Consul MCP Server
A Model Control Protocol (MCP) server for interacting with HashiCorp Consul service discovery and service mesh. This implementation follows Anthropic's MCP specification and allows Claude to analyze your microservices architecture, create diagrams, identify issues, and provide recommendations through natural language interaction.
What is Model Control Protocol?
Model Control Protocol (MCP) is a specification developed by Anthropic that enables AI models like Claude to interact with external tools and APIs. This implementation connects AI Agents to your Consul infrastructure, allowing you to manage and analyze your services using natural language.
Features
- List and analyze services registered in Consul
- Identify and diagnose failing health checks
Requirements
- Node.js 18+
- uv
- python
- A running Consul instance (local or remote)
- Claude Desktop or Cursor IDE with Claude integration
Installation
-
Clone consul mcp repository
git clone https://github.com/kswap/consul-mcp.git cd consul-mcp -
Install uv Install from uv documentation.
-
Install node Install from: nodejs or using a package manager.
-
Setup virtual environment
uv venv && uv sync source .venv/bin/activate export PYTHONPATH=. -
Run Server
python src/server/main.py- Integrate with Claude desktop
- In Claude Desktop, open Settings (⌘+,) and navigate to the "Developer" tab.
- Click "Edit Config" at the bottom of the window.
- Edit the file (~/Library/Application Support/Claude/claude_desktop_config.json) to add code similar to the following, then Save the file.
{ "mcpServers": { "consul_mcp": { "command": "/opt/homebrew/bin/uv", "args": [ "run", "--with", "mcp[cli]", "mcp", "run", "/absolute/path/to/main.py" ], "env": { "PYTHONPATH": "/absolute/path/to/consul-mcp" } } } } - Restart Claude Desktop to ensure the MCP server is properly loaded.
- Integrate with Claude desktop
Example Prompts
Once connected, try these prompts with Claude:
- "Show me all services registered in Consul"
- "Which services have failing health checks?"
Contributing
Contributions are welcome! Please feel free to submit a pull request.
Recommend MCP Servers 💡
@modelcontextprotocol/server-filesystem
A Node.js server implementing the Model Context Protocol (MCP) to enable AI models to perform various filesystem operations, including reading, writing, creating, listing, moving, searching files and directories, and retrieving file metadata, with dynamic access control via MCP Roots.
mcp-monitor
A system monitoring tool that exposes system metrics via the Model Context Protocol (MCP). This tool allows LLMs to retrieve real-time system information through an MCP-compatible interface.
mcp-create
A dynamic MCP server management service that creates, runs, and manages MCP servers dynamically
cfbd-mcp-server
An MCP server that provides access to comprehensive college football statistics and data from the College Football Data API V2, enabling AI assistants like Claude Desktop to query game results, team records, player statistics, and more using natural language.
AgentMode
AgentMode is an enterprise-ready platform that provides a unified MCP server to connect AI coding assistants to various development tools, offering features like codebase search, issue identification, and fix testing.
@agentset/mcp
An MCP server for Agentset, an open-source platform for Retrieval-Augmented Generation (RAG), designed for building intelligent, document-based applications.