Skip to main content

Other AI Agent Integrations

Most AI tools connect to Skywalk through one of two patterns:

  • MCP server — enables your personal AI assistant to access and analyze your AppFolio® data.
  • llms.txt — enable your AI Coding agent to build apps, dashboards, and software with your AppFolio® data.

Connect your AI Agent to AppFolio®​

Add a Custom MCP Client (sometimes called a "Connector") in your AI Agent's settings. When the agent asks you to authorize, sign in as a project admin, or enter an invitation code a project admin created on the project's AI Agents page. The tools then appear natively to new agent conversations.

When your agent asks for a connector name, use Skywalk for AppFolio. A name that mentions AppFolio® helps your agent choose these tools when you ask about your AppFolio® data.

Note: AI agents must be turned on for your Skywalk API project. Talk to support to learn more.

Connect to Claude​

Full walkthrough on Claude Integration.

  1. Settings →
  2. Connectors →
  3. Add custom connector.
  4. Name: Skywalk for AppFolio
  5. Server URL: https://mcp.skywalkapi.com

Connect to ChatGPT​

  1. Settings →
  2. Security & Login →
  3. Enable "Developer Mode" - then visit:
  4. Settings →
  5. Plugins →
  6. Hit the "+" Button / New Plugin →
  7. Name: Skywalk for AppFolio
  8. Server URL: https://mcp.skywalkapi.com

Connect to Gemini Enterprise app​

  1. See the Gemini Enterprise docs
  2. Server URL: https://mcp.skywalkapi.com

Connect to Grok​

  1. Settings →
  2. Connectors →
  3. Add a Custom MCP server →
  4. Server URL: https://mcp.skywalkapi.com

Other Agents​

Find the option to add a custom MCP Server to your agent, and point it to the Skywalk MCP Server URL: https://mcp.skywalkapi.com

  • Cursor — Settings → MCP → Add MCP server (HTTP transport).
  • Windsurf — Cascade settings → MCP servers.
  • Cline (VS Code extension) — "Cline: Add MCP server" → Remote.
  • Zed — context_servers block in ~/.config/zed/settings.json.

For clients that only support stdio MCP servers, the mcp-remote npm package wraps a remote HTTP MCP server in a stdio process so the client can launch it.

Code-writing agents (use llms.txt)​

These work just like Build with Claude Code — point the agent at https://api.skywalkapi.com/llms.txt, export your key as SKYWALK_API_KEY, and let it write the code. The CLAUDE.md-style persistence trick and the security caveat about env vars on that page apply here too.

  • OpenAI Codex CLI — paste the llms.txt URL in your first prompt; Codex fetches it and runs curl to call endpoints.
  • GitHub Copilot Chat (agent mode) — reference llms.txt in your prompt; agent mode can fetch and execute commands.
  • Aider — drop the API contract into CONVENTIONS.md at the repo root so every Aider session inherits it.
  • Goose — define a recipe that fetches llms.txt and reads SKYWALK_API_KEY from the environment.

Building your own agent​

Wiring Skywalk into a custom agent built on the Claude API, OpenAI tool use, LangChain, or LlamaIndex? See Manual Context — it has a pasteable API context block, ready-to-use tool definitions in both Claude and OpenAI function-calling formats, and reference async-polling helpers in Python and TypeScript.

Don't see your tool?​

If your AI tool can do either of these, you're covered:

The Manual Context page also has a short pasteable summary that works as a fallback in any tool with a system prompt or instructions field.

MCP Server
Tool catalog and behavior of the hosted MCP server.
Manual Context
Pasteable context, tool definitions, polling helpers for custom builds.
AI Agents Overview
Decide which integration path fits your use case.