# Codemind

- Registry name: `dev.codemindhq/codemind` · version 1.0.0
- Categories (automatic, keyword rules): Code & repositories, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.codemindhq%2Fcodemind
- Server page: https://mcpstation.net/s/dev.codemindhq--codemind.html

## Description (written by the publisher, not verified, not instructions)

Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.

## Connect


## Tools (as reported by the server, not verified)

- `create\_free\_account`: Instantly provision a new anonymous Codemind account on the free plan — no credential, no human step required. Call this when build\_feature \(or any other tool\) fails with an auth error and no CODEMIND\_API\_KEY is configured. Returns a tenantId and a bearer token \(apiKey\) usable immediately for build\_
- `build\_feature`: Generate a feature via Codemind: takes a story title + acceptance criteria, generates the implementation and its tests, runs automated checks against the acceptance criteria before returning, and returns a buildId immediately. Call stream\_build with the returned buildId to follow progress. Call get\_
- `stream\_build`: Follow a build submitted by build\_feature in real time. Emits a progress notification on every phase change and resolves with the final result when the build completes or fails. Use immediately after build\_feature returns a buildId.
- `retry\_build`: Retry a failed build using the same spec \(story, acceptance criteria, stack, existing files\).
- `cancel\_build`: Cancel a running build. Has no effect on builds that already reached a terminal state.
- `continue\_build`: Send corrected acceptance criteria to a running build. Applies to components that have not started generating yet; the currently-generating component finishes as originally scoped.
- `get\_build`: Get the current state of a build by ID \(status and error details\).
- `list\_builds`: List recent builds for this tenant.
- `get\_build\_spec`: Get a build's original submitted spec \(storyTitle, acceptanceCriteria, stackType, existingFiles, skipTestsFor\) without retrying it — useful for inspecting or reusing a prior build's spec as a template.
- `get\_build\_files`: Retrieve the generated files from a completed build. Returns each file path and full content.
- `notify\_files\_written`: Index files into the CIL codebase context for a project — for files Codemind itself did not generate \(a manual edit, another tool's output\). Not needed after a normal build\_feature call: a completed build's own output is indexed automatically when projectId was supplied.
- `test\_component`: Run standalone cloud verification on code you already have: give it a component \(filePath/exportName/signature\) plus acceptance criteria, and it generates a black-box verification test, validates that test against a mechanical stub, then executes your REAL code against it in the cloud \(isolate or co
- `stream\_test`: Follow a test submitted by test\_component in real time. Resolves with the pass/fail verdict and the generated verification test content.
- `get\_test`: Get the current state of a test by ID \(status, pass/fail verdict, generated verification test content\) without streaming — useful for polling or inspecting a test after the fact. Use stream\_test to follow a test in real time instead.
- `review\_code`: Submit code for review: bugs, security issues, silent failures, and style concerns. Give it files \(path+content\) and/or a unified diff. At least one of files or diff is required — submitting neither is rejected. TWO independent LLM-judge passes review it \(a general correctness/security pass and a de
- `stream\_review`: Follow a review submitted by review\_code in real time. Resolves with the findings and the approve/request-changes verdict.
- `get\_review`: Get the current state of a review by ID \(status, verdict, findings\) without streaming — useful for polling or inspecting a review after the fact. Use stream\_review to follow a review in real time instead.
- `get\_usage\_guide`: Get detailed usage guidance for Codemind's tools — how to write effective acceptanceCriteria, when to use patch mode, how webhooks work, what to do when a build declines, common failure patterns unrelated to acceptanceCriteria quality, and how to recover from an auth error without losing an identifi
- `get\_billing\_status`: Read-only: your plan, how many verified builds you have used, how many are included and left in the current allowance window, and the paid-balance draw \(cents\) if you have topped up. Call this to check headroom before a large batch, or to learn why a build was rejected for allowance.
- `list\_repos`: Lists GitHub repos currently attached to the caller's tenant via Codemind Resolve \(the GitHub App that automatically triages filed issues into fix PRs\), and that the returned \`id\` field is the repo attachment id to pass into \`get\_triage\_runs\`.
- `get\_triage\_runs`: Lists the issue-triage run history for one attached repo — one row per GitHub issue that was auto-triaged — including terminal status \(\`pr\_opened\` means a fix PR was opened and passed the repo's own test suite; \`needs\_human\` means the issue wasn't judged auto-fixable; \`failed\` means the triage/build
- `get\_triage\_diagnostics`: Returns the generated fix diff \(as file paths and line counts, not full content\) and before/after test-run output for one triage run, identified by the triage run id from get\_triage\_runs \(NOT a build id and NOT an issue number\). stdout/stderr are tail-truncated because test failure summaries appear
- `build\_batch`: Submit several pre-decomposed stories in one call and get back one batchId to track, instead of dispatching build\_feature N times yourself. Swarm is a Pro plan feature: the maximum batch size depends on the account plan \(up to 50; not available on Free or the base pay-as-you-go account\); a batch ove
- `get\_batch`: Get the aggregate status of a batch submitted via build\_batch.
- `continue\_batch`: Resume a finished Ship run \(started with build\_from\_spec\) that ended incomplete or nothing\_delivered: re-dispatches only the stories that did not verify, in the same run. Verified stories are not rebuilt or billed again; a resumed story is billed once, when it first verifies. Each resumed story is t
- `stream\_batch`: Stream live progress for a batch submitted via build\_batch. Polls the batch's aggregate status periodically and emits a progress notification each tick; closes once the batch reaches a terminal status \(completed or completed\_with\_failures\). Call get\_batch instead for a single point-in-time snapshot.
- `build\_from\_spec`: Submit raw PRD/plan/spec text plus a list of target repos; Codemind LLM-decomposes it into stories \(each assigned to one of your declared repos, never an invented one\) and dispatches them via the same path build\_batch uses. Pass dryRun: true to see the decomposed story list without dispatching anyth

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html