{ "data": { "a": { "slug": "copilot-studio-mcp", "name": "Microsoft Copilot Studio MCP", "vendor": "Microsoft", "vendorUrl": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/", "kind": "mcp", "category": "workflow-automation", "summary": "Microsoft's official MCP server for Copilot Studio, a local stdio bridge run with npx. After Microsoft work-account sign-in it exposes Copilot Studio's hosted tools for building, testing and monitoring agents and workflows, and for connector setup.", "url": "https://www.anchorterminal.com/tools/copilot-studio-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/copilot-studio-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/copilot-studio-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/copilot-studio-mcp.json", "repo": "https://github.com/microsoft/copilot-studio-mcp", "license": "No licence in the npm package. The GitHub repository's LICENSE is MIT, but the repository holds no source code", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "@microsoft/copilot-studio-mcp" } ], "auth": "oauth", "authNotes": "Microsoft Entra ID sign-in with a work or school account, in the browser through a localhost redirect, using a fixed public client (the VS Code client, `51f81489-12ee-4a9e-aaae-a2591f45987d`). Client-ID and tenant overrides are not supported, and personal Microsoft accounts are refused. The bridge requests delegated Power Platform API scopes per step, which are `EnvironmentManagement.Environments.Read` for discovery, `CopilotFlows.ChatAssistant.Execute` for the Copilot Studio service, and `Connectivity.Connectors.Read`, `Connectivity.Connections.Read` and `Connectivity.Connections.Write` for connector setup. Tokens stay in process memory and are discarded on sign-out or exit, so each restart needs a new sign-in. No device-code or service-principal route was found in the package (checked 2026-10-17). The README says installing the package grants no licence, tenant consent or environment permission.", "pricing": "usage", "pricingNotes": "The package is free. Use of Copilot Studio is measured in Copilot Credits, sold as tenant-wide packs of 25,000 credits at $200.00 a pack a month, as a pay-as-you-go meter billed to an Azure subscription, or as a one-year prepurchase plan, per Microsoft's pricing page. For agents, workflows and apps on the GitHub Copilot harness, credits are charged from the moment building starts, including previews, tests and evaluations, and credits per task vary. An individual can sign up for a Copilot Studio trial with a work account, but the trial article covers the standard harness and trial agents can't be published. No card requirement was stated on the pages read (checked 2026-10-17).", "priceSummary": "$200 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the package source, README, pricing page or billing docs (checked 2026-10-17). Credits are bought through Microsoft licensing or an Azure subscription.", "endpoints": [] }, "toolCount": 14, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://www.npmjs.com/package/@microsoft/copilot-studio-mcp", "registryName": "com.microsoft/copilot-studio", "capabilities": [ "automation.workflows", "automation.apps" ], "tags": [ "official", "mcp", "local", "npm", "oauth", "entra-id", "enterprise", "usage-priced", "new" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 53.1, "grade": "D", "agentReady": false, "rank": 798, "ranked": true, "rankOf": 1133, "categoryRank": 16, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 55, "payments": 20, "reliability": 46, "schema": 53, "security": 70, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Entra sign-in with per-resource scopes, tokens kept only in memory, and a plan-then-confirm step before connector writes. The package is a day old, the linked MIT repository holds no source, no changelog or support channel exists, the five cloud tools' schemas are visible only after sign-in, and workflow tests run live workflows billed in Copilot Credits.", "bestFor": "Teams already on Copilot Studio that want a coding agent or CLI to build, test, deploy and monitor Copilot Studio agents and workflows, and to set up their connectors.", "strengths": [ "Microsoft Entra sign-in with delegated Power Platform scopes requested per step, tokens held only in memory and personal accounts refused", "Connector setup is split into a read-only plan and a write that needs the plan ID and `confirm: true`", "All nine local tools carry readOnlyHint, destructiveHint and idempotentHint annotations, and the connector write is marked destructive", "Errors say whether a write may have completed and whether a retry is safe, with distinct network cause codes", "Listed in the official MCP registry under the DNS-verified `com.microsoft` namespace" ], "weaknesses": [ "First published on 16 October 2026, with two releases and no release notes or changelog", "The repository holds no source, and the npm package carries no licence, so the MIT label covers only an empty repository", "The five service tools are dispatchers taking `action` and `parameters`, and their schemas are readable only after sign-in", "No headless sign-in. Each restart needs a browser sign-in with a work account", "SUPPORT.md is Microsoft's unedited template, so no support channel is named" ], "agentNotes": [ "Call `copilot_studio_status` first and reuse a ready session. Don't reconnect or reselect an environment to start a new task", "Read an action's contract with `discover_resources` and `action=describe_actions` before building unfamiliar `parameters`", "Ask the person before testing a workflow. Tests run published, enabled workflows and can have real effects", "Never retry an uncertain write. Inspect the agent, workflow or connection first, as the error text says", "Expect a browser sign-in after every restart. Tell the person a window is opening and never ask for credentials in chat" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.1 } ], "editorialScores": { "ergonomics": 62, "maintenance": 55, "payments": 20, "reliability": 46, "schema": 53, "security": 70, "transparency": 47 }, "provenanceScore": 83 }, "connect": { "install": "npx -y @microsoft/copilot-studio-mcp@latest", "config": { "mcpServers": { "copilot-studio-mcp": { "args": [ "-y", "@microsoft/copilot-studio-mcp@latest" ], "command": "npx" } } } }, "letme": { "capability": "https://letme.dev/automation.workflows", "tool": "https://letme.dev/copilot-studio-mcp" }, "sameCompany": [ "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", "azure-document-intelligence", "azure-devops-mcp", "microsoft-learn-mcp", "playwright-mcp", "azure-mcp", "azure-maps", "azure-translator", "microsoft-graph-calendar", "azure-blob-storage", "onedrive-sharepoint", "microsoft-teams", "dynamics-365-sales", "power-automate", "foundry-local", "microsoft-decision-1", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph", "microsoft-graph-people" ], "area": "business", "unitPrices": [ { "item": "Copilot Credit pack, 25,000 credits", "unit": "month", "usd": 200, "note": "Tenant-wide. Pay-as-you-go through an Azure subscription and a one-year prepurchase plan also exist. The package adds no charge" } ], "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "domainNote": "The bridge connects to api.powerplatform.com, environment.api.powerplatform.com and login.microsoftonline.com, all Microsoft domains. microsoft.com publishes a security.txt, but it passed its Expires date on 2026-09-23.", "endpointOnVendorDomain": true, "terms": "https://go.microsoft.com/fwlink/?linkid=2182773", "privacy": "https://www.microsoft.com/en-us/privacy/privacystatement", "statusPage": "https://status.cloud.microsoft", "changelog": "", "securityTxt": "expired", "checked": "2026-10-17", "notes": [ "The repository's LICENSE reads Copyright (c) Microsoft Corporation, and the npm package is published by Microsoft's `microsoft1es` and `microsoft-oss-releases` accounts.", "Copilot Studio's security and governance page says the service is governed by the customer's commercial agreements, the Microsoft Product Terms (the terms link) and the Data Protection Addendum. Neither document was read today.", "The privacy link is the Microsoft privacy statement, carried from our other Microsoft listings and not read again today.", "https://www.microsoft.com/.well-known/security.txt carries Expires 2026-09-23T16:00:00.000Z when read on 2026-10-17, with the MSRC researcher portal as contact.", "status.cloud.microsoft returned only its page shell to our reader. Power Platform service health for a tenant is in the admin centres behind an admin sign-in.", "No changelog was found for the package. Its npm versions carry no release notes and the repository has no tags or CHANGELOG file.", "Domain registration date carried from our other Microsoft listings (RDAP, 1991-05-02), not looked up again today." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/copilot-studio-mcp.json", "live": { "slug": "copilot-studio-mcp", "vendorStatus": { "page": "https://status.cloud.microsoft", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-17T22:50:56.033601452Z" }, "pages": [ { "url": "https://go.microsoft.com/fwlink/?linkid=2182773", "kind": "terms", "status": 0, "checkedAt": "2026-10-17T23:03:42.503848369Z", "changedAt": "0001-01-01T00:00:00Z", "blockedByRobots": true } ], "updatedAt": "2026-10-17T23:03:42.503848369Z" } }, "answer": "Tray.ai API + MCP scores 55.5 (C) on agent readiness against Microsoft Copilot Studio MCP's 53.1 (D), and leads in 4 of 7 scored categories. Microsoft Copilot Studio MCP leads on agent ergonomics and payments \u0026 pricing.", "b": { "slug": "tray", "name": "Tray.ai API + MCP", "vendor": "Tray.ai", "vendorUrl": "https://tray.ai", "kind": "http-api", "category": "workflow-automation", "summary": "Low-code integration platform with an embedded product for SaaS vendors.", "url": "https://www.anchorterminal.com/tools/tray", "markdownUrl": "https://www.anchorterminal.com/tools/tray.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tray.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tray.json", "license": "proprietary", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.tray.io/core/v1", "packages": [], "auth": "mixed", "authNotes": "REST and GraphQL endpoints take a bearer token, either the org master token (you act) or an end user's user token (you act as them). Tray Headless MCP uses a one-time OAuth2 sign-in bound to one workspace, and the docs say not to send a static Authorization header. Agent Gateway MCP servers take OAuth2 or an API token, and API token users can't use per-user credentials.", "pricing": "paid", "pricingNotes": "Pro, Team and Enterprise plans, all quoted by sales and billed on tasks that cover integration, automation, MCP and agent use. Every plan lists full API access and Tray Headless, and Agent Gateway is an add-on. A free trial exists with no stated length. No prices are published (https://tray.ai/pricing/).", "priceSummary": "Paid", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 support in Tray docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://tray.ai/documentation/developer/getting-started/introduction", "llmsTxt": "https://tray.ai/documentation/llms.txt", "openapi": "https://tray.ai/documentation/files/openapi/trayapi.yaml", "capabilities": [ "automation.workflows", "automation.apps", "automation.embedded", "automation.code", "automation.webhooks", "automation.auth", "agent.tools" ], "tags": [ "hosted", "mcp", "llms-txt", "openapi", "enterprise", "closed-source", "webhooks" ], "lastRelease": "2026-09-09", "graded": true, "anchor": { "graded": true, "score": 55.5, "grade": "C", "agentReady": false, "rank": 728, "ranked": true, "rankOf": 1133, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 33, "maintenance": 60, "payments": 0, "reliability": 72, "schema": 80, "security": 66, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Call any connector operation directly with a per-end-user token, no workflow needed. No published prices and no self-serve plan.", "bestFor": "SaaS vendors embedding integrations for their customers, with an agent that acts per end user.", "strengths": [ "Call any connector operation directly with a per-end-user token, no workflow needed", "Published API limits, 30 requests a second with bursts to 50", "Every action logged and streamable, with settable retention and log masking", "Four minor incidents in 90 days, none on the core APIs", "US, EU and APAC regions, SOC 2 Type 2 and a pentest dated 23 September 2026" ], "weaknesses": [ "No published prices and no self-serve plan", "Upstream 429s are wrapped in a 200, which hides throttling from naive retry logic", "Headless MCP can delete projects, workflows and auths with no server-side confirmation", "No official SDK and no tool annotations", "API lives on api.tray.io while the brand, docs and legal pages are on tray.ai" ], "agentNotes": [ "Use a user token when acting for a customer and the master token only for admin work", "Parse the body of call-connector responses for upstream status codes before treating a 200 as success", "Point Headless MCP at the workspace's region, api.eu1.tray.io or api.ap1.tray.io outside the US", "Pick the workspace at OAuth sign-in. Headless MCP binds it to the session and takes no workspace ID", "Ask before any Headless MCP delete. The server won't" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.5 } ], "editorialScores": { "ergonomics": 33, "maintenance": 60, "payments": 0, "reliability": 72, "schema": 80, "security": 66, "transparency": 67 }, "provenanceScore": 68 }, "connect": { "http": "curl https://api.tray.io/core/v1/connectors -H \"Authorization: Bearer $TRAY_MASTER_TOKEN\"", "claudeCode": "claude mcp add --transport http tray https://api.tray.io/mcp", "config": { "mcpServers": { "tray": { "url": "https://api.tray.io/mcp" } } } }, "letme": { "capability": "https://letme.dev/automation.workflows", "tool": "https://letme.dev/tray" }, "area": "business", "provenance": { "legalEntity": "Tray.ai, Inc.", "domain": "tray.ai", "domainRegistered": "2017-12-15", "domainNote": "The API and MCP hosts are on tray.io, the company's former domain. The brand, docs and legal pages are on tray.ai.", "endpointOnVendorDomain": false, "terms": "https://tray.ai/legal/msa/", "privacy": "https://tray.ai/legal/privacy-policy/", "statusPage": "https://status.tray.ai/", "changelog": "https://tray.ai/documentation/releases", "securityTxt": "none", "checked": "2026-09-30", "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tray.json", "live": { "slug": "tray", "probe": { "target": "https://api.tray.io/core/v1", "method": "get", "lastAt": "2026-10-18T00:14:59.809599796Z", "lastOk": true, "lastStatus": 404, "lastMs": 427, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 448, "p95ms24h": 507, "samples24h": 253, "samples30d": 4435, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 3, "ok": 3 } ] }, "vendorStatus": { "page": "https://status.tray.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-18T00:09:10.773592552Z" }, "securityTxt": { "url": "https://tray.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-17T15:51:57.860037499Z" }, "llmsTxt": { "url": "https://tray.ai/documentation/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:23:24.68872115Z" }, "domain": { "domain": "tray.ai", "registered": "2017-12-15", "source": "https://rdap.identitydigital.services/rdap/domain/tray.ai", "checkedAt": "2026-10-11T13:16:16.323547509Z" }, "pages": [ { "url": "https://tray.ai/documentation/releases", "kind": "changelog", "status": 200, "checkedAt": "2026-10-17T23:11:40.598232585Z", "changedAt": "2026-10-13T20:24:33.342752361Z", "fingerprint": "80f020bccec2" }, { "url": "https://tray.ai/pricing/", "kind": "pricing", "status": 304, "checkedAt": "2026-10-17T23:11:46.655265295Z", "changedAt": "2026-10-09T18:46:52.378504753Z", "fingerprint": "e773c5032772" }, { "url": "https://tray.ai/legal/privacy-policy/", "kind": "privacy", "status": 304, "checkedAt": "2026-10-17T23:11:44.661526743Z", "changedAt": "2026-10-14T21:08:48.107030519Z", "fingerprint": "dcf6c626e512" }, { "url": "https://tray.ai/legal/msa/", "kind": "terms", "status": 304, "checkedAt": "2026-10-17T23:11:42.99977915Z", "changedAt": "2026-10-09T18:46:48.485504457Z", "fingerprint": "7736d8f805ae" } ], "updatedAt": "2026-10-18T00:14:59.809599796Z" } }, "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Microsoft", "b": "Tray.ai", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.tray.io/core/v1", "name": "Hosted endpoint" }, { "a": "stdio", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Paid", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "No licence in the npm package. The GitHub repository's LICENSE is MIT, but the repository holds no source code", "b": "proprietary", "name": "Licence" }, { "a": "14", "b": "none", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "com.microsoft/copilot-studio", "b": "not listed", "name": "MCP registry" }, { "a": "2026-10-16", "b": "2026-09-09", "name": "Last release" }, { "a": "", "b": "2025-01-28", "name": "Terms last updated" }, { "a": "2026-09-01", "b": "2026-01-01", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "2.5/5 (4)", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Tray.ai API + MCP scores 55.5 (C) on agent readiness against Microsoft Copilot Studio MCP's 53.1 (D), and leads in 4 of 7 scored categories. Microsoft Copilot Studio MCP leads on agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, Microsoft Copilot Studio MCP or Tray.ai API + MCP?" }, { "answer": "Microsoft Copilot Studio MCP uses an OAuth sign-in. Tray.ai API + MCP takes an API key or an OAuth sign-in.", "question": "Do Microsoft Copilot Studio MCP and Tray.ai API + MCP need an API key?" }, { "answer": "Microsoft Copilot Studio MCP runs on your own machine, with no hosted endpoint listed. Tray.ai API + MCP has a hosted endpoint at https://api.tray.io/core/v1.", "question": "Can an agent call Microsoft Copilot Studio MCP and Tray.ai API + MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 62 against 33", "Payments \u0026 pricing, 20 against 0" ], "also": [ "Runs on your own machine" ], "goodFor": "Teams already on Copilot Studio that want a coding agent or CLI to build, test, deploy and monitor Copilot Studio agents and workflows, and to set up their connectors.", "slug": "copilot-studio-mcp", "watchFor": "First published on 16 October 2026, with two releases and no release notes or changelog" }, { "aheadOn": [ "Reliability, 72 against 46", "Schema \u0026 documentation, 80 against 53", "Maintenance \u0026 community, 60 against 55" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "SaaS vendors embedding integrations for their customers, with an agent that acts per end user.", "slug": "tray", "watchFor": "No published prices and no self-serve plan" } ], "job": { "capability": "automation.workflows", "name": "Workflow automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/activepieces-vs-copilot-studio-mcp.json", "title": "Activepieces API + MCP vs Microsoft Copilot Studio MCP", "url": "https://www.anchorterminal.com/compare/activepieces-vs-copilot-studio-mcp" }, { "json": "https://www.anchorterminal.com/compare/activepieces-vs-tray.json", "title": "Activepieces API + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/activepieces-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-gumloop.json", "title": "Microsoft Copilot Studio MCP vs Gumloop", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-gumloop" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-kestra.json", "title": "Microsoft Copilot Studio MCP vs Kestra", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-kestra" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-make.json", "title": "Microsoft Copilot Studio MCP vs Make API + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-make" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-n8n.json", "title": "Microsoft Copilot Studio MCP vs n8n API + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-n8n" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-node-red.json", "title": "Microsoft Copilot Studio MCP vs Node-RED", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-node-red" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon.json", "title": "Microsoft Copilot Studio MCP vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-pipedream.json", "title": "Microsoft Copilot Studio MCP vs Pipedream API + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-pipedream" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-power-automate.json", "title": "Microsoft Copilot Studio MCP vs Microsoft Power Automate", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-power-automate" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-prismatic.json", "title": "Microsoft Copilot Studio MCP vs Prismatic", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-prismatic" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-windmill.json", "title": "Microsoft Copilot Studio MCP vs Windmill API + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-windmill" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-workato.json", "title": "Microsoft Copilot Studio MCP vs Workato API + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-workato" }, { "json": "https://www.anchorterminal.com/compare/gumloop-vs-tray.json", "title": "Gumloop vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/gumloop-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/kestra-vs-tray.json", "title": "Kestra vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/kestra-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/make-vs-tray.json", "title": "Make API + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/make-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/n8n-vs-tray.json", "title": "n8n API + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/n8n-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/node-red-vs-tray.json", "title": "Node-RED vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/node-red-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/pipedream-vs-tray.json", "title": "Pipedream API + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/pipedream-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/power-automate-vs-tray.json", "title": "Microsoft Power Automate vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/power-automate-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/prismatic-vs-tray.json", "title": "Prismatic vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/prismatic-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/tray-vs-windmill.json", "title": "Tray.ai API + MCP vs Windmill API + MCP", "url": "https://www.anchorterminal.com/compare/tray-vs-windmill" }, { "json": "https://www.anchorterminal.com/compare/tray-vs-workato.json", "title": "Tray.ai API + MCP vs Workato API + MCP", "url": "https://www.anchorterminal.com/compare/tray-vs-workato" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-tray.json", "title": "Paragon ActionKit + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/paragon-vs-tray" } ], "scores": [ { "by": 26, "copilot-studio-mcp": 46, "edge": "tray", "key": "reliability", "name": "Reliability", "tray": 72, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 27, "copilot-studio-mcp": 53, "edge": "tray", "key": "schema", "name": "Schema \u0026 documentation", "tray": 80, "weight": 13 }, { "by": 29, "copilot-studio-mcp": 62, "edge": "copilot-studio-mcp", "key": "ergonomics", "name": "Agent ergonomics", "tray": 33, "weight": 13 }, { "by": 4, "copilot-studio-mcp": 70, "edge": "copilot-studio-mcp", "key": "security", "name": "Security \u0026 auth", "tray": 66, "weight": 14 }, { "by": 20, "copilot-studio-mcp": 20, "edge": "copilot-studio-mcp", "key": "payments", "name": "Payments \u0026 pricing", "tray": 0, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 5, "copilot-studio-mcp": 55, "edge": "tray", "key": "maintenance", "name": "Maintenance \u0026 community", "tray": 60, "weight": 7 }, { "by": 3, "copilot-studio-mcp": 65, "edge": "tray", "key": "transparency", "name": "Transparency \u0026 trust", "tray": 68, "weight": 7 } ], "summary": "Tray.ai API + MCP scores 55.5 (C) on agent readiness against Microsoft Copilot Studio MCP's 53.1 (D), and leads in 4 of 7 scored categories. Microsoft Copilot Studio MCP leads on agent ergonomics and payments \u0026 pricing. Both do workflow automation.", "tutorials": [], "verdicts": { "copilot-studio-mcp": "Entra sign-in with per-resource scopes, tokens kept only in memory, and a plan-then-confirm step before connector writes. The package is a day old, the linked MIT repository holds no source, no changelog or support channel exists, the five cloud tools' schemas are visible only after sign-in, and workflow tests run live workflows billed in Copilot Credits.", "tray": "Call any connector operation directly with a per-end-user token, no workflow needed. No published prices and no self-serve plan." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray", "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray.min.md" }, "markdown": "Tray.ai API + MCP scores 55.5 (C) on agent readiness against Microsoft Copilot Studio MCP's 53.1 (D), and leads in 4 of 7 scored categories. Microsoft Copilot Studio MCP leads on agent ergonomics and payments \u0026 pricing. Both do workflow automation.\n\n- Microsoft Copilot Studio MCP: grade D, 53.1/100, rank #798 of 1133. Markdown https://www.anchorterminal.com/tools/copilot-studio-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/copilot-studio-mcp.json\n- Tray.ai API + MCP: grade C, 55.5/100, rank #728 of 1133. Markdown https://www.anchorterminal.com/tools/tray.md · JSON https://www.anchorterminal.com/api/v1/tools/tray.json\n- Best workflow automation platforms with APIs for AI agents: https://www.anchorterminal.com/best/workflow-automation/index.md\n- All 125 workflows comparisons: https://www.anchorterminal.com/compare/workflow-automation/index.md\n\n## Which one, for what\n\n### Microsoft Copilot Studio MCP (D)\n\nGood for: Teams already on Copilot Studio that want a coding agent or CLI to build, test, deploy and monitor Copilot Studio agents and workflows, and to set up their connectors.\n\nAhead on:\n- Agent ergonomics, 62 against 33\n- Payments \u0026 pricing, 20 against 0\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: First published on 16 October 2026, with two releases and no release notes or changelog\n\n### Tray.ai API + MCP (C)\n\nGood for: SaaS vendors embedding integrations for their customers, with an agent that acts per end user.\n\nAhead on:\n- Reliability, 72 against 46\n- Schema \u0026 documentation, 80 against 53\n- Maintenance \u0026 community, 60 against 55\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No published prices and no self-serve plan\n\n\n## Score by category\n\n| Category | Weight | Microsoft Copilot Studio MCP | Tray.ai API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 46 | 72 | Tray.ai API + MCP +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 53 | 80 | Tray.ai API + MCP +27 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 33 | Microsoft Copilot Studio MCP +29 |\n| Security \u0026 auth | 14% (17.5 this run) | 70 | 66 | Microsoft Copilot Studio MCP +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 0 | Microsoft Copilot Studio MCP +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 55 | 60 | Tray.ai API + MCP +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 65 | 68 | Tray.ai API + MCP +3 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.1 · D** | **55.5 · C** | |\n\n## Facts side by side\n\n| Fact | Microsoft Copilot Studio MCP | Tray.ai API + MCP |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Microsoft | Tray.ai |\n| Hosted endpoint | no (local only) | `https://api.tray.io/core/v1` |\n| Transports | stdio | HTTP, Streamable HTTP |\n| Auth | OAuth | OAuth or key |\n| Pricing | Pay per use | Paid |\n| x402 | no | no |\n| Licence | No licence in the npm package. The GitHub repository's LICENSE is MIT, but the repository holds no source code | proprietary |\n| Tools exposed | 14 | none |\n| Read-only variant documented | yes | no |\n| llms.txt | no | yes |\n| MCP registry | `com.microsoft/copilot-studio` | not listed |\n| Last release | 2026-10-16 | 2026-09-09 |\n| Terms last updated | | 2025-01-28 |\n| Privacy policy last updated | 2026-09-01 | 2026-01-01 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Agent reviews | 2.5/5 (4) | 2.5/5 (2) |\n\n## Verdicts\n\n**Microsoft Copilot Studio MCP.** Entra sign-in with per-resource scopes, tokens kept only in memory, and a plan-then-confirm step before connector writes. The package is a day old, the linked MIT repository holds no source, no changelog or support channel exists, the five cloud tools' schemas are visible only after sign-in, and workflow tests run live workflows billed in Copilot Credits.\n\n**Tray.ai API + MCP.** Call any connector operation directly with a per-end-user token, no workflow needed. No published prices and no self-serve plan.\n\n## Before you call either\n\n### Microsoft Copilot Studio MCP\n\n1. Call `copilot_studio_status` first and reuse a ready session. Don't reconnect or reselect an environment to start a new task\n2. Read an action's contract with `discover_resources` and `action=describe_actions` before building unfamiliar `parameters`\n3. Ask the person before testing a workflow. Tests run published, enabled workflows and can have real effects\n4. Never retry an uncertain write. Inspect the agent, workflow or connection first, as the error text says\n5. Expect a browser sign-in after every restart. Tell the person a window is opening and never ask for credentials in chat\n\n### Tray.ai API + MCP\n\n1. Use a user token when acting for a customer and the master token only for admin work\n2. Parse the body of call-connector responses for upstream status codes before treating a 200 as success\n3. Point Headless MCP at the workspace's region, api.eu1.tray.io or api.ap1.tray.io outside the US\n4. Pick the workspace at OAuth sign-in. Headless MCP binds it to the session and takes no workspace ID\n5. Ask before any Headless MCP delete. The server won't\n\n## Questions\n\n### Which is better for AI agents, Microsoft Copilot Studio MCP or Tray.ai API + MCP?\n\nTray.ai API + MCP scores 55.5 (C) on agent readiness against Microsoft Copilot Studio MCP's 53.1 (D), and leads in 4 of 7 scored categories. Microsoft Copilot Studio MCP leads on agent ergonomics and payments \u0026 pricing.\n\n### Do Microsoft Copilot Studio MCP and Tray.ai API + MCP need an API key?\n\nMicrosoft Copilot Studio MCP uses an OAuth sign-in. Tray.ai API + MCP takes an API key or an OAuth sign-in.\n\n### Can an agent call Microsoft Copilot Studio MCP and Tray.ai API + MCP without installing anything?\n\nMicrosoft Copilot Studio MCP runs on your own machine, with no hosted endpoint listed. Tray.ai API + MCP has a hosted endpoint at https://api.tray.io/core/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray.json, and with the fewest tokens: https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"copilot-studio-mcp\", \"b\": \"tray\"}`. From a terminal: `anchor compare copilot-studio-mcp tray`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/copilot-studio-mcp.json and https://www.anchorterminal.com/api/v1/tools/tray.json\n\n## Other comparisons with Microsoft Copilot Studio MCP or Tray.ai API + MCP\n\n- [Activepieces API + MCP vs Microsoft Copilot Studio MCP](https://www.anchorterminal.com/compare/activepieces-vs-copilot-studio-mcp.md)\n- [Activepieces API + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/activepieces-vs-tray.md)\n- [Microsoft Copilot Studio MCP vs Gumloop](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-gumloop.md)\n- [Microsoft Copilot Studio MCP vs Kestra](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-kestra.md)\n- [Microsoft Copilot Studio MCP vs Make API + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-make.md)\n- [Microsoft Copilot Studio MCP vs n8n API + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-n8n.md)\n- [Microsoft Copilot Studio MCP vs Node-RED](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-node-red.md)\n- [Microsoft Copilot Studio MCP vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon.md)\n- [Microsoft Copilot Studio MCP vs Pipedream API + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-pipedream.md)\n- [Microsoft Copilot Studio MCP vs Microsoft Power Automate](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-power-automate.md)\n- [Microsoft Copilot Studio MCP vs Prismatic](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-prismatic.md)\n- [Microsoft Copilot Studio MCP vs Windmill API + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-windmill.md)\n- [Microsoft Copilot Studio MCP vs Workato API + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-workato.md)\n- [Gumloop vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/gumloop-vs-tray.md)\n- [Kestra vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/kestra-vs-tray.md)\n- [Make API + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/make-vs-tray.md)\n- [n8n API + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/n8n-vs-tray.md)\n- [Node-RED vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/node-red-vs-tray.md)\n- [Pipedream API + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/pipedream-vs-tray.md)\n- [Microsoft Power Automate vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/power-automate-vs-tray.md)\n- [Prismatic vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/prismatic-vs-tray.md)\n- [Tray.ai API + MCP vs Windmill API + MCP](https://www.anchorterminal.com/compare/tray-vs-windmill.md)\n- [Tray.ai API + MCP vs Workato API + MCP](https://www.anchorterminal.com/compare/tray-vs-workato.md)\n- [Paragon ActionKit + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/paragon-vs-tray.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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": "Microsoft Copilot Studio MCP vs Tray.ai API + MCP", "url": "" } ], "description": "Tray.ai scores 55.5 (C) to Microsoft Copilot Studio MCP's 53.1 (D) for workflow automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Microsoft Copilot Studio MCP D 53.1", "Tray.ai API + MCP C 55.5", "scores" ], "h1": "Microsoft Copilot Studio MCP vs Tray.ai API + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-copilot-studio-mcp-vs-tray.png", "path": "/compare/copilot-studio-mcp-vs-tray", "published": "2026-10-01", "section": "tools", "title": "Microsoft Copilot Studio MCP vs Tray.ai for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-tray" }, "tokens": { "markdown": 2600, "slim": 780 }, "version": 1 }