dosco/graphjin

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

View on GitHub ↗Jump to charts ↓

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 1 hour ago
Added to GitGenius on September 21st, 2026
Created on March 24th, 2019
Open Issues & Pull Requests: 21 (+0)
GitHub issues: Enabled
Number of forks: 197
Total Stargazers: 3,171 (+0)
Total Subscribers: 42 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 5.9 days
Mean response time: 101.0 days
90th percentile: 149.0 days
Tracked items: 36

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 7
New in 7 days: 2
Closed in 7 days: 3
Avg open age: 376 days
Stale 30+ days: 5
Stale 90+ days: 5

Recent activity

Opened in 7 days: 2
Closed in 7 days: 3
Comments in 7 days: 0
Events in 7 days: 1

Top labels

  • bug (13)
  • enhancement (7)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

GraphJin is a GraphQL server that exposes databases, files, APIs, and code through a unified graph interface accessible to AI agents via the Model Context Protocol.

The tool solves the problem of giving AI agents safe, governed access to backend systems without requiring custom integration code for each data source. It works by translating GraphQL queries into database queries and API calls, applying role-based access control and permission rules at query time. This approach lets developers define what data and operations agents can access through a single declarative configuration, rather than building separate API layers or agent tools for each backend system.

Teams should adopt GraphJin when they need to expose multiple data sources to AI agents while maintaining strict control over what those agents can read and modify. It suits projects where you want agents to query databases, fetch files, or call APIs through a consistent interface without writing custom connectors. The tool supports a wide range of databases including PostgreSQL, MySQL, MariaDB, SQLite, MongoDB, CockroachDB, Oracle, and others, making it applicable to diverse backend architectures.

The project shows active development with regular commits addressing bug fixes and feature additions. Work spans multiple areas including core GraphQL functionality, database driver support, and agent integration features. The codebase receives ongoing refinement with attention to both new capabilities and stability improvements across the supported database systems.