Skip to main content
Glama
Sign In
geldata

Gel MCP Server

by geldata
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Gel MCP server

This MCP server provides tools and resources that help coding agents use the Gel database.

Available tools

  1. execute_query: run a query against the Gel instance configured in the current project. Supports arguments and globals.

  2. try_query: run a query in a transaction that gets rolled back in the end, preventing actual data modification.

  3. list_examples and fetch_example: access code examples for advanced workflows such as configuring the AI extension.

  4. list_rules and fetch_rule: in case you forgot to configure Gel rules in your text editor, the agent can access them like this, too.

Related MCP server: @iadev/mcp-server

Install

If at any point you get lost, refer to this repository to see an example config layout for your editor.

Cursor

  1. Add the following to .cursor/mcp.json:

{
  "mcpServers": {
    "gel": {
      "command": "uvx",
      "args": [
        "--refresh",
        "--python",
        "3.13",
        "--directory",
        ".",
        "--from",
        "git+https://github.com/geldata/gel-mcp.git",
        "gel-mcp"
      ]
    }
  }
}

  1. Open MCP settings, e.g. via Command Palette: View: Open MCP Settings and toggle Gel in there.

Claude Code

Add the following to .mcp.json:

{
  "mcpServers": {
    "gel": {
      "command": "uvx",
      "args": [
        "--refresh",
        "--python",
        "3.13",
        "--directory",
        ".",
        "--from",
        "git+https://github.com/geldata/gel-mcp.git",
        "gel-mcp"
      ]
    }
  }
}

VSCode with Copilot

Add the following to .vscode/mcp.json:

{
  "servers": {
    "gel": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--refresh",
        "--python",
        "3.13",
        "--directory",
        ".",
        "--from",
        "git+https://github.com/geldata/gel-mcp.git",
        "gel-mcp"
      ]
    }
  }
}

Windsurf

Follow Windsurf Cascade's documentation to open global mcp_config.json via the clicky interface. Add the following:

{
  "mcpServers": {
    "gel": {
      "command": "uvx",
      "args": [
        "--refresh",
        "--python",
        "3.13",
        "--directory",
        ".",
        "--from",
        "git+https://github.com/geldata/gel-mcp.git",
        "gel-mcp"
      ]
    }
  }
}

Zed

Add the following to .zed/settings.json:

{
  "context_servers": {
    "gel": {
      "source": "custom",
      "command": {
        "path": "uvx",
        "args": [
          "--refresh",
          "--python",
          "3.13",
          "--directory",
          ".",
          "--from",
          "git+https://github.com/geldata/gel-mcp.git",
          "gel-mcp"
        ],
        "env": {}
      }
    }
  }
}

Develop

Clone the repository and create the virtual environment:

uv sync

Open the server in the MCP Inspector:

mcp dev src/gel_mcp/server.py

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • TextQL MCP Server

    alexandme
    A
    license
    Not graded
    quality
    D
    maintenance
    Translates natural language to SQL/GraphQL queries and executes them, enabling AI agents to interact with databases through the Model Context Protocol.
    1
    Apache 2.0

  • SQL Server MCP Server

    Claritas-LLC
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to inspect schemas, analyze performance, check security, and troubleshoot SQL Server 2019+ databases through a safe, controlled interface.
    -

  • DB Gateway MCP Server

    sijunkim
    A
    license
    A
    quality
    C
    maintenance
    Gives AI agents direct access to databases across 8 engines with 145+ tools, enabling schema-aware query execution and management through natural language.
    17
    66 npm
    MIT