// docs / mcp

Your library, inside your agents.

The MCP server lets an agent read, search, and fill your prompts directly — read-only by design, so it can never burn your tokens or change your library.

Status

The MCP server is rolling out — the package publishes as promptlike-mcp. Once it's live on npm the one-line install below will work; until then this page documents what it does and how it's wired.

Connect it to Claude Code

$ terminal

# sign in with the CLI first (MCP shares the same session)
npm i -g promptlike && ple login

# add it to Claude Code
claude mcp add promptlike -- npx -y promptlike-mcp

Zero extra auth: the server reads the same ~/.config/promptlike/config.json session the CLI wrote. Any MCP client works — point it at npx -y promptlike-mcp over stdio.

The tools (v1, read-only)

mcp tools

list_prompts(tag?)         → browse your library, incl. {{var}} names
search_prompts(query)      → search titles & descriptions
get_prompt(name, version?) → full content, optionally a pinned version
fill_variables(name, vars) → fill {{var}}s, return ready-to-use text

Read-only is intentional: an agent can browse and fill your prompts, but it can never spend your AI tokens or mutate the library. Ambiguous names return a candidate list so the agent picks; rate limits surface as Retry in Ns so it can back off.

Why this matters

MCP has a first-class prompts concept but no versioning, diff, or history — that stays in PLE. So agents pull the current version over MCP while you keep the full engineering history on the web. You version it; your agents read it. More on the approach in variables and versioning.