Document how to use the Ontos MCP server with Genie

Open Beginner friendly
#759 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-2 days
Newbie friendliness
84/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Active
Tech stack
python
Domain
documentation

Research direction

Start with docs/handbook/mcp-and-ask-ontos.md and inspect routes/mcp_routes.py for the /api/mcp endpoint and exposed tools. Document MCP token creation, least-privilege scopes, endpoint registration, and a Genie example covering token, registration, and a sample tool call. Done means a reviewer can follow the guide using a live MCP token.

Written by the indexing model from the issue text.

Description

source/external-request stakeholder/fpiz type/docs

Part of the "Large-account scale, async importers, and UC domain sync" epic. PRD: docs/prds/prd-large-account-scale-and-uc-sync.md.

Problem statement

The Ontos MCP server (routes/mcp_routes.py, POST /api/mcp) exposes tools and the handbook (docs/handbook/mcp-and-ask-ontos.md) explains Ask Ontos vs MCP conceptually, but there is no concrete guide to connect Genie / an external agent: token creation, scopes, endpoint registration, or a worked example.

Proposed Solution

Extend docs/handbook/mcp-and-ask-ontos.md (or a focused sibling it links) with: creating an MCP token in Settings → MCP Tokens, a scope-to-use-case table (least privilege), registering the /api/mcp endpoint, and a Genie-specific worked example (token → registration → sample tool call). Docs-only.

Additional Context

No API/tool/scope changes. If the worked example reveals a missing scope or ergonomics gap, file that separately. Validation is a reviewer walking the guide against a live MCP token.

Dominant language
Python
Stars
212
Forks
71
Avg merge
4d 10h
Merged PRs (30d)
43

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from databrickslabs/ontos

All issues in databrickslabs/ontos

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.