MCP server

SpecPilot Official

dev.specpilot/specpilot

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent

Working at last checkVerified publisher: specpilot.devAbout 2,933 tokens per request once connected2 tools

https://init.specpilot.dev/mcp

At a glance

Type: MCP server
Publisher: specpilot.dev (verified by the MCP Registry)
Status: Working at last check
Tools: 2
Token cost: About 2,933 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 25 Oct 2026, 20:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http specpilot https://init.specpilot.dev/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.specpilot]
url = "https://init.specpilot.dev/mcp"

Gemini CLI

{"mcpServers":{"specpilot":{"httpUrl":"https://init.specpilot.dev/mcp"}}}

Cursor

{"mcpServers":{"specpilot":{"url":"https://init.specpilot.dev/mcp"}}}

VS Code

{"servers":{"specpilot":{"type":"http","url":"https://init.specpilot.dev/mcp"}}}

Antigravity

agy mcp add specpilot https://init.specpilot.dev/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"specpilot","server_url":"https://init.specpilot.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"specpilot","server_url":"https://init.specpilot.dev/mcp"}

specpilot_generate_specs ~789 tokens
Generates 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
specpilot_next_questions ~2144 tokens
Returns the unanswered SpecPilot onboarding questions of the next incomplete step, gated by the answers so far: questions that do not apply are omitted, and options are filtered, badged or flagged as in the SpecPilot web chat. Stateless: send every answer collected so far on each call. Procedure: (

Codemind
Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
Protogen
MCP CAD services; bundles with SmartScale (measure to CAD).
AI Design Blueprint
Doctrine and validators for governable agentic AI products.
oasdiff
Detect breaking changes, generate changelogs, diff, and validate OpenAPI specs.
Ai Visibility
AI-search-visibility tools: check crawler access, generate llms.txt, lint robots.txt, census data.
Flux Cloud
Deploy, pay for and manage apps on Flux Cloud, the decentralized cloud. Prices in USD.
Sato Hub: Build Onchain & Crypto Agents
Build any crypto agent: stack picks, x402 and ERC-8004 lookups, wallet-key checks, unsigned swaps.
ExchangeRebel — pay-per-call APIs for AI agents (x402 on Solana)
166 pay-per-call APIs for AI agents: market, company, dev + verification tools — x402 on Solana.

[![AptLynx](https://aptlynx.net/badge/dev.specpilot/specpilot.svg)](https://aptlynx.net/servers/dev.specpilot/specpilot)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents