Gel

This MCP server provides tools and resources that help coding agents use the Gel database.
- execute_query: run a query against the Gel instance configured in the current project. Supports arguments and globals.
- try_query: run a query in a transaction that gets rolled back in the end, preventing actual data modification.
- list_examplesandfetch_example: access code examples for advanced workflows such as configuring the AI extension.
- list_rulesandfetch_rule: in case you forgot to configure Gel rules in your text editor, the agent can access them like this, too.

If at any point you get lost, refer tothis repositoryto see an example config layout for your editor.

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

- Open MCP settings, e.g. via Command Palette:View: Open MCP Settingsand toggle Gel in there.

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

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

Follow Windsurf Cascade'sdocumentationto open globalmcp_config.jsonvia 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" ] } } }

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": {} } } } }

Clone the repository and create the virtual environment:

Efficient, SQL-backed C++ project indexer designed for large codebases with low memory footprint.

MCP servers that give AI clients safe, structured access to SQL databases. One installable package per database engine. Every package exposes the same minimal two-tool surface, execute_sql and search_objects, with guardrails on by default: read-only mode, row caps, and statement timeouts.

MCP server that gives AI agents deep understanding of contemporary or legacy relational databases.

Browse, create, and manage schema projects on the Schematica schema library. 8 MCP tools for AI-powered schema design and data modeling.

Interact with Supabase databases, query tables, and generate TypeScript types.

Hosted MCP server and coordination layer for AI coding agents — live API contracts, database schema, frontend/backend mismatch detection, and shared handoff tickets for Claude Code, Cursor, Codex, and Lovable.

An MCP server that indexes local code into a graph database to provide context to AI assistants.

connect a read-only replica, analytics database, or staging database. Keep credentials on your machine while the tool discovers schema, generates safe SQL, previews it for approval, runs the query, and summarizes the result.

An example of a remote, authentication-free MCP server deployable on Cloudflare Workers.