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

Works with PostgreSQL, MySQL, MongoDB, SQLite, Oracle, MSSQL, Snowflake, S3/GCS/files, CodeSQL source indexes - and models from Claude/GPT-4 to local 7B models.

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

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

Before graphjin cli or graphjin mcp can talk to a server, point them at one. There are no --server or --token flags — both come from a single saved config file (~/.config/graphjin/client.json, mode 0600):

graphjin cli setup http://localhost:8080            # local dev, no auth needed
graphjin cli setup https://graphjin.example.com     # signs in via the server's OIDC IdP

What setup does, depending on the server:

• No built-in login (the server has auth_login.enabled: false): saves only the URL. CLI calls send no Authorization header.
• Built-in login enabled: kicks off an RFC 8628 device-code flow. The CLI prints a verification URL + short code, opens your browser, you sign in with the configured identity provider (Google, Okta, Keycloak, Auth0-as-IdP, Azure AD — anything OIDC), and the server mints a 30-day JWT. Both URL and JWT are saved to client.json.

After setup every graphjin cli ... command just works:

graphjin cli health
graphjin cli query list
graphjin cli schema tables
graphjin cli setup show       # print the saved config (token redacted)
graphjin cli setup logout     # delete client.json
graphjin cli setup            # re-run sign-in against the same server (refresh token)

To enable built-in login, set this on the server:

auth:
  jwt:
    secret: "long-random-shared-secret"   # used to sign and verify local JWTs

auth_login:
  enabled: true
  audience_graphjin: true                 # shorthand for audience: "graphjin-cli"
  oidc:
    issuer_url: "https://accounts.google.com"
    client_id: "..."
    client_secret: "..."                  # or $GJ_AUTH_LOGIN_OIDC_CLIENT_SECRET
    allowed_domains: ["example.com"]      # optional allow-list

Successful authentication is recorded in structured logs with the verified email and name claims (when present), giving you a clean audit trail of who called every endpoint.

GraphJin includes a guided installer that configures MCP for OpenAI Codex, Claude Code, or both. Run graphjin mcp setup <server-url> first — mcp install reads the server URL from client.json, and the MCP-client config it writes is credential-free, so rotating tokens (re-running mcp setup) needs no edits to Claude / Codex.

graphjin mcp setup https://graphjin.example.com
graphjin mcp install                                # guided: target client + scope

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

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

• mcp install requires a saved server URL — run graphjin mcp setup <server-url> first if you see "no GraphJin server configured".
• The generated MCP-client config is args: ["mcp"]. graphjin mcp reads server + token from client.json on its own, in proxy mode when a server is saved or local mode when it's not.
• 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

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"

1. Connects to database - Reads your schema automatically
2. Discovers relationships - Foreign keys become navigable joins
3. Exposes metadata - gj_* tables make discovered databases, tables, columns, relationships, functions, and indexes queryable when the GraphJin source is enabled
4. Indexes source code - CodeSQL turns tree-sitter syntax trees and database references into a managed SQLite database
5. Exposes MCP tools - Teach any LLM the query syntax
6. Runs JS workflows - Chain multiple GraphJin MCP tools in one reusable workflow
7. Compiles to SQL - Every request becomes a single optimized query

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

CodeSQL is a managed source kind for source trees. Configure a source folder and GraphJin creates a SQLite cache under config/codesql/, indexes it with tree-sitter, and updates it on restart. In development it also watches for changes while the service runs; in production live watching is disabled.

sources:
  - name: app
    kind: sql
    type: postgres
    connection_string: postgres://app:secret@db/app
    default: true

  - name: code
    kind: codesql
    path: /srv/app
    infer_db_refs: true

  - name: graphjin
    kind: graphjin
    metadata: true

tables:
  - name: users
    source: app

  - name: gj_code
    source: code
    read_only: true

GraphJin exposes CodeSQL through one ordinary GraphQL root, gj_code. Use kind to select files, symbols, references, imports, database references, docs, parse errors, change sets, and locks:

query {
  gj_code(where: { kind: { eq: "symbol" }, name: { iregex: "handler|resolver" } }, limit: 20) {
    name
    symbol_kind
    language
    start_row
    path
    hash
  }
}

With a kind: graphjin source, GraphJin creates a read-only system graph named graphjin by default. Schema, catalog, entrypoint, capability, workflow, and system metadata are catalog items in gj_catalog; table and column metadata are selected by kind. When one CodeSQL source is active, GraphJin links catalog items to code references automatically:

query {
  gj_catalog(where: { kind: { eq: "column" }, table_name: { eq: "users" }, column_name: { eq: "email" } }) {
    database_name
    table_name
    column_name
    gj_code {
      kind
      ref_kind
      path
      symbol_id
    }
  }
}

This is where the model gets genuinely powerful: the same agent can inspect production data systems and the code that operates them. It can ask, "which handlers touch customer invoices?", "what tables do these workflows depend on?", or "show me the imports and call sites near this data path" without switching tools or inventing a new backend.

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 } }

Analytics directives:

{
  orders {
    account_id
    month
    total
    running_total: total @running(aggregate: sum, by: "account_id", orderBy: { month: asc })
    moving_avg_total: total @moving(aggregate: avg, rows: 6, by: "account_id", orderBy: { month: asc })
    previous_total: total @previous(by: "account_id", orderBy: { month: asc })
    rank_by_total: total @rank(by: "account_id", order: desc)
  }
}

Use analytics directives when each original row should remain visible while adding report metrics such as running totals, moving averages, previous/next values, first/last values, and rank within a group. Ordinary one-row-per-group summaries still use distinct plus aggregate fields. Supported SQL databases validate analytics support at compile time; MongoDB and known-old database versions return clear errors.

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
  }
}

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

Subscribe over WebSockets (graphql-ws / graphql-transport-ws subprotocols) or Server-Sent Events — set Accept: text/event-stream on a POST /api/v1/graphql request and GraphJin streams event: next frames for each result, terminated by event: complete. Works from Node.js, Go, or any browser EventSource / WebSocket client.

Object stores show up as ordinary tables in your GraphQL schema. Declare them in config and they get the same query surface as a database table — no per-storage GraphQL plumbing on your side.

sources:
  - name: avatars
    kind: filesystem
    backend: s3
    bucket: my-bucket
    prefix: avatars/
    region: us-east-1
    presign_ttl: 15m

  - name: invoices
    kind: filesystem
    backend: gcs
    bucket: invoices
    prefix: 2026/

  - name: uploads_local
    kind: filesystem
    backend: local
    root: /var/lib/graphjin/uploads

tables:
  - name: avatars
    source: avatars
    read_only: true

  - name: invoices
    source: invoices
    read_only: true

  - name: uploads_local
    source: uploads_local

Every filesystem table exposes the same columns regardless of backend:

{ avatars(
    where: { key: { like: "users/%" } }
    order_by: { key: asc }
    limit: 50
  ) {
    key size content_type modified_at url
  }
}

{ avatars(id: "users/42.png") {
    key size url data    # data is base64 because the field was selected
  }
}

The legacy prefix, key, and inline_data arguments remain accepted, but new callers should use the normal GraphJin read surface: id, where, order_by, limit, offset, first, last, after, and before. For cursor pagination, request the standard root cursor field, e.g. avatars_cursor, and pass it back through after: $cursor.

url is a presigned GET URL by default (15 min, configurable per table). Auth follows the standard credential chain: AWS env / ~/.aws / IRSA / EC2 IMDS for S3, Application Default Credentials for GCS — never embedded in GraphJin config.

Slim builds drop SDK weight: -tags no_s3 or -tags no_gcs excludes either backend. Custom backends register through core.OptionSetFilesystemBackend(name, factory) — same SDK GraphJin uses for the built-ins.

The GraphQL endpoint accepts multipart bodies per the graphql-multipart-request-spec. Files can be inlined as base64 (default) or streamed straight to a filesystem table:

uploads:
  enabled: true
  storage: avatars               # name of a filesystems[] entry; omit to inline as base64
  storage_key_prefix: "{date}/"  # {date} → YYYY/MM/DD
  max_size: 25_000_000
  allowed_mime: ["image/*", "application/pdf"]

When storage is set, the file body is written to the backend and the GraphQL variable becomes a stable reference — mutations persist this directly into a JSONB column:

{ "key": "2026/05/08/abc123.png",
  "url":  "https://s3.../...?presigned",
  "size": 12345,
  "content_type": "image/png" }

When storage is empty the variable carries the bytes inline as {filename, content_type, size, data} (base64) — useful for small uploads going straight into bytea.

GraphJin can register as a federation subgraph so it composes with other services behind Apollo Router / Cosmo / Hive Gateway:

federation:
  enabled: true
  version: "v2.5"
  keys:
    users: ["id"]                  # auto-derived from PKs by default
    orders: ["id", "tenant_id"]    # composite keys via override
  shareable: ["Tag.name"]          # field-level @shareable
  inaccessible: ["Users.encrypted_password"]

_service { sdl } returns a federation-flavoured SDL with @link, @key, @shareable, @inaccessible, @tag, _Service, and _Entity. Composition succeeds out of the box; _entities resolution is on the roadmap (the engine returns a clear error today, so gateways see the gap rather than silent failures).

graphjin serve exposes everything under a single host/port. All routes go through the configured auth handler unless noted.

Mode flags that change which routes are live:

• mcp.disable: true — removes /api/v1/mcp and /api/v1/mcp/message.
• mcp.only: true — keeps only /health and /api/v1/mcp*. Legacy /api/v1/workflows/* and /api/v1/discovery* remain only when mcp.legacy_discovery: true.
• Source mode (sources: present) disables legacy /api/v1/workflows/* and /api/v1/discovery* unless mcp.legacy_discovery: true.
• webui: false — drops / and the /api/v1/admin/* routes.

GraphJin exposes a catalog-first agent surface that guides AI models to discover before acting. Start with query_catalog, then inspect evidence with get_catalog_card before writing queries, choosing relationships, or using GraphJin-specific syntax. For actions, agents can use GraphJin control-plane GraphQL roots such as gj_workflow_execution(insert), gj_workflow(insert/update/delete), and gj_config(id: "current", update: ...). Schema reloads, schema changes, where-clause validation, and query repair remain MCP action tools. The legacy discovery tools are migration shims and are disabled unless mcp.legacy_discovery: true.

For teams building MCP agents, internal copilots, workflow agents, or enterprise automation, see AGENTIC.md. It explains the catalog-first agent loop in detail: discover, inspect, validate, act, observe, and refine.

Key discovery tools:

• get_catalog_entrypoints to choose a discovery path when the task is broad
• query_catalog to search schema, relationship, workflow, language, config, policy, capability, and query-pattern items. Use search for ranked text discovery and where for exact filters.
• get_catalog_card to inspect evidence, examples, details, safety notes, and graph edges
• validate_where_clause to validate filters before execution

For JS orchestration, use:

• query_catalog with where: { kind: { eq: "workflow" } } to discover reusable workflows
• get_js_runtime_api to discover exactly which globals/functions are available inside workflow scripts
• gj_workflow_execution(insert: { workflow_name: "...", variables: {...} }) to run ./workflows/<name>.js through GraphQL. This is mutation-only and returns an ephemeral result row; it does not store run history. Mark the workflows source or gj_workflow_execution table read_only to block it. The execute_workflow MCP compatibility tool is available only when mcp.legacy_discovery: true and mcp.allow_workflow_execution: true.

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

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.queryCatalog({
    where: { kind: { eq: "table" } }
  }).cards;
  const top = gj.tools.executeSavedQuery({
    name: "top_customers",
    variables: { limit: input.limit || 5 }
  });
  return { tables, top };
}

mutation {
  gj_workflow_execution(insert: {
    workflow_name: "customer_insights"
    variables: { limit: 5 }
  }) {
    status
    result_json
    error
  }
}

Legacy MCP clients can call execute_workflow only when mcp.legacy_discovery: true.

This legacy HTTP endpoint is available in legacy database mode, or in source mode only when mcp.legacy_discovery: true.

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

Both map variables to the same workflow input object.

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

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 discover the catalog surface.

calls query_catalog with where: {kind: {eq: "table"}}

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

You: Show me users with their orders.

Claude: calls query_catalog with search: "join users orders", where: {kind: {eq: "relationship"}}, then get_catalog_card, then execute_graphql

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

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

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

Claude: Let me check what database containers you have running.

calls discover_databases

Found a MySQL Docker container:

• MySQL via Docker — container myapp-db-1, image mysql:8.0, port mapped to localhost:13306

I'll configure GraphJin with the discovered connection details.

calls update_current_config with databases: {"main": {type: "mysql", host: "localhost", port: 13306, user: "root", dbname: ""}}

What's the database name and password for your MySQL instance?

You: Database is "shop_db", password is "secret123".

Claude: calls update_current_config with the full credentials

Connected! Let me explore the catalog.

calls query_catalog with where: {kind: {eq: "table"}}

Tables found: customers, products, orders, order_items, categories. Let me check how they relate.

calls query_catalog with search: "join orders customers order_items products", where: {kind: {eq: "relationship"}}, then get_catalog_card for the relevant relationship items

orders connects to customers (via customer_id) and order_items (via order_id), and order_items links to products. Here's a nested query:

{ orders { id total customer { name email } order_items { quantity product { name price } } } }

You: I have a SQLite database file in my project. Can GraphJin work with it?

Claude: Absolutely! Let me scan your project directory for SQLite files.

calls discover_databases with scan_dir: "."

Found 1 SQLite database:

• data/app.sqlite3 — file found

I'll configure GraphJin to use it.

calls update_current_config with databases: {"main": {type: "sqlite", path: "data/app.sqlite3"}}

Connected! Let me see your tables.

calls query_catalog with where: {kind: {eq: "table"}}

Tables: tasks, projects, tags, task_tags. Want to query something?

You: Show me all tasks with their project name, sorted by due date.

Claude: calls query_catalog with search: "join tasks projects", where: {kind: {eq: "relationship"}}, then get_catalog_card, then execute_graphql

{ tasks(order_by: {due_date: asc}) { id title due_date completed project { name } } }

Here are your 12 tasks sorted by due date, each showing the parent project name.

Also works with AWS Aurora/RDS, Google Cloud SQL, and YugabyteDB. Snowflake supports key pair (JWT) authentication.

Query allow-lists - In production, only saved queries can run. AI models call execute_saved_query with pre-approved queries. No arbitrary SQL injection possible.

Role-based access - Different roles see different data:

roles:
  user:
    tables:
      - name: orders
        query:
          filters: ["{ user_id: { eq: $user_id } }"]

JWT authentication - Supports Auth0, Firebase, JWKS endpoints.

Response caching - Redis with in-memory fallback. Automatic cache invalidation on mutations. Stale-while-revalidate support: serve cached responses immediately while a background worker refreshes the entry — concurrent refreshes for the same key are deduplicated via singleflight, and the worker pool is bounded so a thundering herd can't spawn unbounded goroutines.

caching:
  ttl: 3600          # hard expiry in seconds
  fresh_ttl: 300     # soft expiry — entries past this trigger SWR refresh

GraphJin works as a traditional API too - use it from Go or as a standalone service.

go get github.com/dosco/graphjin/core/v3

db, _ := sql.Open("pgx", "postgres://localhost/myapp")
gj, _ := core.NewGraphJin(nil, db)
res, _ := gj.GraphQL(ctx, `{ users { id email } }`, nil, nil)

brew install dosco/graphjin/graphjin  # Mac
graphjin new myapp && cd myapp
graphjin serve

Built-in web UI at http://localhost:8080 for query development.

• Configuration Reference
• Feature Reference
• Go Examples

Twitter @dosco | Discord

Apache Public License 2.0