toolbridge-mcp-server
Click on "Install 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., "@toolbridge-mcp-serverquery the database for users who signed up last week"
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.
ToolBridge MCP Server
Model Context Protocol (MCP) Server for ToolBridge โ bridging tools and AI agents through a standardized protocol.
Overview
ToolBridge MCP Server implements the Model Context Protocol (MCP) to expose tools, resources, and prompts to AI agents in a standardized way. It acts as a bridge between AI agents and external tools, APIs, databases, and services.
Features
๐ MCP 1.0+ Compatible โ Full implementation of the Model Context Protocol
๐ง Tool Registration โ Decorator-based tool registration with schema validation
๐ฆ Resource Management โ Expose files, databases, and APIs as MCP resources
๐ฌ Prompt Templates โ Reusable prompt templates for common workflows
๐ Authentication & Authorization โ Built-in auth with API keys, OAuth, and JWT
๐ Observability โ Structured logging, metrics, and tracing
๐ณ Docker Ready โ Production-ready containerization
๐งช Well Tested โ Comprehensive test suite with pytest
Quick Start
Prerequisites
Python 3.10+
pip / uv / poetry
Installation
# Clone the repository
git clone https://github.com/toolbridge/mcp-server.git
cd mcp-server
# Install dependencies
pip install -e ".[dev]"
# Or with uv (recommended)
uv pip install -e ".[dev]"Configuration
Copy the example environment file and configure:
cp .env.example .env
# Edit .env with your settingsRunning the Server
# Development mode with auto-reload
python -m mcp_server
# Or using the CLI
mcp-server run --reload
# Production mode
mcp-server run --host 0.0.0.0 --port 8000Using with MCP Clients
{
"mcpServers": {
"toolbridge": {
"command": "python",
"args": ["-m", "mcp_server"],
"env": {
"MCP_SERVER_HOST": "localhost",
"MCP_SERVER_PORT": "8000"
}
}
}
}Project Structure
toolbridge-mcp-server/
โโโ mcp_server/ # Main MCP server package
โ โโโ __init__.py
โ โโโ server.py # Core MCP server implementation
โ โโโ tools/ # Built-in tools
โ โ โโโ __init__.py
โ โ โโโ filesystem.py
โ โ โโโ web_search.py
โ โ โโโ code_execution.py
โ โ โโโ api_client.py
โ โโโ resources/ # Resource providers
โ โ โโโ __init__.py
โ โ โโโ filesystem.py
โ โ โโโ database.py
โ โโโ prompts/ # Prompt templates
โ โ โโโ __init__.py
โ โ โโโ templates.py
โ โโโ auth/ # Authentication
โ โ โโโ __init__.py
โ โ โโโ api_key.py
โ โ โโโ jwt.py
โ โโโ config.py # Configuration management
โ โโโ logging.py # Structured logging
โ โโโ middleware/ # MCP middleware
โ โโโ __init__.py
โ โโโ auth.py
โ โโโ logging.py
โโโ agent/ # Agent integration layer
โ โโโ __init__.py
โ โโโ base.py
โ โโโ orchestrator.py
โ โโโ tools.py
โโโ tests/ # Test suite
โ โโโ unit/
โ โโโ integration/
โ โโโ fixtures/
โ โโโ conftest.py
โโโ docs/ # Documentation
โ โโโ index.md
โ โโโ getting-started.md
โ โโโ tools.md
โ โโโ resources.md
โ โโโ deployment.md
โโโ docker/ # Docker configuration
โ โโโ Dockerfile
โ โโโ docker-compose.yml
โ โโโ docker-compose.dev.yml
โโโ sample_data/ # Sample data for testing
โโโ scripts/ # Utility scripts
โโโ .env.example # Environment template
โโโ requirements.txt # Production dependencies
โโโ pyproject.toml # Build configuration
โโโ LICENSE # MIT License
โโโ README.md # This fileDevelopment
Running Tests
# Run all tests
pytest
# Run with coverage
pytest --cov=mcp_server --cov-report=html
# Run specific test file
pytest tests/unit/test_tools.py -vCode Quality
# Format code
ruff format .
# Lint
ruff check .
# Type check
mypy mcp_server
# Pre-commit hooks
pre-commit install
pre-commit run --all-filesAdding Tools
# mcp_server/tools/my_tool.py
from mcp_server.tools import tool
from pydantic import BaseModel
class MyToolInput(BaseModel):
query: str
limit: int = 10
@tool(
name="my_tool",
description="Description of what this tool does",
)
async def my_tool(input: MyToolInput) -> str:
# Implementation here
return f"Result for: {input.query}"Configuration
Environment variables (see .env.example):
Variable | Description | Default |
| Server host |
|
| Server port |
|
| Log level |
|
| API key for auth | - |
| JWT secret | - |
Deployment
Docker
# Build
docker build -t toolbridge/mcp-server .
# Run
docker run -p 8000:8000 --env-file .env toolbridge/mcp-server
# Docker Compose
docker-compose up -dKubernetes
kubectl apply -f k8s/Contributing
Fork the repository
Create a feature branch
Make your changes
Run tests and linting
Submit a PR
License
MIT License โ see LICENSE for details.
Links
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LeelaissakAttota/toolbridge-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server