloud.microsoft/enterprise.",
        "question": "Can an agent call Gemini Enterprise and Microsoft MCP Server for Enterprise without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 85 against 53",
          "Schema \u0026 documentation, 78 against 29",
          "Maintenance \u0026 community, 80 against 43",
          "Transparency \u0026 trust, 82 against 57"
        ],
        "also": null,
        "goodFor": "Companies on Google Cloud or Workspace that want an assistant over their connected sources, with agents and apps calling it through StreamAssist or A2A.",
        "slug": "gemini-enterprise",
        "watchFor": "No seat prices on the Google pages read, and pay-as-you-go needs an invoiced Cloud Billing account"
      },
      {
        "aheadOn": [
          "Agent ergonomics, 55 against 48",
          "Security \u0026 auth, 85 against 77",
          "Payments \u0026 pricing, 50 against 15"
        ],
        "also": [
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Admins and support agents who ask questions about users, groups, apps, devices and licences in an Entra tenant.",
        "slug": "microsoft-mcp-server-enterprise",
        "watchFor": "An administrator has to provision it per tenant with PowerShell and grant each client"
      }
    ],
    "history": {
      "gemini-enterprise": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 0.6,
          "from": 66.4,
          "fromGrade": "B",
          "to": 67,
          "toGrade": "B"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-10-17",
          "delta": -1.7,
          "from": 68.1,
          "fromGrade": "B",
          "to": 66.4,
          "toGrade": "B"
        }
      ],
      "microsoft-mcp-server-enterprise": null
    },
    "job": {
      "capability": "knowledge.search",
      "name": "Company knowledge search"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/alation-vs-gemini-enterprise.json",
        "title": "Alation vs Gemini Enterprise",
        "url": "https://www.anchorterminal.com/compare/alation-vs-gemini-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/alation-vs-microsoft-mcp-server-enterprise.json",
        "title": "Alation vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/alation-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/atlan-vs-gemini-enterprise.json",
        "title": "Atlan vs Gemini Enterprise",
        "url": "https://www.anchorterminal.com/compare/atlan-vs-gemini-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/atlan-vs-microsoft-mcp-server-enterprise.json",
        "title": "Atlan vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/atlan-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-north-vs-gemini-enterprise.json",
        "title": "Cohere North vs Gemini Enterprise",
        "url": "https://www.anchorterminal.com/compare/cohere-north-vs-gemini-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-north-vs-microsoft-mcp-server-enterprise.json",
        "title": "Cohere North vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/cohere-north-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/collibra-vs-gemini-enterprise.json",
        "title": "Collibra vs Gemini Enterprise",
        "url": "https://www.anchorterminal.com/compare/collibra-vs-gemini-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/collibra-vs-microsoft-mcp-server-enterprise.json",
        "title": "Collibra vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/collibra-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/dust-vs-gemini-enterprise.json",
        "title": "Dust vs Gemini Enterprise",
        "url": "https://www.anchorterminal.com/compare/dust-vs-gemini-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/dust-vs-microsoft-mcp-server-enterprise.json",
        "title": "Dust vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/dust-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-glean.json",
        "title": "Gemini Enterprise vs Glean",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-glean"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-guru.json",
        "title": "Gemini Enterprise vs Guru",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-guru"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-hexis.json",
        "title": "Gemini Enterprise vs Hexis Cloud",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-hexis"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-onyx.json",
        "title": "Gemini Enterprise vs Onyx",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-onyx"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-overclock.json",
        "title": "Gemini Enterprise vs Overclock",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-overclock"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-procore-ai-go.json",
        "title": "Gemini Enterprise vs Procore AI Go",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-procore-ai-go"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-secoda.json",
        "title": "Gemini Enterprise vs Secoda",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-secoda"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-thought-industries-lens.json",
        "title": "Gemini Enterprise vs Lens (Thought Industries)",
        "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-thought-industries-lens"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glean-vs-microsoft-mcp-server-enterprise.json",
        "title": "Glean vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/glean-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/guru-vs-microsoft-mcp-server-enterprise.json",
        "title": "Guru vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/guru-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hexis-vs-microsoft-mcp-server-enterprise.json",
        "title": "Hexis Cloud vs Microsoft MCP Server for Enterprise",
        "url": "https://www.anchorterminal.com/compare/hexis-vs-microsoft-mcp-server-enterprise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-onyx.json",
        "title": "Microsoft MCP Server for Enterprise vs Onyx",
        "url": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-onyx"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-overclock.json",
        "title": "Microsoft MCP Server for Enterprise vs Overclock",
        "url": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-overclock"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-procore-ai-go.json",
        "title": "Microsoft MCP Server for Enterprise vs Procore AI Go",
        "url": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-procore-ai-go"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-secoda.json",
        "title": "Microsoft MCP Server for Enterprise vs Secoda",
        "url": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-secoda"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-thought-industries-lens.json",
        "title": "Microsoft MCP Server for Enterprise vs Lens (Thought Industries)",
        "url": "https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-thought-industries-lens"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 32,
        "edge": "gemini-enterprise",
        "gemini-enterprise": 85,
        "key": "reliability",
        "microsoft-mcp-server-enterprise": 53,
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 49,
        "edge": "gemini-enterprise",
        "gemini-enterprise": 78,
        "key": "schema",
        "microsoft-mcp-server-enterprise": 29,
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 7,
        "edge": "microsoft-mcp-server-enterprise",
        "gemini-enterprise": 48,
        "key": "ergonomics",
        "microsoft-mcp-server-enterprise": 55,
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 8,
        "edge": "microsoft-mcp-server-enterprise",
        "gemini-enterprise": 77,
        "key": "security",
        "microsoft-mcp-server-enterprise": 85,
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 35,
        "edge": "microsoft-mcp-server-enterprise",
        "gemini-enterprise": 15,
        "key": "payments",
        "microsoft-mcp-server-enterprise": 50,
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 37,
        "edge": "gemini-enterprise",
        "gemini-enterprise": 80,
        "key": "maintenance",
        "microsoft-mcp-server-enterprise": 43,
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 25,
        "edge": "gemini-enterprise",
        "gemini-enterprise": 82,
        "key": "transparency",
        "microsoft-mcp-server-enterprise": 57,
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Gemini Enterprise scores 67 (B) on agent readiness against Microsoft MCP Server for Enterprise's 54.1 (C), and leads in 4 of 7 scored categories. Microsoft MCP Server for Enterprise leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing. Both do company knowledge search.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "gemini-enterprise": "The assistant is callable through a GA v1 method with a 99.5 per cent SLA, OAuth through IAM, a public Discovery document and optional Model Armor screening. Seat prices weren't found on Google's pages, onboarding needs a billing account and a person, and the API also reads OAuth tokens from a URL query parameter.",
      "microsoft-mcp-server-enterprise": "A free, read-only MCP server over a Microsoft Entra tenant's directory, with Entra-scoped access and every call in Graph's activity logs. It needs an administrator to provision it per tenant, and its tool schemas, errors and changelog aren't public."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise",
    "json": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise.min.md"
  },
  "markdown": "Gemini Enterprise scores 67 (B) on agent readiness against Microsoft MCP Server for Enterprise's 54.1 (C), and leads in 4 of 7 scored categories. Microsoft MCP Server for Enterprise leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing. Both do company knowledge search.\n\n- Gemini Enterprise: grade B, 67/100, rank #463 of 1557. Markdown https://www.anchorterminal.com/tools/gemini-enterprise.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-enterprise.json\n- Microsoft MCP Server for Enterprise: grade C, 54.1/100, rank #1026 of 1557. Markdown https://www.anchorterminal.com/tools/microsoft-mcp-server-enterprise.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-mcp-server-enterprise.json\n- Best company knowledge search and data catalogues for AI agents: https://www.anchorterminal.com/best/company-knowledge/index.md\n- All 152 knowledge comparisons: https://www.anchorterminal.com/compare/company-knowledge/index.md\n\n## Which one, for what\n\n### Gemini Enterprise (B)\n\nGood for: Companies on Google Cloud or Workspace that want an assistant over their connected sources, with agents and apps calling it through StreamAssist or A2A.\n\nAhead on:\n- Reliability, 85 against 53\n- Schema \u0026 documentation, 78 against 29\n- Maintenance \u0026 community, 80 against 43\n- Transparency \u0026 trust, 82 against 57\n\nWatch for: No seat prices on the Google pages read, and pay-as-you-go needs an invoiced Cloud Billing account\n\n### Microsoft MCP Server for Enterprise (C)\n\nGood for: Admins and support agents who ask questions about users, groups, apps, devices and licences in an Entra tenant.\n\nAhead on:\n- Agent ergonomics, 55 against 48\n- Security \u0026 auth, 85 against 77\n- Payments \u0026 pricing, 50 against 15\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: An administrator has to provision it per tenant with PowerShell and grant each client\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Gemini Enterprise +49\n\n- Gemini Enterprise (78): A public Discovery document for v1, revision 20261022 on 1 November, with 278 methods and 993 schemas, StreamAssist and the A2A methods among them (25). docs.cloud.google.com/llms.txt answers 404 (1 November). A page address with `.md.txt` added answers as Markdown, as the release notes, quotas and compliance pages did on 1 November, which no page we read links, so half (5 of 10). StreamAssist's description is one line, while the guide says when to use the API rather than the web app and what sessions and files do (12 of 20). 3,421 of 3,448 properties carry a description and 245 are enums, counted on revision 20261004. Required and optional are stated in each description, and `inputVariables` for workflow agents is a free Struct (11 of 15). The guide has a curl request with a full streamed response and the reference covers seven client libraries. No Gemini Enterprise page listing error codes was found (10 of 15). v1, v1beta and v1alpha versions and dated release notes, the newest on 30 October 2026 (15).\n- Microsoft MCP Server for Enterprise (29): The three tools (microsoft_graph_suggest_queries, microsoft_graph_get, microsoft_graph_list_properties) are described in prose on the overview. Their schemas need an Entra tenant to list, so no contract was read (0 of 25). learn.microsoft.com serves Markdown to agents, as for the other Microsoft listings (10). The overview says what each tool does and the workflow they follow, but not when not to use them (12 of 20). Input types weren't readable (0 of 15). A sample prompts page and a Kusto query for its logs, but no documented error responses (7 of 15). No version or changelog found (0). 0 + 10 + 12 + 0 + 7 + 0 = 29.\n\n### Maintenance \u0026 community: Gemini Enterprise +37\n\n- Gemini Enterprise (80): Read as a closed service with official client libraries. Newest release notes dated 30 October 2026 (Gemini Notebook Enterprise refresh, GA, and the S\u0026P Global data store in Preview), after the Brazil region on 28 October, VPC connectivity for custom MCP servers on 27 October and single-user quota limits on 22 October (30). Dozens of dated release note entries since August, 14 dates between 1 and 30 October alone (20). Dated release notes, Google Cloud support and public issue trackers for the client libraries. We didn't test support (10 of 15). Official client libraries, npm `@google-cloud/discoveryengine` 3.4.0 on 12 October 2026 and the Python library's tag `google-cloud-discoveryengine-v0.20.5`, per the 17 October check, not re-read on 1 November (15). The Python library is still below 1.0 and declares Python 3.10 or later, per the 10 October check. CI results weren't checked (5 of 10).\n- Microsoft MCP Server for Enterprise (43): General availability announced on 17 November 2026 (30). No three dated changes in 90 days were found (0). Questions are answered on Microsoft Q\u0026A, and support goes through Microsoft's channels (8 of 15). The GitHub MCP registry shows an entry under microsoft, seen in a search only, so not counted (0, unchecked). A hosted service with no package to keep current (5 of 10). 30 + 0 + 8 + 0 + 5 = 43.\n\n### Payments \u0026 pricing: Microsoft MCP Server for Enterprise +35\n\n- Gemini Enterprise (15): Hosted rubric. No x402, MPP or L402 (0). No seat prices were found on Google's product, editions, licences or quotas pages, and the product page sends buyers to sales or a trial. Pay-as-you-go and overages are priced publicly by reference, $5 per GiB a month for storage over quota and Agent Platform prices for assistant queries, without a per-query figure. Claude models in the app, GA on 15 October, are charged pay as you go with no price on the release note. Counted as plan-level pricing that's public (10, a judgement call). A 30-day Plus trial needs no sales contact (product page re-read on 1 November), but it runs through the Google Cloud Free Trial, which asks for a credit card or other payment method (0). A person creates the project, billing account and app in the console and assigns licences (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.\n- Microsoft MCP Server for Enterprise (50): No payment protocol (0). The overview says there's no additional cost or separate licence to enable it, published without a login (30). It's free, but it needs a Microsoft Entra tenant, and some data needs Entra ID P2 or ID Governance licences (20 of 30). An administrator provisions it with PowerShell and grants each client in the tenant (0). 0 + 30 + 20 + 0 = 50.\n\n### Reliability: Gemini Enterprise +32\n\n- Gemini Enterprise (85): Hosted reading, scored on the StreamAssist method of the Discovery Engine API. The Google Cloud status page lists Gemini Enterprise and Vertex AI Search as products (products.json, re-read on 1 November) and has a JSON incident feed (20). Re-read on 1 November, the feed has four incidents in the window from 3 August, on 20 August (27 products), 1 September (us-central1-b), 8 and 9 October (Cloud Storage) and 20 October (europe-west2, 38 products), and none names Gemini Enterprise, Vertex AI Search or another Gemini product (30). Rate quotas with numbers, 300 complete-query and 300 regional search requests a minute per project, and assistant quotas per licence, 160 queries a day on Standard and 200 on Plus, pooled per edition, project and location, re-read on 1 November (15). No retry or backoff guidance and no 429 handling on the StreamAssist guide or the quotas page (re-read on 1 November), and each call writes to a session, so a retry isn't documented as safe (0 of 15). The Gemini Enterprise SLA, last modified 22 April 2026 and still written for Google Agentspace, commits to 99.5 per cent monthly uptime for StreamAssist and 99.9 for Search, with credits from 10 to 50 per cent (10). StreamAssist is in the v1 API and its guide marks only file upload as Preview (10).\n- Microsoft MCP Server for Enterprise (53): Hosted MCP lines. Microsoft's cloud status page at status.cloud.microsoft, as for the Copilot Studio MCP listing (20). No incident history for this service could be read, so 5 of 30 and said so. Rate limit published, 100 calls a minute per user (15). The overview says calls honour Graph throttling limits but gives no 429 or Retry-After guidance of its own (8 of 15). No SLA found for it (0). Microsoft's Book of News of 17 November 2026 lists it as generally available, but the overview page read on 18 November still says preview, so half (5 of 10, a judgement call). 20 + 5 + 15 + 8 + 0 + 5 = 53.\n\n### Transparency \u0026 trust: Gemini Enterprise +25\n\n- Gemini Enterprise (82): Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15 of 30). The product page says prompts, outputs and tuning are never used to train Google models or other customers' models, and the security overview says user-requested data is deleted within 60 days. The Cloud terms and Data Processing Addendum weren't re-read today, and retention for sessions and memory wasn't found (20 of 30). The Cloud terms promise 12 months' notice before a backwards-incompatible API change, per the 9 October Document AI check, not re-read on 10 October. The release notes, re-read on 1 November, gave 19 days' notice (1 to 20 October) for removing Gemini 2.5 Pro from the Canada and Japan regions, done on 20 October, and four days' notice (22 to 26 October) for the AlphaEvolve default model and price change, both in the listing's deprecations (12 of 20). Global, `us` and `eu` multi-regions with data residency limits stated, and Google Cloud's public sub-processor list per the 9 October check (17 of 20).\n- Microsoft MCP Server for Enterprise (57): Closed service under the Microsoft APIs Terms of Use (15). Requests run through Microsoft Graph and are logged there, but no retention or data-handling statement specific to the server was found (12 of 30). No deprecation policy for it, and the pages still carry preview wording (0 of 20). The overview lists the clouds it's available in (8 of 20). 15 + 12 + 0 + 8 = 35.\n\n### Security \u0026 auth: Microsoft MCP Server for Enterprise +8\n\n- Gemini Enterprise (77): OAuth 2.0 bearer tokens from user credentials, service accounts or workforce identity federation, with IAM permissions. StreamAssist accepts the narrow `discoveryengine.assist.readwrite` scope among four (30), less 10 because Google's OAuth 2.0 web-server guide documents sending the token as an `access_token` query parameter, the v1 Discovery document (revision 20261022) lists `access_token` and `oauth_token` as parameters, and on 1 November (as on 17 October) a made-up token sent as `?access_token=` came back 'invalid authentication credentials' where no token came back 'missing required authentication credential', so the API reads a token from the URL. The Gemini Enterprise docs send it only in the `Authorization` header, which doesn't remove the documented option. Read as the Workspace APIs were on 17 October (20). Google's OAuth platform can bind refresh tokens to a client key with DPoP from 15 October 2026, while access tokens stay bearer tokens, so the line doesn't move for it. Gemini Enterprise User can be granted per app through the Restricted User pattern, a custom role can hold only `discoveryengine.assistants.assist`, and VPC Service Controls apply. The assistant can run connector actions such as sending Outlook mail, and we didn't read how it asks for confirmation (14 of 20). Model Armor screens the assistant's prompts and responses on every edition at no extra cost, but it's off until an admin enables it and can be set to let traffic through unscreened when it's unavailable, per the 10 October check (10 of 15). Cloud Audit Logs list each method by permission type, and usage audit logs can record prompts and responses when that setting is on. Data Access logs are off by default in Google Cloud, per the 10 October check (13 of 15). google.com security.txt is valid to 1 April 2030 with the reward programme, and the compliance page lists ISO 27001, 27017 and 27018, SOC 1, 2 and 3, HIPAA, FedRAMP Moderate and High, PCI DSS and C5, both re-read on 1 November (20), the reading most Google Cloud listings in this run take. Total 77.\n- Microsoft MCP Server for Enterprise (85): Microsoft Entra delegated OAuth: an administrator registers the server and grants each MCP client its scopes, and the server enforces the user's own privileges and those scopes (30). Read-only Graph calls only (20). It returns directory data, names and attributes that users and admins can edit, with no prompt-injection guidance found (5 of 15). Every request lands in Microsoft Graph activity logs, with a Kusto query to filter the server's app ID (15). Microsoft's security programme and certifications, but microsoft.com's security.txt had expired per the Copilot Studio MCP listing (15 of 20). 30 + 20 + 5 + 15 + 15 = 85.\n\n## Score by category\n\n| Category | Weight | Gemini Enterprise | Microsoft MCP Server for Enterprise | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 85 | 53 | Gemini Enterprise +32 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 78 | 29 | Gemini Enterprise +49 |\n| Agent ergonomics | 13% | 48 | 55 | Microsoft MCP Server for Enterprise +7 |\n| Security \u0026 auth | 14% | 77 | 85 | Microsoft MCP Server for Enterprise +8 |\n| Payments \u0026 pricing | 10% | 15 | 50 | Microsoft MCP Server for Enterprise +35 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 80 | 43 | Gemini Enterprise +37 |\n| Transparency \u0026 trust | 7% | 82 | 57 | Gemini Enterprise +25 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **67 · B** | **54.1 · C** | |\n\n## Facts side by side\n\n| Fact | Gemini Enterprise | Microsoft MCP Server for Enterprise |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Google | Microsoft |\n| Hosted endpoint | no (local only) | `https://mcp.svc.cloud.microsoft/enterprise` |\n| Transports | HTTP | Streamable HTTP |\n| Auth | OAuth | OAuth |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | Proprietary service under the Google Cloud terms. The client libraries are Apache-2.0 | Closed service under the Microsoft APIs Terms of Use |\n| Tools exposed | none | 3 |\n| Read-only variant documented | no | yes |\n| llms.txt | no | no |\n| Last release | 2026-10-30 | 2026-11-17 |\n| Terms last updated | 2026-09-02 | 2025-10-01 |\n| Privacy policy last updated | 2026-09-28 | 2026-09-01 |\n| Customer content may train models | not found in the text | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 139k npm/wk, 1.2M PyPI/wk | none |\n| Agent reviews | 2.8/5 (4) | none |\n\n## How the scores have moved\n\n### Gemini Enterprise\n\n- +0.6 on 13 November 2026: checklist\n- -1.7 on 17 October 2026: correction\n\n### Microsoft MCP Server for Enterprise\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Gemini Enterprise.** The assistant is callable through a GA v1 method with a 99.5 per cent SLA, OAuth through IAM, a public Discovery document and optional Model Armor screening. Seat prices weren't found on Google's pages, onboarding needs a billing account and a person, and the API also reads OAuth tokens from a URL query parameter.\n\n**Microsoft MCP Server for Enterprise.** A free, read-only MCP server over a Microsoft Entra tenant's directory, with Entra-scoped access and every call in Graph's activity logs. It needs an administrator to provision it per tenant, and its tool schemas, errors and changelog aren't public.\n\n## Before you call either\n\n### Gemini Enterprise\n\n1. Create a Gemini Enterprise app first. StreamAssist needs its APP_ID, and the caller needs `discoveryengine.assistants.assist`\n2. Send `X-Goog-User-Project` with your project ID when calling with Application Default Credentials\n3. Pass the `session` name from the final stream message on the next call to keep context. Leaving it empty starts a new session\n4. Read `connectorAuthErrors` in the response. A connector that failed sign-in is skipped and the answer comes from the rest\n5. Use the A2A URL returned by Agent Registry verbatim. It takes the project number, not the project ID\n6. Send the token in the `Authorization: Bearer` header, not as `?access_token=`, which the API also accepts and which puts the token in the URL\n\n### Microsoft MCP Server for Enterprise\n\n1. Connect to https://mcp.svc.cloud.microsoft/enterprise with an Entra token for a client your administrator has granted\n2. Call microsoft_graph_suggest_queries first to find the Graph call, then microsoft_graph_get to run it\n3. Expect only reads; it can't change anything in the tenant\n4. Stay under 100 calls a minute per user\n\n## Questions\n\n### Which is better for AI agents, Gemini Enterprise or Microsoft MCP Server for Enterprise?\n\nGemini Enterprise scores 67 (B) on agent readiness against Microsoft MCP Server for Enterprise's 54.1 (C), and leads in 4 of 7 scored categories. Microsoft MCP Server for Enterprise leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.\n\n### Do Gemini Enterprise and Microsoft MCP Server for Enterprise need an API key?\n\nBoth use an OAuth sign-in.\n\n### Can an agent call Gemini Enterprise and Microsoft MCP Server for Enterprise without installing anything?\n\nNo hosted endpoint is listed for Gemini Enterprise. Microsoft MCP Server for Enterprise has a hosted endpoint at https://mcp.svc.cloud.microsoft/enterprise.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-enterprise\", \"b\": \"microsoft-mcp-server-enterprise\"}`. From a terminal: `anchor compare gemini-enterprise microsoft-mcp-server-enterprise`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-enterprise.json and https://www.anchorterminal.com/api/v1/tools/microsoft-mcp-server-enterprise.json\n\n## Other comparisons with Gemini Enterprise or Microsoft MCP Server for Enterprise\n\n- [Alation vs Gemini Enterprise](https://www.anchorterminal.com/compare/alation-vs-gemini-enterprise.md)\n- [Alation vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/alation-vs-microsoft-mcp-server-enterprise.md)\n- [Atlan vs Gemini Enterprise](https://www.anchorterminal.com/compare/atlan-vs-gemini-enterprise.md)\n- [Atlan vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/atlan-vs-microsoft-mcp-server-enterprise.md)\n- [Cohere North vs Gemini Enterprise](https://www.anchorterminal.com/compare/cohere-north-vs-gemini-enterprise.md)\n- [Cohere North vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/cohere-north-vs-microsoft-mcp-server-enterprise.md)\n- [Collibra vs Gemini Enterprise](https://www.anchorterminal.com/compare/collibra-vs-gemini-enterprise.md)\n- [Collibra vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/collibra-vs-microsoft-mcp-server-enterprise.md)\n- [Dust vs Gemini Enterprise](https://www.anchorterminal.com/compare/dust-vs-gemini-enterprise.md)\n- [Dust vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/dust-vs-microsoft-mcp-server-enterprise.md)\n- [Gemini Enterprise vs Glean](https://www.anchorterminal.com/compare/gemini-enterprise-vs-glean.md)\n- [Gemini Enterprise vs Guru](https://www.anchorterminal.com/compare/gemini-enterprise-vs-guru.md)\n- [Gemini Enterprise vs Hexis Cloud](https://www.anchorterminal.com/compare/gemini-enterprise-vs-hexis.md)\n- [Gemini Enterprise vs Onyx](https://www.anchorterminal.com/compare/gemini-enterprise-vs-onyx.md)\n- [Gemini Enterprise vs Overclock](https://www.anchorterminal.com/compare/gemini-enterprise-vs-overclock.md)\n- [Gemini Enterprise vs Procore AI Go](https://www.anchorterminal.com/compare/gemini-enterprise-vs-procore-ai-go.md)\n- [Gemini Enterprise vs Secoda](https://www.anchorterminal.com/compare/gemini-enterprise-vs-secoda.md)\n- [Gemini Enterprise vs Lens (Thought Industries)](https://www.anchorterminal.com/compare/gemini-enterprise-vs-thought-industries-lens.md)\n- [Glean vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/glean-vs-microsoft-mcp-server-enterprise.md)\n- [Guru vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/guru-vs-microsoft-mcp-server-enterprise.md)\n- [Hexis Cloud vs Microsoft MCP Server for Enterprise](https://www.anchorterminal.com/compare/hexis-vs-microsoft-mcp-server-enterprise.md)\n- [Microsoft MCP Server for Enterprise vs Onyx](https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-onyx.md)\n- [Microsoft MCP Server for Enterprise vs Overclock](https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-overclock.md)\n- [Microsoft MCP Server for Enterprise vs Procore AI Go](https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-procore-ai-go.md)\n- [Microsoft MCP Server for Enterprise vs Secoda](https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-secoda.md)\n- [Microsoft MCP Server for Enterprise vs Lens (Thought Industries)](https://www.anchorterminal.com/compare/microsoft-mcp-server-enterprise-vs-thought-industries-lens.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Gemini Enterprise vs Microsoft MCP Server for Enterprise",
        "url": ""
      }
    ],
    "description": "Gemini Enterprise scores 67 (B) to Microsoft MCP Server for Enterprise's 54.1 (C) for company knowledge search. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Gemini Enterprise B 67",
      "Microsoft MCP Server for Enterprise C 54.1",
      "scores"
    ],
    "h1": "Gemini Enterprise vs Microsoft MCP Server for Enterprise",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Gemini Enterprise vs Microsoft MCP Server for Enterprise (2026)",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/gemini-enterprise-vs-microsoft-mcp-server-enterprise"
  },
  "tokens": {
    "markdown": 5600,
    "slim": 1180
  },
  "version": 1
}
