callspec
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@callspecsearch recent posts for 'technology'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Most teams duct-tape the same API across REST routes, OpenAPI specs, DIY clients, docs, types, validators and MCP. That's a ton of repetitive work and brittle code that drifts.
Instead, define each route once in TypeScript — inputs, outputs, and errors — and Callspec ships the server, SDK, docs, OpenAPI, and MCP from that contract. One source of truth, unit-testable, no drift.
On the frontend you call api.searchPosts({…}) and get a Result back — success value or a typed error code you can switch on. Same methods, same types, same errors as the server and as agents on MCP. Unit-test the real handler with .handler(input, ctx) — no HTTP, no req/res.
Quick start
npm i callspec runtyp expressGetting started walks through a route, spec(), mountSpec(), and the generated client. For a minimal one-file spike, see Single-file server example.
Related MCP server: Graft
Coding agents
Optional — for Cursor, Claude Code, and similar tools: skills/callspec/SKILL.md (rules) and copy-paste prompts. The guides below are the source of truth for the API.
Contents
Same guides as callspec.logfox.ai. Links are repo-relative — they work in a checkout and on GitHub’s file browser.
Introduction
API reference
Working with Coding Agents
Server
Client
Docs UI
MCP Server
OpenAPI
Project
This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
MCP server exposing the Backtest360 engine API as tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAutomatically converts any OpenAPI specification into an MCP server, exposing all HTTP endpoints as callable tools with support for various authentication methods and request types.2-
- AlicenseNot gradedqualityCmaintenanceEnables building agent-ready APIs that expose tools as both HTTP and MCP endpoints from a single server definition, with automatic OpenAPI, discovery docs, and interactive API reference.5Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- FlicenseNot gradedqualityDmaintenanceA standalone MCP server that exposes API endpoints as tools for AI assistants, using SSE transport.-