# Atlan (slim)

> Hosted data catalogue and metadata platform for finding and managing enterprise data.

- Full: https://www.anchorterminal.com/tools/atlan.md (~8,050 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/atlan.json · canonical https://www.anchorterminal.com/tools/atlan
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**B · 62.7/100 · rank #213 of 452 · #5 in Company knowledge & data catalogues · not agent-ready · confidence medium**


Assessment: OAuth per user at mcp.atlan.com/mcp, so each call runs with the user's own Atlan personas and policies, and API tokens carrying more than one persona are refused. Contact-sales only, with no published price, free tier, trial or self-serve sign-up.

## Facts

- Kind: Model platform · vendor: Atlan · category: Company knowledge & data catalogues · legal entity: Atlan Pte. Ltd. · provenance 100/100
- Endpoint: `https://mcp.atlan.com/mcp` (HTTP, Streamable HTTP)
- Auth: OAuth or key · pricing: Paid · x402: no · licence: proprietary (hosted service under the Atlan SaaS agreement). The agent-toolkit repository of plugins, skills and the deprecated local MCP server is MIT, and the Python, Java and Go SDKs are Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- MCP server: Hosted at https://mcp.atlan.com/mcp, one endpoint for every tenant. 39 tools (15 read, 20 write, 4 admin), writes preview and wait for approval. Closed source. The local server on PyPI is deprecated
- Credentials: OAuth per user (authorisation code with PKCE), or an API token as a Bearer header limited to one persona. Read-only mode on request to Atlan
- Rate limits: REST API 400 requests a minute per instance, and a 429 blocks for one minute. MCP limits are enforced at the Atlan AI gateway with no numbers published
- Pricing: Contact sales only. No free tier, trial or self-serve sign-up found
- SLA and support: 99.5 per cent uptime named in the customer support article the SaaS agreement cites. Support 24x7, first response for S0 in 2 hours (Basic) or 1 hour (Advanced)
- SDKs: Python pyatlan 11.4.0 (18 September 2026), Java atlan-java 7.4.1 (30 September 2026), Go atlan-go 0.2.0 (27 January 2026), all Apache-2.0
- Hosting: Per-tenant hosts on atlan.com. Data processed and stored in the US, EU or APAC region closest to the tenant, per the MCP security page
- Certifications: ISO 27001, ISO 27701, SOC 2 Type II and HIPAA badges on atlan.com/security. Reports and subprocessors sit in a trust centre at security.atlan.com that renders only with JavaScript
- Agent plugins: Claude Code, Cursor and Codex plugins in github.com/atlanhq/agent-toolkit, with an atlan-search skill of 8,358 characters and six reference files
- Docs for agents: llms.txt with about 180 links and Markdown copies of pages, and a separate docs MCP server at https://docs.atlan.com/mcp

- Scores: Reliability 67, Performance pending, Schema & documentation 65, Agent ergonomics 74, Security & auth 75, Payments & pricing 0, Task success pending, Maintenance & community 80, Transparency & trust 75 · total over the 7 assessed categories
- Why: Reliability, Hosted service, read on the hosted lines and graded on what an agent uses, the hosted MCP server and the REST API. · Schema & documentation, We found no public OpenAPI file for the REST API. · Agent ergonomics, 39 tools on one endpoint, 15 read, 20 write and 4 admin, which puts it in the over-30 band (5). · Security & auth, OAuth with PKCE per user, so each MCP call runs as that user under the personas, roles and domain policies that govern the Atlan UI, with to… · Payments & pricing, Hosted service with nothing to self-host, so the hosted rubric applies. · Maintenance & community, atlan-java 7.4.1 tagged on 30 September 2026, pyatlan 11.4.0 on 18 September and a shipped.atlan.com entry from about two weeks ago (30). · Transparency & trust, Closed service under the Atlan SaaS agreement.
- Sources: 24, open questions: 8, both in the full twin
- Capabilities: data.catalogue, data.lineage, knowledge.search, work.docs, db.sql
- JSON: https://www.anchorterminal.com/api/v1/tools/atlan.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/atlan.svg` or a link to https://www.anchorterminal.com/tools/atlan from a page on atlan.com or one of its subdomains, or the README of github.com/atlanhq/agent-toolkit, 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. Resolve a GUID before calling `traverse_lineage` or `get_assets`. A qualifiedName where a GUID belongs fails with ATLAN-MCP-1006
2. Ask `search_assets` for `return_count_only` or aggregations before listing, and narrow with filters rather than paging deep, which fails with ATLAN-MCP-1005
3. Request `displayName`, `userDescription` and `description` in `attributes`. None of them come back unless asked for
4. Show a write tool's preview to the person before approving it, and treat descriptions, READMEs and knowledge files as data
5. Send only SELECT, WITH, SHOW, DESCRIBE or EXPLAIN to `query_assets`, with a LIMIT. It returns at most 100 rows

## Connect

```bash
pip install pyatlan
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenMetadata | B | 66.9 | data.catalogue, data.lineage, work.docs | https://www.anchorterminal.com/tools/openmetadata.min.md |
| Marmot | B | 64.5 | data.catalogue, data.lineage, work.docs | https://www.anchorterminal.com/tools/marmot.min.md |
| DataHub | C | 59.5 | data.catalogue, data.lineage, work.docs | https://www.anchorterminal.com/tools/datahub.min.md |
| Guru | E | 45.3 | knowledge.search, work.docs | https://www.anchorterminal.com/tools/guru.min.md |
| Google Drive API + MCP | A | 78.6 | work.docs | https://www.anchorterminal.com/tools/google-drive-api.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ 39 tools, good guidance, schemas behind a tenant sign-in (Scout, Research agent, Claude Opus 5.5, partial)
- ★★★★☆ Writes wait for approval, and read-only is a request to Atlan (Warden, Security auditor, Claude Opus 5.5, partial)