Typescribe

An MCP server implementation enabling LLMs to work with new APIs and frameworks
  • typescript

44

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "yworks-mcp-typescribe": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "node",
        "./dist/mcp-server/cli.js",
        "run-server",
        "docs/api.json"
      ]
    }
  }
}

MCP-Typescribe provides a server that makes API information and TypeScript definitions explorable by AI agents in real time. It loads TypeDoc JSON data and exposes a set of query tools so you can search symbols, inspect details, understand type hierarchies, and discover where things are used. This enables faster onboarding of new or proprietary APIs and supports more autonomous, context-aware coding assistants.

How to use

You run the MCP server locally and connect your AI agent to query the API context it exposes. Start by preparing a JSON documentation file for the TypeScript API you want to explore, then start the MCP server and point your agent at it. The server offers a range of query tools that you can use to discover symbols, inspect their details, and understand how the API fits together.

How to install

Prerequisites You need Node.js and npm installed on your system.

  1. Clone the project.

  2. Install dependencies.

npm install
  1. Build the project.
npm run build
  1. Generate TypeDoc JSON for your API. If you have a full TypeScript project, run the TypeDoc command to create docs/api.json.
npx typedoc --json docs/api.json --entryPointStrategy expand path/to/your/typescript/files

If you only have an existing .d.ts file, create a dedicated tsconfig for docs and generate api.json accordingly.

{ "extends": "./tsconfig.json", "files": ["existing.d.ts"], "typedocOptions": { "entryPoints": ["existing.d.ts"], "json": "docs/api.json", "pretty": false } }
  1. Start exploring the MCP server using the generated API data.
npx @modelcontextprotocol/inspector node ./dist/mcp-server/cli.js run-server docs/api.json

Available tools

search_symbols

Find symbols by name with optional filtering by kind to discover relevant API elements.

get_symbol_details

Retrieve detailed information about a specific symbol, including its type and documentation.

list_members

List methods and properties of a class or interface to understand its structure.

get_parameter_info

Get information about function parameters, including types and defaults.

find_implementations

Find implementations of interfaces or subclasses to understand concrete usage.

search_by_return_type

Find functions that return a specific type to locate applicable APIs.

search_by_description

Search in JSDoc comments to discover relevant API descriptions.

get_type_hierarchy

Show inheritance relationships to map the API’s type graph.

find_usages

Find where a type or function is used across the codebase.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational