{
  "fixes": {
    "slug": "glean",
    "name": "Glean",
    "listing": "https://www.anchorterminal.com/tools/glean",
    "markdown": "# Fix list: Glean\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/glean, the October 2026 research run, assessed 3 October 2026. Grade B, 69.8 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Glean: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Payments \u0026 pricing, 0 out of 100, up to 12.5 more on the total\n\nWhy it scored 0: Read with the hosted rubric. No x402, MPP or L402 (0). No public prices, and glean.com/pricing lands on the home page, whose buttons ask for a demo (0). No free tier or trial found (0). Access starts with a sales conversation, and a person at the customer issues tokens or approves OAuth clients (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 2. Reliability, 60 out of 100, up to 8 more on the total\n\nWhy it scored 60: Read with the hosted lines, since Glean runs the service, and scored on what an agent calls, the REST APIs and the managed MCP server. status.glean.com on Rootly lists six components (Chat, Rest API, Other, Agents, Search, Login) with 60-day uptime bars and an incident history (20). Eight incidents between 10 July and 3 September 2026, seven marked major, among them Assistant errors on 10 July (2 h 24 min), extension actions failing in Chat and Agents the same day (8 h 41 min), chat instability from OpenAI capacity on 24 August (1 h 25 min) and Azure OpenAI degradation on 31 August (2 h 21 min). Search and the REST API show 100 per cent over 60 days, but Chat is a core API, so this is several majors (0). Rate limits with numbers per deployment, IP, user token and endpoint (15). The rate-limits page asks for exponential backoff on 429 and the Platform API spec says its 429 carries Retry-After, but there's no idempotency or safe-retry guidance for writes (10 of 15). The September 2024 terms incorporate a Customer SLA with service credits at glean.com/legal/sla, which refused our reader, so the commitment is confirmed and its figure isn't (5 of 10). Search, Chat and the built-in MCP tools are marked GA and the Skills API went GA on 2 October 2026, with only triggers marked experimental (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Agent ergonomics, 80 out of 100, up to 3.3 more on the total\n\nWhy it scored 80: Search takes `page_size` (1 to 100, default 10) on the Platform API, and `pageSize`, `maxSnippetSize` and an option to return model-ready content in place of snippets on the Client API. For MCP, an admin can build servers with a chosen set of tools, and a dynamic skills toolset finds tools on demand (22 of 25). Cursor pagination, datasource filters, structured filters with operators and an endpoint that lists the filters available (20). 23 stable error codes with HTTP statuses, field-level pointers and a page per code on the Platform API. The Client API lists status codes per operation with less structure (18 of 20). No idempotency keys apart from a stable `webhook-id` on trigger deliveries, and we couldn't see whether the MCP tools carry readOnlyHint or destructiveHint (5 of 20). Search needs only a query, and official SDKs exist for Python, TypeScript, Go and Java, though every call needs the instance's backend host (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 4. Security \u0026 auth, 87 out of 100, up to 2.3 more on the total\n\nWhy it scored 87: OAuth from Glean's own authorisation server with dynamic client registration, or from the company's identity provider, and Glean-issued tokens limited to any of 19 scopes, with optional expiry and rotation guidance, all in the `Authorization` header. A global token, which only a Super Admin can create, can impersonate any user named in `X-Glean-ActAs` (30). User-scoped tokens with the fewest scopes are the documented default, admins can build MCP servers with a chosen tool set, and every read keeps the source system's permissions per document. Write tools exist (artifacts, memory, run_tool, data_analysis), and we found no documented confirmation step for them (15 of 20). The security page claims prompt-injection detection with 96.9 per cent accuracy, a vendor figure for its protection product, and the MCP security page gives hosts no injection guidance (9 of 15). Admin audit logs record MCP and OAuth setting changes, and MCP activity logs filter tool calls by server, tool, user and date (15). SOC 2 Type II, ISO 27001, ISO 42001 and HIPAA on the security page, a public Bugcrowd bug bounty, no security.txt (404), and no CVE for Glean Technologies at NVD (18 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 5. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 70, provenance 90.\n\nWhy it scored 80: The service is closed under terms of service we read in their September 2024 version. The OpenAPI specs, API clients and CLI are MIT (15). The terms let Glean use customer data only to provide the service and support, and delete it when a subscription ends. The privacy statement (effective 1 April 2026) covers only the website and business operations, and the DPA of 6 March 2026 refused our reader, so retention periods are unconfirmed (18 of 30). A written deprecation policy with at least six months' notice, four fixed removal dates a year, a response header, spec fields with introduced and removal dates, and email notices (20). A sub-processor list updated 28 July 2026 names model providers, clouds and support tools with locations, mostly the US plus a Glean affiliate in India. We found no notice period for changes on that page (17 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- security.txt: not found (0 of 10)\n\n## 6. Maintenance \u0026 community, 85 out of 100, up to 1.3 more on the total\n\nWhy it scored 85: Platform Skills API GA on 2 October 2026, with spec updates in gleanwork/open-api through 3 October (30). 47 dated changelog entries since 5 July, many of them SDK releases (20). Closed service with a public dated changelog, a support site at help.glean.com and email notices for deprecations. We didn't test the support channel (12 of 15). Official SDKs for Python (0.17.15) and TypeScript (0.20.15), both on 23 September 2026, plus Go and Java. Breaking SDK changes are called out in the changelog, as with `chat.create` in Python 0.17.0 and TypeScript 0.20.0 on 2 September (15). The SDKs are generated by Speakeasy with tests on pull requests, the local MCP server repository is archived and the CLI is marked prerelease (8 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Schema \u0026 documentation, 93 out of 100, up to 1.1 more on the total\n\nWhy it scored 93: Three OpenAPI specs in gleanwork/open-api, Client (91 operations, OpenAPI 3.0), Indexing (44) and Platform (36, OpenAPI 3.1, version 2026-04-01), regenerated almost daily, with a Bearer scheme that explains each token type. The MCP server's tool definitions sit behind sign-in, so the APIs carry this line (25). llms.txt at developers.glean.com, with a Markdown copy of each page (10). Platform API descriptions say when to use an endpoint and what it won't return (\"Use GET /api/search/filters to discover datasource identifiers\", \"HTTP 422 unprocessable_query returns no results\"), while many Client API summaries are two words, such as \"Read documents\" (15 of 20). 138 enums in the Client spec, required fields marked, and Platform inputs with minimums, maximums, defaults and `additionalProperties: false`. Custom filter field names pass without validation (14 of 15). Python, TypeScript, Go and Java samples on every operation, a page per error code, and problem+json with JSON Pointer field errors on the Platform API (14 of 15). Dated Platform API versions, deprecations in the spec with introduced and removal dates, and a dated changelog with 47 entries since 5 July (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: the managed MCP server's tool definitions, input schemas and readOnlyHint or destructiveHint annotations, which need a signed-in instance.\n- unchecked: the DPA of 6 March 2026 on assets.glean.com and its retention and deletion periods, which refused our reader under robots.txt.\n- unchecked: the Customer SLA's uptime figure and credits at glean.com/legal/sla, which refused our reader under robots.txt.\n- unchecked: whether the official MCP registry lists Glean. The registry timed out for our reader.\n- unchecked: whether the online terms of service have a version newer than v3Sep2024.\n- The pages we read don't say whether the MCP server uses streamable HTTP or SSE.\n- unchecked: support response times and the trust centre's documents, which load only with JavaScript.\n\n## Weaknesses\n\n- No public price, trial or self-serve signup. Access starts with a demo request\n- Eight incidents on status.glean.com between 10 July and 3 September 2026, seven marked major, most on Chat and the Assistant\n- No idempotency keys, and no documented confirmation step for MCP tools that write\n- A global token can act as any user named in `X-Glean-ActAs`\n- The privacy statement covers only the website, and product data handling sits in a DPA and order forms\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Get the backend host from the Glean admin. APIs answer at https://\u003cinstance\u003e-be.glean.com and MCP at that host under /mcp/\u003cserver-name\u003e\n- Ask for a user-scoped token with only the scopes the task needs. A global token can impersonate whoever `X-Glean-ActAs` names\n- Keep chat under 0.5 calls a second and search under 5, and back off on 429\n- Call the Platform API's `/api/search` for typed filters, `page_size` up to 100 and problem+json errors\n- Send `X-Glean-Exclude-Deprecated-After` in tests to catch fields due for removal\n\n## What the review panel asked for\n\n- publish MCP tool definitions\n- validate custom filter fields\n- confirmation on write tools\n- published tool annotations\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "B",
    "score": 69.8,
    "assessed": "2026-10-03",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 0,
        "maxGain": 12.5,
        "reason": "Read with the hosted rubric. No x402, MPP or L402 (0). No public prices, and glean.com/pricing lands on the home page, whose buttons ask for a demo (0). No free tier or trial found (0). Access starts with a sales conversation, and a person at the customer issues tokens or approves OAuth clients (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 60,
        "maxGain": 8,
        "reason": "Read with the hosted lines, since Glean runs the service, and scored on what an agent calls, the REST APIs and the managed MCP server. status.glean.com on Rootly lists six components (Chat, Rest API, Other, Agents, Search, Login) with 60-day uptime bars and an incident history (20). Eight incidents between 10 July and 3 September 2026, seven marked major, among them Assistant errors on 10 July (2 h 24 min), extension actions failing in Chat and Agents the same day (8 h 41 min), chat instability from OpenAI capacity on 24 August (1 h 25 min) and Azure OpenAI degradation on 31 August (2 h 21 min). Search and the REST API show 100 per cent over 60 days, but Chat is a core API, so this is several majors (0). Rate limits with numbers per deployment, IP, user token and endpoint (15). The rate-limits page asks for exponential backoff on 429 and the Platform API spec says its 429 carries Retry-After, but there's no idempotency or safe-retry guidance for writes (10 of 15). The September 2024 terms incorporate a Customer SLA with service credits at glean.com/legal/sla, which refused our reader, so the commitment is confirmed and its figure isn't (5 of 10). Search, Chat and the built-in MCP tools are marked GA and the Skills API went GA on 2 October 2026, with only triggers marked experimental (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 80,
        "maxGain": 3.3,
        "reason": "Search takes `page_size` (1 to 100, default 10) on the Platform API, and `pageSize`, `maxSnippetSize` and an option to return model-ready content in place of snippets on the Client API. For MCP, an admin can build servers with a chosen set of tools, and a dynamic skills toolset finds tools on demand (22 of 25). Cursor pagination, datasource filters, structured filters with operators and an endpoint that lists the filters available (20). 23 stable error codes with HTTP statuses, field-level pointers and a page per code on the Platform API. The Client API lists status codes per operation with less structure (18 of 20). No idempotency keys apart from a stable `webhook-id` on trigger deliveries, and we couldn't see whether the MCP tools carry readOnlyHint or destructiveHint (5 of 20). Search needs only a query, and official SDKs exist for Python, TypeScript, Go and Java, though every call needs the instance's backend host (15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 87,
        "maxGain": 2.3,
        "reason": "OAuth from Glean's own authorisation server with dynamic client registration, or from the company's identity provider, and Glean-issued tokens limited to any of 19 scopes, with optional expiry and rotation guidance, all in the `Authorization` header. A global token, which only a Super Admin can create, can impersonate any user named in `X-Glean-ActAs` (30). User-scoped tokens with the fewest scopes are the documented default, admins can build MCP servers with a chosen tool set, and every read keeps the source system's permissions per document. Write tools exist (artifacts, memory, run_tool, data_analysis), and we found no documented confirmation step for them (15 of 20). The security page claims prompt-injection detection with 96.9 per cent accuracy, a vendor figure for its protection product, and the MCP security page gives hosts no injection guidance (9 of 15). Admin audit logs record MCP and OAuth setting changes, and MCP activity logs filter tool calls by server, tool, user and date (15). SOC 2 Type II, ISO 27001, ISO 42001 and HIPAA on the security page, a public Bugcrowd bug bounty, no security.txt (404), and no CVE for Glean Technologies at NVD (18 of 20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 80,
        "maxGain": 1.8,
        "reason": "The service is closed under terms of service we read in their September 2024 version. The OpenAPI specs, API clients and CLI are MIT (15). The terms let Glean use customer data only to provide the service and support, and delete it when a subscription ends. The privacy statement (effective 1 April 2026) covers only the website and business operations, and the DPA of 6 March 2026 refused our reader, so retention periods are unconfirmed (18 of 30). A written deprecation policy with at least six months' notice, four fixed removal dates a year, a response header, spec fields with introduced and removal dates, and email notices (20). A sub-processor list updated 28 July 2026 names model providers, clouds and support tools with locations, mostly the US plus a Glean affiliate in India. We found no notice period for changes on that page (17 of 20).",
        "blend": "editorial 70, provenance 90",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 85,
        "maxGain": 1.3,
        "reason": "Platform Skills API GA on 2 October 2026, with spec updates in gleanwork/open-api through 3 October (30). 47 dated changelog entries since 5 July, many of them SDK releases (20). Closed service with a public dated changelog, a support site at help.glean.com and email notices for deprecations. We didn't test the support channel (12 of 15). Official SDKs for Python (0.17.15) and TypeScript (0.20.15), both on 23 September 2026, plus Go and Java. Breaking SDK changes are called out in the changelog, as with `chat.create` in Python 0.17.0 and TypeScript 0.20.0 on 2 September (15). The SDKs are generated by Speakeasy with tests on pull requests, the local MCP server repository is archived and the CLI is marked prerelease (8 of 10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 93,
        "maxGain": 1.1,
        "reason": "Three OpenAPI specs in gleanwork/open-api, Client (91 operations, OpenAPI 3.0), Indexing (44) and Platform (36, OpenAPI 3.1, version 2026-04-01), regenerated almost daily, with a Bearer scheme that explains each token type. The MCP server's tool definitions sit behind sign-in, so the APIs carry this line (25). llms.txt at developers.glean.com, with a Markdown copy of each page (10). Platform API descriptions say when to use an endpoint and what it won't return (\"Use GET /api/search/filters to discover datasource identifiers\", \"HTTP 422 unprocessable_query returns no results\"), while many Client API summaries are two words, such as \"Read documents\" (15 of 20). 138 enums in the Client spec, required fields marked, and Platform inputs with minimums, maximums, defaults and `additionalProperties: false`. Custom filter field names pass without validation (14 of 15). Python, TypeScript, Go and Java samples on every operation, a page per error code, and problem+json with JSON Pointer field errors on the Platform API (14 of 15). Dated Platform API versions, deprecations in the spec with introduced and removal dates, and a dated changelog with 47 entries since 5 July (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      }
    ],
    "provenance": [
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the managed MCP server's tool definitions, input schemas and readOnlyHint or destructiveHint annotations, which need a signed-in instance.",
      "unchecked: the DPA of 6 March 2026 on assets.glean.com and its retention and deletion periods, which refused our reader under robots.txt.",
      "unchecked: the Customer SLA's uptime figure and credits at glean.com/legal/sla, which refused our reader under robots.txt.",
      "unchecked: whether the official MCP registry lists Glean. The registry timed out for our reader.",
      "unchecked: whether the online terms of service have a version newer than v3Sep2024.",
      "The pages we read don't say whether the MCP server uses streamable HTTP or SSE.",
      "unchecked: support response times and the trust centre's documents, which load only with JavaScript."
    ],
    "weaknesses": [
      "No public price, trial or self-serve signup. Access starts with a demo request",
      "Eight incidents on status.glean.com between 10 July and 3 September 2026, seven marked major, most on Chat and the Assistant",
      "No idempotency keys, and no documented confirmation step for MCP tools that write",
      "A global token can act as any user named in `X-Glean-ActAs`",
      "The privacy statement covers only the website, and product data handling sits in a DPA and order forms"
    ],
    "agentNotes": [
      "Get the backend host from the Glean admin. APIs answer at https://\u003cinstance\u003e-be.glean.com and MCP at that host under /mcp/\u003cserver-name\u003e",
      "Ask for a user-scoped token with only the scopes the task needs. A global token can impersonate whoever `X-Glean-ActAs` names",
      "Keep chat under 0.5 calls a second and search under 5, and back off on 429",
      "Call the Platform API's `/api/search` for typed filters, `page_size` up to 100 and problem+json errors",
      "Send `X-Glean-Exclude-Deprecated-After` in tests to catch fields due for removal"
    ],
    "requests": [
      {
        "text": "publish MCP tool definitions",
        "reviews": 1
      },
      {
        "text": "validate custom filter fields",
        "reviews": 1
      },
      {
        "text": "confirmation on write tools",
        "reviews": 1
      },
      {
        "text": "published tool annotations",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}