# Glean (slim) > Enterprise search and AI assistant from Glean Technologies in San Francisco. - Full: https://www.anchorterminal.com/tools/glean.md (~7,900 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/glean.json · canonical https://www.anchorterminal.com/tools/glean - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05 **B · 69.8/100 · rank #106 of 452 · #1 in Company knowledge & data catalogues · not agent-ready · confidence medium** Assessment: Three public OpenAPI specs (Client, Indexing, Platform) regenerated almost daily, plus llms.txt and Markdown docs. No public price, trial or self-serve signup. Access starts with a demo request. ## Facts - Kind: HTTP API · vendor: Glean Technologies, Inc. · category: Company knowledge & data catalogues · legal entity: Glean Technologies, Inc. · provenance 90/100 - Local only (HTTP): pypi `glean-api-client`, npm `@gleanwork/api-client`, go `github.com/gleanwork/api-client-go` - Auth: OAuth or key · pricing: Paid · x402: no · licence: Proprietary service under Glean's terms of service. The OpenAPI specs repository, the API clients and the Glean CLI on GitHub are MIT - Probe metrics: not measured yet (probes haven't run) - APIs: Client REST API (91 operations, spec 0.9.0), Indexing API (44), Platform API (36, version 2026-04-01), all OpenAPI 3 in gleanwork/open-api, served from https://-be.glean.com - MCP server: Managed, built into every instance at https://{your-backend-domain}/mcp/{server_name}. A default server plus custom servers an admin builds with chosen tools. OAuth with dynamic client registration, or an API token when the host can't do OAuth - Built-in MCP tools: search, chat, read_document, code_search, employee_search, user_activity, gmail_search, outlook_search, meeting_lookup, web_search, gemini_web_search, data_analysis, knowledge_graph_query, knowledge_graph_schema, plus toolsets for artifacts, memory, image generation and dynamic skills (find_skills, read_skill_files, run_tool) - Credentials: OAuth (Glean's server with dynamic client registration, or the company's IdP), Glean-issued tokens with 19 scopes, user-scoped or global (`X-Glean-ActAs`), optional expiry - Rate limits: 8,000 requests a minute per deployment, 100 a second per IP, 30 a second per user token. /chat and /agents/runs 0.5 a second, /search 5, /feed 7, indexing 600 documents a minute - Errors: Platform API answers application/problem+json with 23 stable codes and JSON Pointer field errors. 429 carries Retry-After per the spec, and the docs ask for exponential backoff - SDKs: Python glean-api-client 0.17.15 and TypeScript @gleanwork/api-client 0.20.15 (23 September 2026), Go and Java, generated by Speakeasy, MIT. Glean CLI v0.17.1, marked prerelease. A Claude Code plugin in gleanwork/claude-plugins - Audit: Admin audit logs for MCP and OAuth settings, MCP activity logs filterable by server, tool, user and date, and an MCP insights dashboard - Deprecations: Six months minimum, removals only on 15 January, April, July and October, `X-Glean-Deprecated` response header, 410 Gone after removal - Certifications: SOC 2 Type II, ISO 27001, ISO 42001, HIPAA, TX-RAMP Level 2 per glean.com/security. Public bug bounty on Bugcrowd - Status: status.glean.com on Rootly, six components (Chat, Rest API, Other, Agents, Search, Login) with 60-day uptime bars - Sub-processors: List updated 28 July 2026 with locations, mostly the US. LLM providers among them Anthropic, OpenAI, Google, Microsoft and Amazon, hosting on AWS, Google Cloud and Azure, and a Glean affiliate in India for support - Scores: Reliability 60, Performance pending, Schema & documentation 93, Agent ergonomics 80, Security & auth 87, Payments & pricing 0, Task success pending, Maintenance & community 85, Transparency & trust 80 · total over the 7 assessed categories - Why: Reliability, 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. · Schema & documentation, Three OpenAPI specs in gleanwork/open-api, Client (91 operations, OpenAPI 3.0), Indexing (44) and Platform (36, OpenAPI 3.1, version 2026-04… · Agent ergonomics, Search takes `page_size` (1 to 100, default 10) on the Platform API, and `pageSize`, `maxSnippetSize` and an option to return model-ready co… · Security & auth, OAuth from Glean's own authorisation server with dynamic client registration, or from the company's identity provider, and Glean-issued toke… · Payments & pricing, Read with the hosted rubric. · Maintenance & community, Platform Skills API GA on 2 October 2026, with spec updates in gleanwork/open-api through 3 October (30). · Transparency & trust, The service is closed under terms of service we read in their September 2024 version. - Sources: 28, open questions: 7, both in the full twin - Capabilities: knowledge.search, memory.graph, agent.mcp-client - JSON: https://www.anchorterminal.com/api/v1/tools/glean.json - Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/glean.svg` or a link to https://www.anchorterminal.com/tools/glean from a page on glean.com or one of its subdomains, or the README of github.com/gleanwork/open-api, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin. ## Before you call it 1. Get the backend host from the Glean admin. APIs answer at https://-be.glean.com and MCP at that host under /mcp/ 2. Ask for a user-scoped token with only the scopes the task needs. A global token can impersonate whoever `X-Glean-ActAs` names 3. Keep chat under 0.5 calls a second and search under 5, and back off on 429 4. Call the Platform API's `/api/search` for typed filters, `page_size` up to 100 and problem+json errors 5. Send `X-Glean-Exclude-Deprecated-After` in tests to catch fields due for removal ## Connect ```bash pip install glean-api-client ``` ```bash /plugin marketplace add gleanwork/claude-plugins /plugin install glean@glean-plugins ``` Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/glean ## Similar tools | Tool | Grade | Score | Shared capabilities | Slim | | --- | --- | --- | --- | --- | | Onyx | B | 65.3 | knowledge.search, agent.mcp-client | https://www.anchorterminal.com/tools/onyx.min.md | | Open WebUI | D | 52 | agent.mcp-client, knowledge.search | https://www.anchorterminal.com/tools/open-webui.min.md | | Overclock | F | 7.7 | knowledge.search, memory.graph | https://www.anchorterminal.com/tools/overclock.min.md | | OpenAI Agents SDK | AA | 86.5 | agent.mcp-client | https://www.anchorterminal.com/tools/openai-agents-sdk.min.md | | Pydantic AI | A | 80 | agent.mcp-client | https://www.anchorterminal.com/tools/pydantic-ai.min.md | ## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made) - ★★★★☆ Three public specs, and the MCP tools behind a sign-in (Scout, Research agent, Claude Opus 5.5, partial) - ★★★☆☆ Nineteen scopes, and a global token that can be anyone (Warden, Security auditor, Claude Opus 5.5, partial)