Advertise
MCP.so
Sign In

MCP Framework

@QuantGeekDev

RepositoryHomepage

Basic information

Category

Developer Tools

License

MIT

Transports

stdio

Author

QuantGeekDev

About MCP Framework

The Typescript MCP Framework

#mcp#claude#llm#llms#anthropic#genai#modelcontextprotocol

MCP Framework config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-framework": {
      "command": "node",
      "args": [
        "dist/index.js",
        "#",
        "Server",
        "validates",
        "tools",
        "on",
        "startup"
      ]
    }
  }
}

MCP Framework tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Framework?

MCP Framework is a TypeScript framework for building Model Context Protocol (MCP) servers. It provides automatic directory-based discovery of tools, resources, and prompts, along with a CLI for project scaffolding. The framework is designed for developers who want to create MCP servers with minimal boilerplate and built-in validation.

How to use MCP Framework?

Install the framework globally with npm install -g mcp-framework, then create a project using mcp create my-mcp-server. Add tools, prompts, or resources with mcp add tool <name>, mcp add prompt <name>, or mcp add resource <name>. Build and validate with npm run build. Serve the server with node dist/index.js and configure MCP clients (e.g., Claude Desktop) by pointing to the built dist/index.js.

Key features of MCP Framework

  • Automatic discovery and loading of tools, resources, and prompts
  • Multiple transport support: stdio, SSE, and HTTP Stream
  • TypeScript-first development with full type safety
  • Built on the official MCP SDK
  • Easy-to-use base classes for tools, prompts, and resources
  • Out-of-the-box authentication for SSE endpoints (OAuth 2.1, JWT, API Key)

Use cases of MCP Framework

  • Build custom MCP servers with structured tool, resource, and prompt management
  • Develop AI‑assistant integrations that use MCP to expose actions (e.g., crypto tipping via tip.md)
  • Rapidly prototype and deploy MCP servers for Claude Desktop or other MCP clients

Frequently asked questions

1

How do I add a new tool to my MCP server?

Use the CLI command `mcp add tool <name>` from the project root. This generates a skeleton file in the `tools/` directory. Define the tool’s schema using a Zod object and implement the `execute` method.

2

Which transports does MCP Framework support?

The framework supports stdio (default), SSE, and HTTP Stream. You can enable HTTP transport at creation time with `mcp create <project> --http --port 1337 --cors`.

3

How can I validate that my tools have proper descriptions?

Run `npm run build` (which includes automatic validation) or the standalone command `mcp validate`. The framework enforces that every Zod schema field has a `.describe()` call.

4

Where are log files stored and how can I enable them?

Logging to files is disabled by default. Set the environment variable `MCP_ENABLE_FILE_LOGGING=true` and optionally `MCP_LOG_DIRECTORY` (default `logs`). Debug console output is enabled via `MCP_DEBUG_CONSOLE=true`.

5

What authentication options are available for SSE endpoints?

MCP Framework provides built‑in authentication for SSE endpoints using OAuth 2.1, JWT, and API Key mechanisms.

Comments

More Developer Tools MCP servers

Kaiva Bridge

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

1

Yocoolab

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

1

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

1
Advertise