MCP
Connect an MCP-compatible client (Cursor, Claude, Codex, and more) so the
agent can search and fetch tool context in-session.
REST API
Call the registry from your own agent runtime, backend, or automation with
standard HTTP.
CLI
Search the registry and fetch context from a terminal or script.
Querying UseAgents is currently free during our public beta. Requests are subject to rate limits.
Same workflow, any surface
Whatever you connect with, keep this order:- Search the registry with a task and constraints.
- Shortlist candidates from the returned metadata.
- Fetch context for the chosen tool (install, examples, docs link).
- Search docs for deeper how-to answers from that tool’s official documentation - do not invent setup from training data when context is missing.
- Test a small snippet in a UseAgents sandbox when you want to confirm the packages install and the code runs.
MCP
Best when your agent already speaks MCP. Add the UseAgents server once, then ask the agent to search when it needs a tool.
See Connecting over MCP and client guides.
REST API
Best when you own the agent loop (custom runtime, backend job, evaluation harness).
See the API Reference,
GET /tools/search, and GET /tools/docs/:slug.
CLI
Install the CLI with npm or the standalone installer, then runuseagents --help. Upgrade a standalone binary with useagents upgrade.
See UseAgents CLI for installation, upgrade, filters, output formats, and scripting examples.
Skills
Install the UseAgents Agent Skill so coding agents automatically follow the search → context → docs → implement workflow when they need a developer tool:Next steps
- Agents introduction - Why query a registry at runtime
- Skills - Install the Agent Skill for discovery guidance
- Connecting over MCP - MCP setup and verification
- API Reference - HTTP access to the registry