SpecPilot MCP server
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
38 stars
Reviews
Write oneNobody has reviewed SpecPilot yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
SpecPilot tools (2)
write = sends, deletes, buys or postsspecpilot_generate_specsFreeGenerates the complete SpecPilot .specs/ file set plus the matching IDE rules and slash-command files from a full answer set - identical to what the SpecPilot web chat produces for the same answers. Requires projectName and projectDescription. Returns the files to write and the steps to follow after writing them.
specpilot_next_questionsFreeReturns the still-unanswered SpecPilot onboarding questions of the next incomplete step, gated by the answers supplied so far - questions that do not apply to this kind of project are omitted, and options are filtered, badged or flagged the same way the SpecPilot web chat would. Stateless: send every answer collected so far on each call. Procedure: (1) Decide whether the repository already has real source code and set `isNewBuild` accordingly - it changes which onboarding analysis is generated at the end. (2) Infer what the repo already answers rather than asking: `platforms` from the dependency manifests and layout, `languageOverride`, `ideAgent` (you are the IDE - claudecode, cursor, copilot, codex, windsurf), `handle` from git config or the origin remote, `projectName` from the package manifest or folder name, and `projectDescription` from the README only if it plainly says what the project is. (3) Call this tool with what you have; answer what the repo makes obvious and ask the developer the rest, a whole step per message. Send an empty value for an optional question the developer declines, or it will be asked again; send `todoSentinel` verbatim when they do not know yet. For `projectDescription`, sending one of the returned chip labels exactly is what infers `projectCategory` and gates every later question - free prose infers nothing. Confirm any pre-seeded value rather than accepting it silently. (4) Loop until `done` is true, then call specpilot_generate_specs and follow its `nextSteps` for where each file goes.
Public scan report
scanner v0.1.3 · 2026-09-19 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 874ms20/20
- Tool poisoning2 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 6 days ago15/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
Install directly
claude mcp add --transport http specpilot https://init.specpilot.dev/mcp
SpecPilot: common questions
- Is SpecPilot MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the SpecPilot safety report
- How do I install SpecPilot?
- It runs remotely at init.specpilot.dev. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does SpecPilot need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is SpecPilot maintained?
- The last commit was 6 days ago (2026-09-13). The latest release is v1.0.0.
- Is SpecPilot up?
- 100% of our last 1 checks got an answer. We check remote servers about four times a day.
- What can I use instead of SpecPilot?
- Servers from other publishers that do the same job: Agent-Native Slides MCP server, Orcareplay MCP server and GitWarren MCP server. Compare all SpecPilot alternatives.
Alternatives to SpecPilot
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentationsnot reviewedEstablishedA
- OrcareplayRead, replay and fork recorded coding-agent runs.not reviewedEstablishedA
- GitWarrenCode review on your own machine, for you and your coding agent. Nothing leaves your computer.not reviewedEstablishedA
- ProjectmemCoding agent memory — one local MCP server for every project. Warns before repeating failed fixes.not reviewedGrowingA
- rag-ratRepository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.not reviewedGrowingB