About Agent Surface
Agent Surface provides a guide for making websites, apps, APIs, and CLIs work with AI agents. Its README contains only project setup and test commands, so details of the guide are not described.
Key features
- 01Website, app, API, and CLI guidance
- 02Project documentation
Use cases
- 01Finding guidance on agent-compatible interfaces
- 02Checking project documentation
MCP support
The project is described as a search-and-read MCP server for the Agent Surface guide. The README does not specify its tools or exposed resources.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://agentsurface.dev/mcpclaude mcp add --transport http dev-agentsurface-docs https://agentsurface.dev/mcp{"mcpServers":{"dev-agentsurface-docs":{"type":"http","url":"https://agentsurface.dev/mcp"}}}Open in Cursor{"servers":{"dev-agentsurface-docs":{"type":"http","url":"https://agentsurface.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-agentsurface-docs":{"type":"http","url":"https://agentsurface.dev/mcp"}}}{"mcpServers":{"dev-agentsurface-docs":{"serverUrl":"https://agentsurface.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3This tool takes no parameters.
Details
From the project READMEAgent Surface
Documentation, specifications, decisions and outstanding work live in Linear (howells, AGE).
pnpm install
pnpm dev
pnpm build
pnpm start
pnpm test # docs integrity check
pnpm typecheck
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.