Marketplace for trusted AI agent skills

Skill Detail

Connect agents to governed data and code graphs with GraphJin

Expose databases, files, code indexes, workflows, and policy-aware GraphQL through GraphJin's MCP and agent endpoints for governed discovery and action.

Integrations & ConnectorsMCP
Integrations & Connectors MCP Security Reviewed
⭐ 3.1k GitHub stars ⬇ 866/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill connect-agents-to-governed-data-and-code-graphs-with-graphjin Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
GraphJin CLI or server; approved database/file/code sources; Codex, Claude Code, or another MCP-capable client; optional Docker, Homebrew, npm, or Scoop install path
Install & setup
Install with npm install -g graphjin, brew install dosco/graphjin/graphjin, or scoop install graphjin; run graphjin serve or a documented demo, then add the MCP endpoint with graphjin mcp add codex, graphjin mcp add claude, or the equivalent MCP client configuration.
Author
GraphJin
Publisher
Organization
Last updated
Jul 18, 2026
Quick brief

Use GraphJin when an agent or operator needs a governed graph over company systems before it queries or changes anything. The workflow is concrete: run GraphJin against approved databases, files, source indexes, and workflows; connect Codex, Claude Code, or another MCP client to `/api/v1/mcp`; have the agent inspect catalog entries, security policy, schemas, relationships, saved queries, and runtime status before executing bounded GraphQL, workflow, or agent calls. Invoke this instead of using GraphJin as a generic GraphQL server when the job is to give an AI agent one auditable discovery and action surface over multiple systems. Keep the boundary on policy-aware MCP/agent access, catalog discovery, saved artifacts, and reviewable query or workflow execution; do not treat this as a generic database, API gateway, or SDK listing.

How it works

What this skill actually does

Inputs and prerequisites: GraphJin CLI or server; approved database/file/code sources; Codex, Claude Code, or another MCP-capable client; optional Docker, Homebrew, npm, or Scoop install path.

Setup notes: Install with npm install -g graphjin , brew install dosco/graphjin/graphjin , or scoop install graphjin ; run graphjin serve or a documented demo, then add the MCP endpoint with graphjin mcp add codex , graphjin mcp add claude , or the equivalent MCP client configuration.

Source and verification boundary: use https://graphjin.com as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.