MCP Bridge Api
M

MCP Bridge Api

MCP Bridge is a lightweight, LLM-independent RESTful proxy for connecting to multiple Model Context Protocol (MCP) servers and exposing their functions through a unified REST API. It solves the problem that platforms such as edge devices, mobile devices, and web browsers cannot efficiently run MCP servers, and provides optional risk-based execution levels, including security controls such as standard execution, confirmation workflows, and Docker isolation.
2.5 points
9.9K

What is MCP Bridge?

MCP Bridge is a lightweight proxy service that connects multiple Model Context Protocol (MCP) servers and exposes their functions through a unified REST API. It allows clients on any platform to use MCP functions without directly running the MCP server process.

How to use MCP Bridge?

Interact with MCP Bridge through simple HTTP requests, and it can proxy your requests to the backend MCP servers. You can also use the accompanying MCP-Gemini Agent to interact with MCP tools in natural language.

Use cases

Suitable for scenarios where MCP functions need to be used on mobile devices, browsers, or other environments that cannot directly run MCP servers. It is also suitable for situations where multiple MCP server connections need to be centrally managed.

Main features

Multi-server support
Can connect to and manage multiple different types of MCP servers simultaneously
Unified REST API
Provides a consistent RESTful interface for all connected MCP servers
Risk level control
Supports three risk levels (low, medium, high) and provides different security execution strategies
Gemini intelligent agent
The accompanying Python client that enables natural language interaction through Google Gemini LLM
Docker isolation
Automatically uses Docker container isolation for high-risk operations
Advantages
Platform independence: Can be used on any device that can send HTTP requests
Resource efficiency: Multiple clients can share the same MCP server connection
Security controllability: Provides fine-grained security control through the risk level system
Ease of use: The accompanying Gemini Agent enables non-technical users to easily use MCP tools
Limitations
Requires an additional proxy layer, which may add a small amount of latency
High-risk levels require Docker environment support
The Gemini Agent requires a Google API key

How to use

Install MCP Bridge
Ensure that Node.js 18+ is installed, and then run npm install to install dependencies
Configure MCP servers
Edit the mcp_config.json file and add the configuration of the MCP servers you need to connect to
Start MCP Bridge
Run node mcp-bridge.js to start the proxy service
Use the API or Gemini Agent
Call the API directly through HTTP requests or use the MCP-Gemini Agent for natural language interaction

Usage examples

Browse the file system
Access and browse the file system of a remote server through MCP Bridge
Send a Slack message
Send a message to a specified channel through the Slack MCP server
Confirm high-risk operations
Execute medium-risk operations that require confirmation

Frequently Asked Questions

Which MCP servers does MCP Bridge support?
How to add a new MCP server?
How are risk levels determined?
What permissions does the Gemini Agent require?

Related resources

Official documentation of Model Context Protocol
Official documentation and specifications of the MCP protocol
GitHub repository
Source code and the latest version of MCP Bridge
List of MCP servers
List of official and community-maintained MCP servers

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/directory"],
      "riskLevel": 2
    },
    "slack": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-slack"],
      "env": {
        "SLACK_BOT_TOKEN": "your-slack-token",
        "SLACK_TEAM_ID": "your-team-id"
      },
      "riskLevel": 1
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
7.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
7.4K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
4.6K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
8.5K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
6.7K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
6.4K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
7.3K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
8.1K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
20.0K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.2K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
58.9K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
56.1K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
26.5K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
39.2K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase