buddie MCP server

<!-- mcp-name: io.github.tsyyan/buddie -->

Verify the claim. Know the context.

Evidence and environment awareness for AI agents.

Why Buddie?

An agent finishes a task and tells you that CI passed, that a source supports its summary, or that your laptop has CUDA and Python 3.12. It sounds certain, and often it is right. When it is wrong, the mistake hides inside a confident sentence.

Buddie separates what can be checked from what is only claimed. It checks supported claims against the evidence itself, gives the agent real observations of your machine instead of guesses, and marks what it could not check as unchecked. In 929 checkable quotations from published deep-research reports, 212 were altered or absent from the page they cited; Buddie flagged 207 of them (research).

What Buddie does

Verify. Buddie checks supported claims against their evidence: a quotation against the page it links to, a file or commit against your repository, a merged PR or a green CI run against GitHub, a test result against the session's record of the command. No language model takes part in the check, so the agent cannot argue its way to a different verdict.

Catch mismatches. In Claude Code and Codex, Buddie's hook checks the agent's answer before it reaches you. When a claim does not hold, the answer goes back to the agent with the reason, so it can fix the claim or say plainly what is unverified. Other clients call the same checks through MCP or the command line and decide what to do with the result.

Observe. Before it suggests a command, an agent can ask Buddie for the parts of your machine the task needs: the operating system, CPU, memory, GPU, Python, runtimes, tools. Buddie reads only the categories you have granted, changes nothing, and records how each value was observed.

See it in action

Verify an agent's claim

An agent reports that it fixed a date parser and that the test suite is green. It marks the claim with a small anchor, ⚓ run:pytest -q => 41 passed, that Buddie can check. The session transcript records what the test command actually printed:

41 passed. Evidence check, session transcript: 1 failed, 40 passed in 3.1s. Verification outcome: FAIL, effects 0/1 hold, 1 broken, exit 1." width="600">

Run it yourself from a clone; the report and transcript are in examples/work:

<!-- readme-example: work -->

cd buddie/examples/work
buddie verify report.md --transcript session.jsonl --no-github

Shortened. The full README is on GitHub.