GraphJin - A Compiler to Connect AI to Your Databases

Point GraphJin at any database and AI assistants can query it instantly. Auto-discovers your schema, understands relationships, compiles to optimized SQL. No configuration required.

Works with PostgreSQL, MySQL, MongoDB, SQLite, Oracle, MSSQL, Snowflake - and models from Claude/GPT-4 to local 7B models.

Installation

npm (all platforms)

npm install -g graphjin

macOS (Homebrew)

brew install dosco/graphjin/graphjin

Windows (Scoop)

scoop bucket add graphjin https://github.com/dosco/graphjin-scoop
scoop install graphjin

Linux

Download .deb/.rpm from releases

Docker

docker pull dosco/graphjin

Try It Now

This is a quick way to try out GraphJin we'll use the --demo command which automatically starts a database using docker and loads it with demo data.

Download the source which contains the webshop demo

git clone https://github.com/dosco/graphjin
cd graphjin

Now launch the Graphjin service that you installed using the install options above

graphjin serve --demo --path examples/webshop

You'll see output like this:

GraphJin started
───────────────────────
  Web UI:      http://localhost:8080/
  GraphQL:     http://localhost:8080/api/v1/graphql
  REST API:    http://localhost:8080/api/v1/rest/
  Workflows:   http://localhost:8080/api/v1/workflows/<name>
  MCP:         http://localhost:8080/api/v1/mcp

Claude Desktop Configuration
────────────────────────────
Add to claude_desktop_config.json:

  {
    "mcpServers": {
      "Webshop Development": {
        "command": "/path/to/graphjin",
        "args": ["mcp", "--server", "http://localhost:8080"]
      }
    }
  }

Copy the JSON config shown and add it to your Claude Desktop config file (see below for file location). You can also click File > Settings > Developer to get to it in Claude Desktop. You will also need to Restart Claude Desktop

| OS | Possible config file locations | |----|---------------------| | macOS | ~/Library/Application Support/Claude/claude_desktop_config.json | | Windows | %APPDATA%\Claude\claude_desktop_config.json |

MCP install for OpenAI Codex + Claude Code

GraphJin includes a guided installer that configures MCP for OpenAI Codex, Claude Code, or both.

# Guided mode (asks target client and scope)
graphjin mcp install

OpenAI Codex

<img src="website/public/logos/openai-codex.svg" alt="OpenAI Codex logo" width="280">

graphjin mcp install --client codex --scope global --yes

Claude Code

<img src="website/public/logos/claude-code.svg" alt="Claude Code logo" width="280">

graphjin mcp install --client claude --scope global --yes

Troubleshooting

• graphjin mcp install defaults to --server http://localhost:8080/.
• Set a custom server URL with --server, for example:
  • graphjin mcp install --client codex --server http://my-host:8080/ --yes
• Claude installs use graphjin mcp --server <url> under the hood.
• If Codex CLI does not support codex mcp add --scope (older versions), GraphJin automatically falls back to updating:
  • global scope: ~/.codex/config.toml
  • local scope: .codex/config.toml

Getting started

To use GraphJin with your own databases you have to first create a new GraphJin app, then configure it using its config files and then launch GraphJin.

Step 1: Create New GraphJin App

graphjin new my-app

Step 2: Start the GraphJin Service

graphjin serve --path ./my-app

Step 3: Add to Claude Desktop config file

Copy paste the Claude Desktop Config provided by graphjin serve into the Claude Desktop MCP config file. How to do this has been defined clearly above in the Try it Now section.

Step 4: Restart Claude Desktop

Step 5: Ask Claude questions like:

• "What tables are in the database?"
• "Show me all products under $50"
• "List customers and their purchases"
• "What's the total revenue by product?"
• "Find products with 'wireless' in the name"
• "Add a new product called 'USB-C Cable' for $19.99"

How It Works

1. Connects to database - Reads your schema automatically
2. Discovers relationships - Foreign keys become navigable joins
3. Exposes MCP tools - Teach any LLM the query syntax
4. Runs JS workflows - Chain multiple GraphJin MCP tools in one reusable workflow
5. Compiles to SQL - Every request becomes a single optimized query

No resolvers. No ORM. No N+1 queries. Just point and query.

What AI Can Do

Simple queries with filters:

{ products(where: { price: { gt: 50 } }, limit: 10) { id name price } }

Nested relationships:

{
  orders(limit: 5) {
    id total
    customer { name email }
    items { quantity product { name category { name } } }
  }
}

Aggregations:

{ products { count_id sum_price avg_price } }

Mutations:

mutation {
  products(insert: { name: "New Product", price: 29.99 }) { id }
}

Spatial queries:

{
  stores(where: { location: { st_dwithin: { point: [-122.4, 37.7], distance: 1000 } } }) {
    name address
  }
}

Real-time Subscriptions

Get live updates when your data changes. GraphJin handles thousands of concurrent subscribers with a single database query - not one per subscriber.

subscription {
  orders(where: { user_id: { eq: $user_id } }) {
    id total status
    items { product { name } }
  }
}

Why it's efficient:

• Traditional approach: 1,000 subscribers = 1,000 database queries
• GraphJin: 1,000 subscribers = 1 optimized batch query
• Automatic change detection - updates only sent when data actually changes
• Built-in cursor pagination for feeds and infinite scroll

Works from Node.js, Go, or any WebSocket client.

MCP Tools

GraphJin exposes several tools that guide AI models to write valid queries. Key tools: list_tables and describe_table for schema discovery, get_query_syntax for learning the DSL, execute_graphql for running queries, and execute_saved_query for production-approved queries.

For JS orchestration, use:

• get_js_runtime_api to discover exactly which globals/functions are available inside workflow scripts
• execute_workflow to run ./workflows/<name>.js with input variables

Prompts like write_query and fix_query_error help models construct and debug queries.

JS Workflows (MCP + REST)

Workflows let an LLM run multi-step logic in JavaScript while still using GraphJin MCP tools for DB-aware operations.

Create a file in ./workflows, for example ./workflows/customer_insights.js:

function main(input) {
  const tables = gj.tools.listTables({});
  const top = gj.tools.executeSavedQuery({
    name: "top_customers",
    variables: { limit: input.limit || 5 }
  });
  return { tables, top };
}

Run via MCP

Call:

• get_js_runtime_api first (for exact runtime schema)
• execute_workflow with:
  • name: workflow file name (with or without .js)
  • variables: input payload passed to global input and main(input)

Run via REST

• POST /api/v1/workflows/<name> with JSON body
• GET /api/v1/workflows/<name>?variables={...json...}

Both map variables to the same workflow input object.

Chat Walkthroughs

Real conversations showing how an AI assistant uses GraphJin MCP tools to help you go from zero to running queries.

"I have databases running but don't know the details"

You: I have some databases running locally but I'm not sure about the ports or connection details. Can you help me set up GraphJin?

Claude: Let me scan your system to find running databases.

calls discover_databases

I found 2 databases on your system:

• PostgreSQL on localhost:5432 (TCP) — listening, auth: ok (user: postgres), databases: myapp, myapp_test
• MySQL on localhost:3306 (TCP) — listening, auth: auth_failed — default credentials failed, provide username and password

The PostgreSQL instance has databases myapp and myapp_test. Which one would you like to configure GraphJin with?

You: Let's go with the "myapp" database on Postgres.

Claude: I'll configure GraphJin to connect to your PostgreSQL database.

calls update_current_config with databases: {"main": {type: "postgres", host: "localhost", port: 5432, user: "postgres", dbname: "myapp"}}

Connected successfully! Let me see what tables you have.

calls list_tables

Your database has these tables: users, orders, products, reviews. Want me to write a query?

You: Show me users with their orders.

Claude: calls get_query_syntax then execute_graphql

{ users { id name email orders { id total status } } }

Here are the results — 24 users returned, each with their associated orders.

"I have a Docker Compose project with MySQL"

You: I'm running a Docker Compose stack with MySQL. Help me connect GraphJin to it.

Claude: Let me check what datab