Related MCP Server Resources

Explore more AI models, providers, and integration options:

  • Explore AI Models
  • Explore AI Providers
  • Explore MCP Servers
  • LangDB Pricing
  • Documentation
  • AI Industry Blog
  • TMDB MCP Server
  • Vertex AI MCP Server
  • Perplexity AI MCP Server
  • Notion Knowledge Base MCP Server
  • Image Processor MCP Server
Back to MCP Servers
MCP-Typescribe

MCP-Typescribe

Public
yWorks/mcp-typescribe

Provides real-time, machine-readable TypeScript API documentation via the Model Context Protocol, enabling LLMs to efficiently query symbols, explore type hierarchies, and access detailed API context for enhanced autonomous coding and faster SDK onboarding.

typescript
0 tools
May 29, 2025
Updated Jun 4, 2025

Supercharge Your AI with MCP-Typescribe

MCP Server

Unlock the full potential of MCP-Typescribe through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

MCP-Typescribe - an MCP Server providing LLMs API information

The Problem

Large Language Models (LLMs) have made incredible strides in code generation and developer productivity. However, they face a key limitation: they can only reliably use APIs and libraries they’ve seen during training. This creates a bottleneck for adopting new tools, SDKs, or internal APIs — LLMs simply don’t know how to use them effectively.

While tools can be given source code access (when interacting with APIs for which the sources are available) or access to documentation files (e.g. typescript type definition files), this doesn't scale well for large APIs. LLMs need a more efficient way to learn more about an API. Putting all the documentation into context for every request is inefficient, unfeasible, and leads to poor results.

As a result:

Larger new or internal APIs remain "invisible" to LLMs.

Developers must manually guide LLMs or provide example usage.

Innovation is slowed by the lag between an API’s release and its widespread understanding by AI tools.

The Idea

This project is an open-source implementation of the Model Context Protocol (MCP)—a protocol designed to provide LLMs with contextual, real-time access to information. In this case it's the API documentation, and particularly for now in this project TypeScript definitions.

Our goal is to:

Parse TypeScript (and other) definitions into a machine-readable format.

Serve this context dynamically to LLMs through tools like Claude, Cline, Cursor, or Windsurf and other custom interfaces.

Enable agentic behavior by letting LLMs query, plan, and adapt to unfamiliar APIs without retraining.

What This Enables

Plug-and-play API support for LLM-based coding assistants.

Faster onboarding for new or proprietary SDKs.

A step toward more autonomous, context-aware coding agents.

Project Overview

!Image

This project provides a way for AI agents to efficiently explore and understand unknown TypeScript APIs. It loads TypeDoc-generated JSON documentation and exposes it through a set of query endpoints that allow agents to search for symbols, get detailed information about specific parts of the API, and understand relationships between different components.

Current Features

  • TypeDoc Integration: Loads and indexes TypeDoc JSON documentation for efficient querying
  • Comprehensive Query Capabilities: Provides a wide range of tools for exploring TypeScript APIs
  • MCP Protocol: Follows the Model Context Protocol for seamless integration with AI agents

Query Capabilities

The server provides the following tools for querying the API:

  • search_symbols: Find symbols by name with optional filtering by kind
  • get_symbol_details: Get detailed information about a specific symbol
  • list_members: List methods and properties of a class or interface
  • get_parameter_info: Get information about function parameters
  • find_implementations: Find implementations of interfaces or subclasses
  • search_by_return_type: Find functions returning a specific type
  • search_by_description: Search in JSDoc comments
  • get_type_hierarchy: Show inheritance relationships
  • find_usages: Find where a type/function is used

Getting Started

Prerequisites

  • Node.js
  • npm

Installation

  1. Clone the repository
  2. Install dependencies:
    npm install

Usage

  1. Generate TypeDoc JSON for your TypeScript API:

    npx typedoc --json docs/api.json --entryPointStrategy expand path/to/your/typescript/files

    If you (only) have an existing.d.ts file, you can create an api json file like so:

    Create a separate tsconfig.docs.json:

    { "extends": "./tsconfig.json", "files": ["existing.d.ts"], "typedocOptions": { "entryPoints": ["existing.d.ts"], "json": "docs/api.json", "pretty": false } }

    Then do

    npx typedoc --tsconfig tsconfig.docs.json
  2. Build the project:

    npm run build
  3. Explore the MCP server:

    npx @modelcontextprotocol/inspector node ./dist/mcp-server/cli.js run-server docs/api.json
  4. Connect an AI agent to the server to query the API

    E.g. with cline in VSCode, specify the following MCP server in cline_mcp_settings.json:

    { "mcpServers": { "typescribe": { "command": "npx", "args": [ "-y", "mcp-typescribe@latest", "run-server", "" ], "env": {} } } }
  5. Enable the server and likely auto-approve the various tools. Tell the agent to use the "typescribe" tool to learn about your API.

Project Structure

  • src/sample-api/: A sample TypeScript API for testing - it uses a weird German-like dialect for the API names to test that the LLM does not hallucinate the API
  • src/mcp-server/: The MCP server implementation
    • utils/: Utility functions
    • schemas/: JSON schemas for the MCP tools
    • core/: Core functionality
    • server.ts: The MCP server implementation
    • index.ts: Entry point for the library exports
    • cli.ts: the entry point for the CLI/binary
  • tests/: Tests for the API functionality

Development

Running Tests

npm test

Building

npm run build

License

MIT

Copyright 2025 yWorks GmbH - https://www.yworks.com

Publicly Shared Threads0

Discover shared experiences

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!

Share your threads to help others
Related MCPs5
  • TMDB MCP Server
    TMDB MCP Server

    Provides AI assistants with seamless access to The Movie Database API via Model Context Protocol, en...

    Added May 30, 2025
  • Vertex AI MCP Server
    Vertex AI MCP Server

    Provides a Model Context Protocol server enabling advanced interaction with Google Cloud's Vertex AI...

    20 tools
    Added May 30, 2025
  • Perplexity AI MCP Server
    Perplexity AI MCP Server

    Provides seamless integration with Perplexity AI via Model Context Protocol, enabling chat, search, ...

    5 tools
    Added May 30, 2025
  • Notion Knowledge Base MCP Server
    Notion Knowledge Base MCP Server

    Provides seamless access to Notion knowledge bases via Model Context Protocol, enabling detailed, re...

    Added May 30, 2025
  • Image Processor MCP Server
    Image Processor MCP Server

    A TypeScript-based Model Context Protocol server enabling creation, access, and summarization of tex...

    2 tools
    Added May 30, 2025