Skip to main content
Glama
rawtreedb

RawTree MCP Server

Official
by rawtreedb

RawTree MCP Server

An MCP server for RawTree, an analytics database for unstructured data. Query data with SQL, insert JSON, inspect table schemas, review RawTree logs, and manage project credentials from MCP clients like Claude Code, Cursor, and Claude Desktop.

Features

  • Queries — Run read-only SQL against a RawTree project and receive JSON rows, metadata, statistics, and hints.

  • Ingest — Insert a single JSON object, arrays of JSON objects, or public URL data. Supports RawTree built-in transforms for OTLP traces/logs/metrics, CloudWatch Logs, CloudTrail, and Firehose.

  • Tables — List tables, describe table columns and sizes, and delete tables after explicit confirmation.

  • Logs — Inspect RawTree query and insert history with structured filters for type, status, origin, table, hints, time window, and pagination.

  • API Keys — List, create, and revoke RawTree API keys for a project. Creation responses include the one-time token.

  • Projects — Get the current project from API-key context.

  • Transports — Supports stdio for local MCP clients and Streamable HTTP for remote or multi-client deployments.

Setup

Create a RawTree API key from the RawTree CLI, dashboard, or API. A project API key starts with rt_ and is enough for data tools such as run-query, insert-json, list-tables, and list-logs.

The get_project tool uses the current token to read project identity from RawTree's keys endpoint, with a tables endpoint fallback for non-admin read-capable project API keys.

Usage

The server supports two transport modes: stdio (default) and HTTP.

Stdio Transport

Quick Setup

npx add-mcp @rawtree/mcp --name rawtree --env "RAWTREE_API_KEY=rt_xxxxxxxxx"

Claude Code

claude mcp add rawtree -e RAWTREE_API_KEY=rt_xxxxxxxxx -- npx -y @rawtree/mcp

Cursor

Open the command palette and choose "Cursor Settings" > "MCP" > "Add new global MCP server".

{
  "mcpServers": {
    "rawtree": {
      "command": "npx",
      "args": ["-y", "@rawtree/mcp"],
      "env": {
        "RAWTREE_API_KEY": "rt_xxxxxxxxx"
      }
    }
  }
}

Claude Desktop

Open Claude Desktop settings > "Developer" tab > "Edit Config".

{
  "mcpServers": {
    "rawtree": {
      "command": "npx",
      "args": ["-y", "@rawtree/mcp"],
      "env": {
        "RAWTREE_API_KEY": "rt_xxxxxxxxx"
      }
    }
  }
}

HTTP Transport

Run the server over HTTP for remote or web-based integrations. In HTTP mode, each MCP client authenticates by passing its RawTree API key as a Bearer token in the Authorization header.

Start the server:

npx -y @rawtree/mcp --http --port 3000

The server listens on http://127.0.0.1:3000 and exposes the MCP endpoint at /mcp using Streamable HTTP.

Claude Code

claude mcp add rawtree --transport http http://127.0.0.1:3000/mcp --header "Authorization: Bearer rt_xxxxxxxxx"

Cursor

{
  "mcpServers": {
    "rawtree": {
      "url": "http://127.0.0.1:3000/mcp",
      "headers": {
        "Authorization": "Bearer rt_xxxxxxxxx"
      }
    }
  }
}

You can also set the port via the MCP_PORT environment variable:

MCP_PORT=3000 npx -y @rawtree/mcp --http

Scoped Routes

Project API keys are already scoped to one project, so most users do not need these settings.

When using scoped routes, set both organization and project:

RAWTREE_API_KEY=rt_xxx \
RAWTREE_ORG=my_org \
RAWTREE_PROJECT=analytics \
npx -y @rawtree/mcp

Options

  • --key: RawTree project API key for stdio mode

  • --token: Alias for --key

  • --api-url: RawTree API URL, defaults to https://api.rawtree.com

  • --url: Alias for --api-url

  • --org: Organization name for scoped routes

  • --organization: Alias for --org

  • --project: Project name for scoped routes

  • --http: Use HTTP transport instead of stdio

  • --port: HTTP port when using --http, default 3000 or MCP_PORT

Environment variables:

  • RAWTREE_API_KEY: RawTree project API key

  • RAWTREE_TOKEN: Alias for RAWTREE_API_KEY

  • RAWTREE_URL: RawTree API URL

  • RAWTREE_ORG: Organization name for scoped routes

  • RAWTREE_PROJECT: Project name for scoped routes

  • MCP_PORT: HTTP port when using --http

Tools

Data

  • check-health — Check that the configured RawTree API endpoint is reachable.

  • run-query — Run read-only SQL and return RawTree's JSON query response.

  • insert-json — Insert JSON object(s) into a table, optionally with a RawTree transform.

  • insert-from-url — Ingest data from a public URL and return RawTree's NDJSON progress stream.

Tables

  • list-tables — List tables in the configured project.

  • describe-table — Inspect columns, row count, byte count, project, and organization.

  • delete-table — Delete a table after explicit confirmation. Requires admin permission.

Logs

  • list-logs — Read RawTree query and insert logs. Defaults to the last hour when no time window is provided.

Structured log filters include:

{
  "statuses": ["error"],
  "types": ["insert"],
  "tables": ["events"],
  "origins": ["api"],
  "hints": "any",
  "limit": 50
}

API Keys

  • list-api-keys — List API keys for the configured project.

  • create-api-key — Create a key with admin, read_write, write_only, or read_only permission.

  • delete-api-key — Revoke a key after explicit confirmation.

Projects

  • get_project — Return the current project as { "name": "...", "organization": { "name": "..." } }.

Examples

Query

{
  "sql": "SELECT count() AS rows FROM events"
}

Insert JSON

{
  "table": "events",
  "data": [
    {
      "event": "signup",
      "user_id": "user_123",
      "source": "mcp"
    }
  ]
}

Insert OTLP Traces

{
  "table": "traces",
  "transform": "otlp-traces",
  "data": {
    "resource": {
      "attributes": [
        {
          "key": "service.name",
          "value": {
            "stringValue": "api"
          }
        }
      ]
    },
    "scopeSpans": [
      {
        "spans": [
          {
            "name": "GET /health",
            "spanId": "abc"
          }
        ]
      }
    ]
  }
}

Debug Failed Inserts

{
  "statuses": ["error"],
  "types": ["insert"],
  "startTime": "2026-05-28T09:00:00.000Z",
  "endTime": "2026-05-28T10:00:00.000Z",
  "limit": 25
}

Local Development

  1. Install and build:

pnpm install
pnpm build
  1. Use the local build from an MCP client:

claude mcp add rawtree -e RAWTREE_API_KEY=rt_xxxxxxxxx -- node /absolute/path/to/rawtree-mcp/dist/index.js

Live Testing with an MCP Client

Run TypeScript in watch mode, then point a separate MCP client at the built server:

pnpm tsc --watch
{
  "mcpServers": {
    "rawtree-dev": {
      "command": "node",
      "args": ["/absolute/path/to/rawtree-mcp/dist/index.js"],
      "env": {
        "RAWTREE_API_KEY": "rt_xxxxxxxxx"
      }
    }
  }
}

Restart the MCP client session after each rebuild.

Testing with MCP Inspector

Build first:

pnpm build

Start the inspector:

RAWTREE_API_KEY=rt_xxxxxxxxx pnpm inspector

In the Inspector UI, choose stdio:

  • Command: node

  • Args: dist/index.js

  • Environment: RAWTREE_API_KEY=rt_xxxxxxxxx

RawTree References

Install Server
A
license - permissive license
A
quality
C
maintenance

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rawtreedb/rawtree-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server