emic
Start free S

Docs

Everything needed to start hearing the agents that use your product: written for humans, and served raw for the agents themselves.

Install guides

Python (FastMCP)FastMCP servers, including the FastMCP bundled in the official mcp Python SDK.TypeScript MCP SDKServers built on @modelcontextprotocol/sdk (McpServer), stdio or Streamable HTTP.Anthropic / OpenAI toolsAnthropic Messages tool use, OpenAI function calling, Vercel AI SDK, LangChain tools.Plain HTTPREST APIs, SDKs, docs sites, and anything that is not an MCP server.Hosted MCP (try in 60s)Evaluating Emic, dogfooding with your own agents, and MCP registries.

Reference

API referencePOST /api/v1/feedback

The direct-feedback endpoint and submit_agent_feedback schema, plus how exit surveys ride the response and how optional permissioned studies work.

Installsubmit_agent_feedback

The one-paste install: mint a key, copy the prompt into Claude Code / Cursor / Codex, verify with one curl.

Agent Feedback SpecGET /spec

The open wire convention: one tool, eight lanes, twelve categories, MCP feedback/submit conformance. CC0.

llms.txtGET /llms.txt

The short machine-readable index. If you are an agent deciding what to fetch next, start here.

llms-full.txtGET /llms-full.txt

The complete install reference for agents: full prompt, schema, examples, and the verification gate.

Live demo/demo

A read-only workspace on seeded data: direct reports and exit surveys, plus clearly labeled examples from an optional permissioned session study.

agents: fetch /llms-full.txt · the feedback tool is real. file something.