> ## Documentation Index > Fetch the complete documentation index at: https://docs.graphify.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > The PyPI package is graphifyy, with two y's. The command is graphify. > /graphify . is typed in an assistant chat, not in a shell. > Use only commands, flags, and endpoints shown on these pages. Do not invent one. > Choose the surface before you open a page. Local is the graphifyy package on the machine: the skill, the CLI, and the ten-tool MCP. Its pages are the Guides and Reference tabs, /mcp/ (except /mcp/docs-search, which is for both), and the Local skill group in Integrations. Cloud (Graphify Cloud) is the hosted workspace and https://api.graphify.com/mcp (Streamable HTTP, OAuth, no API key). Its pages are the Graphify Cloud tab (/platform/) and the Cloud MCP group in Integrations. Concepts, troubleshooting, pricing, and /platform/local-to-cloud apply to both. Each page's source frontmatter records this as surface: local, cloud, or both. Buildkite is the CI integration. > In llms.txt, tell the surface from the page path. Cloud: /platform/ and /integrations/ cloud, vscode, jetbrains, chatgpt, openclaw, vercel, other-agents, buildkite. Local: /guides/, /reference/, /mcp/overview, /mcp/shared-http, /installation, /quickstart, and /integrations/ claude-code, cursor, codex, gemini-cli, copilot, other-assistants. Everything else applies to both. > The docs changelog summarizes selected graphifyy releases. The current package version is on PyPI (https://pypi.org/project/graphifyy/). The full history is https://graphify.com/changelog. > The official site is https://graphify.com. These docs are https://docs.graphify.com. > The local MCP server is the ten tools in the MCP tool reference and reads a graph on the machine. The hosted server is https://api.graphify.com/mcp (Streamable HTTP, OAuth, no API key). The VS Code, JetBrains, OpenClaw, Vercel, and Other Cloud agents pages, and the page ChatGPT, Codex, and Dots, use the hosted server, not the ten-tool list. Other local assistants is the local skill for clients without their own page. The page titled Graphify with Codex is the local skill. > Read https://docs.graphify.com/llms.txt, then open one page's .md link. Use https://docs.graphify.com/llms-full.txt only when one page is not enough. # Code with an agent on Graphify Cloud > Give Claude Code, Codex, Cursor, or another coding agent your indexed repositories through the hosted MCP server. This guide is for working with a coding agent, sometimes called vibe coding, on top of Graphify Cloud, the hosted version of Graphify. We run it for you, so there's nothing to deploy. Your agent asks the hosted MCP server at `https://api.graphify.com/mcp` about your repositories instead of re-reading the same files every session. ## Before you start * An account at [app.graphify.com](https://app.graphify.com). * At least one repository with the status **Indexed**. The [Cloud quickstart](https://docs.graphify.com/platform/quickstart.md) walks through connecting GitHub and switching on **Indexing** from a repository's **…** menu. ## 1. Connect your agent In the console, go to **Connectors → MCP**. The setup has three steps: **Choose agent**, **Connect**, and **Try a query**. Pick your agent, or open **Browse all agents** for the full list. If you'd rather let the agent do the setup, choose **Copy quick-start prompt** and paste it into your coding agent. Finish the sign-in when the agent asks. Agents such as Claude Code, Codex, and Cursor sign in with OAuth on first use, so there is no API key to paste. Per-agent steps are on [Cloud MCP](https://docs.graphify.com/integrations/cloud.md). ## 2. Check the connection On **Try a query**, the console gives you a test prompt to paste into your agent. It asks the agent to use Graphify's `list_repositories` tool and show the repositories you can access. Check that the list matches the workspace you picked. If you have more than one workspace, the prompt names the one to use. ## 3. Ask about your code Ask in plain language and name the symbol, file, or area you care about. For example: * `Who calls the function that validates a session token?` * `What would break if I changed this module's public interface?` * `Summarize how requests reach the billing service.` When an answer needs a closer look, open the same repository in the console: > **[Graphs](https://docs.graphify.com/platform/graphs.md)** > > See the nodes and most connected areas behind an answer. > **[Wiki](https://docs.graphify.com/platform/wiki.md)** > > Read the generated article for an area before you change it. > **[Memory](https://docs.graphify.com/platform/memory.md)** > > Inspect the shared context your agents and team have recorded. > **[Reviews](https://docs.graphify.com/platform/reviews.md)** > > Check a pull request your agent opened. ## Prefer to stay on your machine? Graphify Local, the open-source `graphifyy` package, builds the graph in your repository and gives your assistant a local skill. See [Choose your coding assistant](https://docs.graphify.com/integrations/overview.md). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.