toolkit-mcp
An MCP server offering developer utilities including JSON validation, base64 encoding, timestamp conversion, and hashing, built with a clean architecture for easy extensibility.
README
toolkit-mcp
Meta-MCP & A2A server — tools for building, testing, and connecting AI agents.
Tools
Meta-MCP — Tools about MCP itself
| Tool | Description |
|---|---|
mcp_validate_config |
Validate MCP server config (Claude / Cursor mcpServers) |
mcp_inspect_schema |
Analyze a JSON Schema and explain its MCP tool mapping |
mcp_format_response |
Wrap data into proper MCP response format |
A2A — Agent-to-Agent capability registry
| Tool | Description |
|---|---|
a2a_register |
Register an agent's capabilities |
a2a_discover |
Find agents by capability or keyword |
a2a_list_all |
List all registered agents |
a2a_submit_task |
Submit a task for processing |
a2a_get_task |
Check task status and get results |
a2a_list_tasks |
List all tasks, optionally filtered by status |
Architecture
server.py
├── ToolRegistry ← Decorator-based framework with auto schema inference
├── Meta-MCP Tools ← MCP diagnostic, validation, formatting utilities
└── A2A Module ← In-memory agent registry & task delegation system
Adding a new tool:
@registry.tool("tool_name", "What it does")
def my_tool(param1: str, param2: int = 42) -> dict:
"""Docstring becomes tool description."""
return {"result": param1 * param2}
Schema is auto-generated from type hints.
Setup
pip install "mcp[cli]"
python server.py # stdio mode
python server.py --transport sse # HTTP mode (port 8080)
Claude Desktop
{
"mcpServers": {
"toolkit": {
"command": "python",
"args": ["/path/to/server.py"]
}
}
}
Requirements
- Python 3.11+
- MCP SDK (
mcp[cli])
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.