Categories › Software Development › Code search, analysis, refactoring & languages
Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
Remote server: your requests and data go to api.codemindhq.dev. Claude Code: claude mcp add --transport http codemind https://api.codemindhq.dev/mcp?utm_source=mcp-registry&utm_medium=directory&utm_campaign=registry-2026-10-10 · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
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 build_feature — Generate a feature via Codemind: takes a story title + acceptance criteria, generates the implementation and its tests, runs automated checkstream_build — Follow a build submitted by build_feature in real time. Emits a progress notification on every phase change and resolves with the final resuretry_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 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 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).test_component — Run standalone cloud verification on code you already have: give it a component (filePath/exportName/signature) plus acceptance criteria, anstream_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 pollinreview_code — Submit code for review: bugs, security issues, silent failures, and style concerns. Give it files (path+content) and/or a unified diff. At lstream_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 get_usage_guide — Get detailed usage guidance for Codemind's tools — how to write effective acceptanceCriteria, when to use patch mode, how webhooks work, whaget_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-blist_repos — Lists GitHub repos currently attached to the caller's tenant via Codemind Resolve (the GitHub App that automatically triages filed issues inget_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_oget_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, identibuild_batch — Submit several pre-decomposed stories in one call and get back one batchId to track, instead of dispatching build_feature N times yourself. 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 distream_batch — Stream live progress for a batch submitted via build_batch. Polls the batch's aggregate status periodically and emits a progress notificatiobuild_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 reNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.