mcpField
M
MCP Server for Axiom

MCP Server for Axiom

Local
github.com/ThetaBirdData & Analytics1Updated 91w ago
Repository

About MCP Server for Axiom

MCP Server for Axiom is a JavaScript implementation of the Axiom MCP server, distributed as an npm module for Node.js environments. It lets AI agents run Axiom Processing Language queries and list datasets.

Key features

  1. 01Run APL queries
  2. 02List Axiom datasets
  3. 03Configure API URL and organization
  4. 04Set query and dataset rate limits

Use cases

  1. 01Query Axiom data from an AI agent
  2. 02Inspect available datasets
  3. 03Integrate Axiom MCP tools in Node.js

MCP support

The server exposes `queryApl` and `listDatasets` tools to MCP clients, using configured Axiom credentials and organization details.

#mcp-server#axiom-js#data-query#axiom#javascript

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "axiom-js": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-axiom"
      ],
      "env": {
        "AXIOM_TOKEN": "<AXIOM_TOKEN>",
        "AXIOM_URL": "<AXIOM_URL>",
        "AXIOM_ORG_ID": "<AXIOM_ORG_ID>"
      }
    }
  }
}
Run commandnpx -y mcp-server-axiom
Environment variables to set
AXIOM_TOKENSecret
AXIOM_URL
AXIOM_ORG_ID

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-server-axiom

Tools

3

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
querystringYesThe APL query to run

Details

From the project README

MCP Server for Axiom

A JavaScript port of the official Axiom MCP server that enables AI agents to query data using Axiom Processing Language (APL).

README image

This implementation provides the same functionality as the original Go version but packaged as an npm module for easier integration with Node.js environments.

Installation & Usage

MCP Configuration

You can run this MCP server directly using npx. Add the following configuration to your MCP configuration file:

{
  "axiom": {
    "command": "npx",
    "args": ["-y", "mcp-server-axiom"],
    "env": {
      "AXIOM_TOKEN": "<AXIOM_TOKEN_HERE>",
      "AXIOM_URL": "https://api.axiom.co",
      "AXIOM_ORG_ID": "<AXIOM_ORG_ID_HERE>"
    }
  }
}
Local Development & Testing
Installation
npm install -g mcp-server-axiom
Environment Variables

The server can be configured using environment variables:

  • AXIOM_TOKEN (required): Your Axiom API token
  • AXIOM_ORG_ID (required): Your Axiom organization ID
  • AXIOM_URL (optional): Custom Axiom API URL (defaults to https://api.axiom.co)
  • AXIOM_QUERY_RATE (optional): Queries per second limit (default: 1)
  • AXIOM_QUERY_BURST (optional): Query burst capacity (default: 1)
  • AXIOM_DATASETS_RATE (optional): Dataset list operations per second (default: 1)
  • AXIOM_DATASETS_BURST (optional): Dataset list burst capacity (default: 1)
  • PORT (optional): Server port (default: 3000)
Running the Server Locally
  1. Using environment variables:
export AXIOM_TOKEN=your_token
mcp-server-axiom
  1. Using a config file:
mcp-server-axiom config.json

Example config.json:

{
  "token": "your_token",
  "url": "https://custom.axiom.co",
  "orgId": "your_org_id",
  "queryRate": 2,
  "queryBurst": 5,
  "datasetsRate": 1,
  "datasetsBurst": 2
}

API Endpoints

  • GET /: Get server implementation info
  • GET /tools: List available tools
  • POST /tools/:name/call: Call a specific tool
    • Available tools:
      • queryApl: Execute APL queries
      • listDatasets: List available datasets
Example Tool Calls
  1. Query APL:
curl -X POST http://localhost:3000/tools/queryApl/call \
  -H "Content-Type: application/json" \
  -d '{
    "arguments": {
      "query": "['logs'] | where ['severity'] == \"error\" | limit 10"
    }
  }'
  1. List Datasets:
curl -X POST http://localhost:3000/tools/listDatasets/call \
  -H "Content-Type: application/json" \
  -d '{
    "arguments": {}
  }'

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.