axone
🤖 Axone’s MCP server – gateway to the dataverse for AI-powered tools
claude mcp add --transport stdio axone-protocol-axone-mcp axone-mcp serve stdio --node-grpc grpc.dentrite.axone.xyz:443
How to use
Axone’s MCP server acts as a gateway to Axone’s dataverse, exposing Axone’s AI-powered capabilities through the Model-Context Protocol. It supports different transport modes, allowing clients to query resources and invoke tools via a standardized interface. The README highlights a few usage patterns: running the server with STDIO transport, or with SSE transport, and integrating with Claude Desktop via a designated MCP server entry.
Common usage patterns include querying the server to execute available tools (for example, get_resource_governance_code) and wiring the server into clients like Claude Desktop or other MCP-enabled tooling. The provided example demonstrates a Claude Desktop configuration that points to the axone-mcp binary with the appropriate gRPC node endpoint. You can also run the server directly in SSE or STDIO modes, specifying the Axone node gRPC endpoint to connect to. The server essentially forwards requests to Axone’s data and tooling endpoints in a standards-compliant way, enabling AI-assisted workflows through MCP-compatible clients.
How to install
Prerequisites:
- A supported runtime for the server (the project is Go-based and released as a binary).
- Optional: Docker if you prefer containerized usage.
Installation steps:
- Download the latest release binary from the Axone MCP releases page and place it in your PATH. For example:
- Linux/macOS: curl -LO https://github.com/axone-protocol/axone-mcp/releases/latest/download/axone-mcp-<version>-linux-amd64 && chmod +x axone-mcp && sudo mv axone-mcp /usr/local/bin/
- Windows: download the release executable and add its directory to your PATH.
- Verify installation:
- axone-mcp --version
- Run the server (STDIO transport as default):
- axone-mcp serve stdio --node-grpc grpc.dentrite.axone.xyz:443
- Alternatively, run in SSE transport:
- axone-mcp serve sse --listen-addr localhost:8080 --node-grpc grpc.dentrite.axone.xyz:443
If you prefer containerized usage:
- Build a Docker image using the provided Makefile or a Dockerfile if included in the repo, then run a container with the appropriate entrypoint and environment. (Refer to the project’s Docker guidance in the repository if available.)
Additional notes
Tips and notes:
- The server connects to Axone’s node via gRPC. Ensure the provided --node-grpc endpoint is accessible from your environment.
- The Claude Desktop integration example shows how to wire the MCP server into Claude’s configuration by listing the axone-mcp command and its arguments under mcpServers.
- If you need to change endpoints or listen addresses, adjust the --node-grpc and --listen-addr flags accordingly.
- Typical tools exposed by the MCP server include resources-related operations like get_resource_governance_code. The exact tool set is announced in the README and may evolve with releases.
- For builds, Go tooling or Docker is recommended depending on your deployment preference. Ensure prerequisites (Go, or Docker) are installed as documented in the repo’s build notes.
Related MCP Servers
mcp-language
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
mcp-victoriametrics
The implementation of Model Context Protocol (MCP) server for VictoriaMetrics
kodit
👩‍💻 MCP server to index external repositories
mcp-difyworkflow
mcp-difyworkflow-server is an mcp server Tools application that implements the query and invocation of Dify workflows, supporting the on-demand operation of multiple custom Dify workflows.
mcp
✨ MCP Server for Effortless Dependency Updates
mcp
Teamwork.com MCP server