Integrations: coding agents and MCP clients

Every agent below can use Graphify. Start with Graphify: it answers from repositories you have indexed, through https://api.graphify.com/mcp, with no local build. Graphify CLI, the alternative for offline or self-hosted setups, installs the open-source graphifyy skill and builds the graph on your machine. See Graphify vs Graphify CLI to choose.

Agents at a glance

Agent	One-click install	Graphify (hosted MCP)	Graphify CLI skill	Always-on context (Graphify CLI)
Claude Code	—	Yes	Yes	`CLAUDE.md` and a PreToolUse hook
Cursor	From the console	Yes	Yes	`.cursor/rules/graphify.mdc` (always applied)
Codex	OpenAI plugin directory	Yes	Yes	`AGENTS.md` and a PreToolUse hook in `.codex/hooks.json`
VS Code and Copilot	VS Code Marketplace	Yes (extension)	Yes	Copilot instructions in VS Code
Gemini CLI	—	Yes	Yes	`GEMINI.md` and a BeforeTool hook
JetBrains	JetBrains Marketplace	Yes (plugin)	—	—
ChatGPT	OpenAI plugin directory	Yes (app)	—	—
OpenClaw	ClawHub	Yes (plugin)	Yes (`--platform claw`)	`AGENTS.md`
Hermes	—	Yes	Yes (`--platform hermes`)	`AGENTS.md`
Other MCP clients	—	Yes	Local MCP server	—

“Always-on context” is what graphify install writes so the agent checks the graph before reading source, without being asked. Hooks never grant the agent new permissions.

Graphify

Sign in at app.graphify.com and wait until the repository status is Indexed. Then pick your agent. Each page signs you in with OAuth; no API key is needed.

Claude Code

One claude mcp add command, then sign in from /mcp.

Cursor

One-click install or mcp.json, with OAuth sign-in.

Codex

codex mcp add and login, or the Graphify plugin.

VS Code

Marketplace extension for the hosted server.

JetBrains

Marketplace plugin for JetBrains AI Assistant.

ChatGPT, Codex, and Dots

One OpenAI plugin. Install it once.

OpenClaw

ClawHub package for the hosted server.

Vercel

A project token, or a per-user Connect token.

Other Cloud agents

Antigravity, Windsurf, Cline, Zed, and any other MCP client.

Graphify CLI

The package is graphifyy. The command is graphify. graphify install writes the skill into the assistant you name.

The common workflow

uv tool install graphifyy
graphify install --platform cursor

Replace cursor with the installer platform for your assistant. Restart or refresh the assistant if it does not discover the new skill immediately, then ask it to map the current repository with Graphify. Skill invocation differs by client. Slash commands are common; Codex also exposes skills through the $ picker. If a client does not show slash commands, explicitly ask it to use the installed Graphify skill.

Project or personal installation

The default registration is personal. Add --project for repository-local registration where supported. This makes the instructions reviewable in version control and lets a team share the setup. The installer adds platform-specific files and may install hooks or instructions that suggest querying the graph before reading source. It does not grant your assistant new permissions.

Local MCP server

The local MCP server exposes a graph that already exists on your machine as MCP tools. Use it with the skill or on its own.

Beyond coding agents

GitHub

Connect repositories and get pull request reviews.

GitLab

Connect GitLab.com projects.

Buildkite and CI

Run only the tests a change can affect.

Google Drive

Add Drive folders to the graph.

Coding agents

Assistants

Source control

CI and deploy

Knowledge sources

For agents

Integrations: coding agents and MCP clients

Agents at a glance