Axiom MCP Server

For guidance on when to use Axiom MCP Server and Axiom Skills, see AI agents.

For the full list of tools and prompts with example queries, see MCP tools reference.

If your agent doesn’t have an Axiom organization to work in yet, it can provision a temporary one itself and hand you a claim link later. For more information, see Agent-created organizations.

Current capabilities#

Tools and prompts#

Axiom MCP Server works with AI agents that support MCP. It exposes tools for querying data, exploring datasets and metrics, and managing dashboards, monitors, and notifiers, plus prebuilt prompts for common investigations. For the full list with example queries, see MCP tools reference.

The Axiom-hosted MCP Server is located in the US. When you query your data using a remote MCP connection, query results are routed through US infrastructure.

Prerequisites#

Create an Axiom account.
Create a dataset in Axiom where you send your data.

Setup#

Remote MCP URL: https://mcp.axiom.co/mcp

Remote MCP with OAuth is the recommended setup for most use cases.

Install with add-mcp#

Use the add-mcp CLI to add Axiom MCP Server to your coding agents:

npx -y add-mcp https://mcp.axiom.co/mcp -g

Authenticate in your browser when the agent prompts you.

Optional flags:

Omit -g to install for the current project only.
Add -y to skip confirmation prompts.
Target specific agents with -a, for example -a cursor -a claude-code.

Quick setup#

Axiom MCP Server works with MCP-compatible clients. Use the tabs below for client-specific steps without add-mcp:

ClaudeClaude CodeCursorVS CodeCodexChatGPTWindsurfGemini

Pro, Max, Team, or Enterprise#

Add Axiom to Claude.
Review the prefilled name and URL, then confirm.
Click Connect and authenticate in your browser.

On Team or Enterprise plans, an organization admin may need to add the connector first. For more information, see the Claude documentation.

Free#

On the Free plan, use Claude Desktop with mcp-remote:

Install Claude Desktop.
In Claude Desktop, go to Settings > Developers, and then click Edit Config.
Add the following to claude_desktop_config.json:

claude_desktop_config.json

{
  "mcpServers": {
    "axiom": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.axiom.co/mcp"]
    }
  }
}

Restart Claude Desktop.
Authenticate in your browser.

claude mcp add --transport http axiom https://mcp.axiom.co/mcp

In Claude Code, run /mcp and authenticate in your browser.

Add Axiom to Cursor.

Optional: add the following to your Cursor MCP config instead:

{
  "mcpServers": {
    "axiom": {
      "url": "https://mcp.axiom.co/mcp"
    }
  }
}

To add Axiom MCP Server for your Cursor team, go to Dashboard > Integrations & MCP in Cursor, and then add Axiom MCP Server using the URL https://mcp.axiom.co/mcp. To make it available to Cursor cloud agents, you must also make it available by default on Dashboard > Plugins.

Add Axiom to VS Code.

Optional: add the following to .vscode/mcp.json instead:

{
  "servers": {
    "axiom": {
      "type": "http",
      "url": "https://mcp.axiom.co/mcp"
    }
  }
}

For setup and authentication, see the VS Code MCP documentation.

codex mcp add axiom --url https://mcp.axiom.co/mcp

For setup and authentication, see the Codex MCP documentation.

Follow the ChatGPT Developer mode guide to add a remote MCP app with these settings:

Name: Axiom
MCP server URL: https://mcp.axiom.co/mcp
Authentication: OAuth

Add the following to your Windsurf mcp_config.json:

{
  "mcpServers": {
    "axiom": {
      "serverUrl": "https://mcp.axiom.co/mcp"
    }
  }
}

For setup and authentication, see the Windsurf MCP documentation.

Add the following to ~/.gemini/settings.json for Gemini CLI or Gemini Code Assist:

{
  "mcpServers": {
    "axiom": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.axiom.co/mcp"]
    }
  }
}

For setup and authentication, see the Gemini CLI MCP documentation or the Gemini Code Assist agent mode documentation.

Goose#

Add Axiom to Goose.

For setup and authentication, see the Goose extension documentation.

Amp#

amp mcp add axiom https://mcp.axiom.co/mcp

For setup and authentication, see the Amp MCP documentation.

fx#

fx mcp add --transport http axiom https://mcp.axiom.co/mcp

For setup and authentication, see the fx MCP documentation.

OpenCode#

Add the following to your OpenCode config (opencode.json):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "axiom": {
      "type": "remote",
      "url": "https://mcp.axiom.co/mcp",
      "oauth": {}
    }
  }
}

For setup and authentication, see the OpenCode MCP documentation.

Warp#

Use this configuration to add Axiom as a Streamable HTTP server in Warp:

{
  "Axiom": {
    "url": "https://mcp.axiom.co/mcp"
  }
}

For setup and authentication, see the Warp MCP documentation.

Zed#

Add the following to your Zed settings (settings.json):

{
  "context_servers": {
    "axiom": {
      "url": "https://mcp.axiom.co/mcp"
    }
  }
}

For setup and authentication, see the Zed MCP documentation.

Other#

If your agent supports remote MCP over HTTP:

Name: Axiom
URL: https://mcp.axiom.co/mcp

If your agent doesn’t support remote MCP directly, use mcp-remote:

{
  "mcpServers": {
    "axiom": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.axiom.co/mcp"]
    }
  }
}

For legacy clients that only support the older HTTP+SSE transport, use https://mcp.axiom.co/sse instead.

Header-based authentication#

If your AI agent doesn’t support browser-based OAuth (for example, Agent Builder from OpenAI), authenticate with headers:

Create a personal access token.
Determine organization ID.
Configure your AI agent to use https://mcp.axiom.co/mcp.
Send these headers with each request:
- Authorization: Bearer PERSONAL_ACCESS_TOKEN
- x-axiom-org-id: ORGANIZATION_ID

Info: Replace PERSONAL_ACCESS_TOKEN with the personal access token you have generated.

Replace ORGANIZATION_ID with your organization ID. For more information, see Determine organization ID.

If your agent only supports the Authorization header, pass the organization ID as a URL parameter: `https://mcp.axiom.co/mcp?org-id=ORGANIZATION_ID`

Optional: run Axiom MCP Server locally for more control.

Local setup

Local setup#

With the local setup:

You run the server yourself.
You authenticate with an API token instead of OAuth 2.0.
You can’t use the MCP prompts.

Install#

Run the following to install the latest built binary from GitHub:

go install github.com/axiomhq/axiom-mcp@latest

Create API token#

Create an API token in Axiom with permissions to update the dataset you have created.

Configure#

Configure your AI agent with a config file or environment variables.

Config file

Create a config file where you specify the authentication and configuration details. For example:

config.txt

token 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

Info: Replace API_TOKEN with the Axiom API token you have generated. For added security, store the API token in an environment variable.

Optionally, configure the rate and the burst limits at the query, dataset, and monitor levels. The rate limit is the maximum number of requests that your AI agent can make per second. The burst limit is the maximum number of requests that your AI agent can make in a short period (burst) before the rate limit applies to further requests.

In the settings of your AI agent, reference the binary file of Axiom MCP Server and the config file you have previously created.

For example, if you use the Claude desktop app, add axiom to the mcpServers section of the Claude configuration file. The default path is ~/Library/Application Support/Claude/claude_desktop_config.json on MacOS and %APPDATA%\Claude\claude_desktop_config.json on Windows.

claude_desktop_config.json
```
{
  "mcpServers": {
    "axiom": {
      "command": "PATH_AXIOM_MCP_BINARY",
      "args": [
        "--config",
        "PATH_AXIOM_MCP_CONFIG"
      ]
    }
  }
}
```

Info: Replace PATH_AXIOM_MCP_BINARY with the path the binary file of Axiom MCP Server.

Replace PATH_AXIOM_MCP_CONFIG with the path the config file you have previously created.

Environment variables

In the settings of your AI agent, use environment variables to specify the authentication details and the binary file of Axiom MCP Server.

For example, if you use the Claude desktop app, add axiom to the mcpServers section of the Claude configuration file. The default path is ~/Library/Application Support/Claude/claude_desktop_config.json on MacOS and %APPDATA%\Claude\claude_desktop_config.json on Windows.

claude_desktop_config.json

{
  "mcpServers": {
    "axiom": {
      "command": "PATH_AXIOM_MCP_BINARY",
      "env": {
        "AXIOM_TOKEN": "API_TOKEN",
        "AXIOM_URL": "https://api.axiom.co",
        "AXIOM_QUERY_RATE": "1",
        "AXIOM_QUERY_BURST": "1",
        "AXIOM_DATASETS_RATE": "1",
        "AXIOM_DATASETS_BURST": "1",
        "AXIOM_MONITORS_RATE": "1",
        "AXIOM_MONITORS_BURST": "1"
      }
    }
  }
}

Info: Replace PATH_AXIOM_MCP_BINARY with the path the binary file of Axiom MCP Server.

Replace API_TOKEN with the Axiom API token you have generated. For added security, store the API token in an environment variable.

Replace AXIOM_DOMAIN with the base domain of your edge deployment. For more information, see Edge deployments.

Optionally, configure the rate and the burst limits at the query, dataset, and monitor levels. The rate limit is the maximum number of requests that your AI agent can make per second. The burst limit is the maximum number of requests that your AI agent can make in a short period (burst) before the rate limit applies to further requests.

Token hygiene#

The remote MCP Server uses OAuth for authentication which handles credential isolation automatically. Agents never see your tokens. You can revoke access at any time.

For the local setup or when using Axiom Skills, you configure API tokens directly. For detailed guidance on secure token configuration, see Token hygiene for AI agents.

Limit query costs#

Query cost limits let you cap the hourly and daily query costs of an AI agent so it can query your data autonomously without creating unexpected costs:

For the local setup, set query cost limits on the API token you create for the agent.
For the remote MCP Server, the agent acts as your user account through OAuth, so set query cost limits on your roles instead.

For more information, see Set query cost limits for AI agents.

Use MCP Server#

After setup, ask your agent about your data. For example:

“List datasets.”
“List the fields in the dataset logs.”
“Get the most common status codes in the last 30 minutes in the dataset logs.”

Optional: use the prebuilt prompts in clients that support MCP prompts.

For more examples and the full tool list, see MCP tools reference.

Revoke access#

To revoke access:

In Axiom, go to Settings > Profile.
In the Sessions section, find the session where you authorized your AI client, and then click Delete on the right.

If you connected with the mcp-remote library, clear the .mcp-auth folder. On a Mac, the default path is ~/.mcp-auth.

Updated Sep 25, 2026