mcp -axiom
Axiom Model Context Protocol Server
claude mcp add --transport stdio axiomhq-mcp-server-axiom axiom-mcp --config /path/to/your/config.txt \ --env AXIOM_URL="https://api.axiom.co" \ --env AXIOM_TOKEN="xaat-your-api-token" \ --env AXIOM_QUERY_RATE="1" \ --env AXIOM_QUERY_BURST="1" \ --env AXIOM_DATASETS_RATE="1" \ --env AXIOM_MONITORS_RATE="1" \ --env AXIOM_DATASETS_BURST="1" \ --env AXIOM_MONITORS_BURST="1"
How to use
This MCP server implementation exposes six MCP tools for querying and managing data in Axiom via the Model Context Protocol: queryApl to run APL queries against Axiom datasets, listDatasets to enumerate available datasets, getDatasetSchema to retrieve a dataset's schema, getSavedQueries to fetch saved or starred APL queries, getMonitors to list monitoring configurations, and getMonitorsHistory to view monitor execution history. All tools require a valid Axiom API token provided as the token parameter or via environment variables, and requests are authenticated against your Axiom tenant. You can configure the MCP server with a config file or environment variables, and wire it into clients such as Claude by specifying the server in the Claude MCP configuration.
To use the server, start the axiom-mcp binary with the appropriate configuration (e.g., a config.txt file) containing your token and endpoint details. The Claude integration example shows how to point Claude at the MCP server and provides an example JSON snippet for the mcpServers section, including optional environment variables for authentication and rate limiting.
How to install
Prerequisites:
- A supported environment (Linux, macOS) with Go installed if you are building from source, or prebuilt binaries available from releases.
- An Ax iom API token and the API URL for your tenant.
Install from releases (recommended):
- Download the latest built binary from the releases page.
- Place the binary somewhere on your PATH, e.g. /usr/local/bin/axiom-mcp
- Create a config file (config.txt) with your credentials and rate settings, for example: token xaat-your-api-token url https://api.axiom.co query-rate 1 query-burst 1 datasets-rate 1 datasets-burst 1 monitors-rate 1 monitors-burst 1
- Run the MCP server: axiom-mcp --config /path/to/config.txt
If building from source:
- Ensure Go is installed (go1.20+ recommended).
- Build the binary: go install github.com/axiomhq/axiom-mcp@latest
- Run the server with your config as above.
Additional notes
Notes and tips:
- This MCP server is deprecated in favor of the official Axiom MCP Server. If you are starting fresh, consider using mcp.axiom.co instead.
- The server requires authentication via an API token. You can provide this token in a config file, as command-line flags, or via environment variables (AXIOM_TOKEN, AXIOM_URL).
- If you upgrade or migrate, ensure your token and endpoint URL are kept secure and not exposed in logs.
- The configuration supports per-tool rate limiting via query-rate, query-burst, datasets-rate, datasets-burst, monitors-rate, and monitors-burst.
- The configuration example uses a config.txt with token and URL; you can also provide these values via environment variables in the env block of the Claude integration configuration.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go