SpecPilot
https://init.specpilot.dev/mcp ↗
Description
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
What our measurements say
SpecPilot is a remote MCP server published at init.specpilot.dev. It has been probed 6 times since 9/14/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 944 ms, a delay an agent will notice. It offers a narrow, focused set of 2 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names clearly indicate their purpose (e.g., 'next_questions' vs 'generate_specs')
- No tool overlap/ambiguity between onboarding and generation functions
Weaknesses
- Parameter schemas lack specific property definitions (both use generic 'object' type)
- Optional parameters may create confusion (first tool's 'answers' is optional but description implies dependency)
- No explicit error handling documentation for missing required parameters
specpilot_next_questions— Parameter 'answers' type is too vague (generic object) without required propertiesspecpilot_generate_specs— Required parameters (projectName, projectDescription) not explicitly defined in schemaspecpilot_next_questions— Optional parameter may create ambiguity in usage context
Verdict
Event narrative
Sign up free to generateSchema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test passed · last run:
- Cold-start: cold 74ms → warm 53ms (penalty 21ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
specpilot_next_questionsReturns 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
answersobject
specpilot_generate_specsGenerates 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.
answersobjectrequired
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Legacy
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/dev-specpilot-specpilot)<a href="https://mcpmetrics.io/servers/dev-specpilot-specpilot"><img src="https://mcpmetrics.io/badge/dev.specpilot/specpilot/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- Carrier MCP: Give Your AI Agent Global Connectivitymcp.carrier.llc
Carrier MCP — natural language control of your MVNO/eSIM fleet. 52 tools (43 OCS API wrappers + 8 AI intelligence + 1 OCS event history), 5 prompts, OAuth 2.1 + PKCE. Streamable HTTP on Cloudflare Workers.
- Invoke — hire a human from your AI agent (first post free)invoke.nanocorp.app
Let your AI agent hire a human for tasks it can't do — first post free.
- Readiness scorer — can an agent sign up to your SaaS?agentwares-readiness.vercel.app
Probe a signup URL you own and score whether an AI agent can sign up unaided.
- Send Your Agent Website Readinesssendyouragent.com
Scan website AI readiness, understand the result and route customers to the right SYA package.
- ASMI — AI avatars for your sitebroen.tech
Design your site's AI avatar in the ASMI studio; your coding agent ships it into your repo.
- skill-reposkillrepo.dev
Governed skills for every AI agent your team runs. Curate one approved library of agent skills, distribute it to developers, and expose it over MCP to remote agents without copying files across machines.
Comments
Sign in to write a comment
No comments yet. Be the first.