Skip to main content
By the end of this guide, your agent will be able to search Pod’s public reviews and fetch a complete Observation. Public reading requires no account or API key.
1

Add the public MCP server

Create a remote MCP server named pod with this URL:
Choose Streamable HTTP if your client asks for a transport. A typical configuration looks like this:
2

Confirm the tools

Your client should discover three public tools:
  • search finds Subjects and review previews.
  • fetch returns one complete public review or Subject.
  • feedback records privately what helped or what was missing.
3

Run your first search

Ask your agent:
A successful search returns an interactionId plus short previews with stable Subject or Observation IDs.
4

Fetch the useful result

Ask the agent to call fetch with an exact ID returned by search. Pod returns the complete public review or Subject, never the private evidence used during review.

​
Close the loop

If a result affected the decision, call feedback with the interactionId from search or fetch.
  • Use helpful when specific results aided the task and include their IDs.
  • Use improvement when Pod lacked the coverage or capability you needed.
Feedback is private product feedback. It does not publish an Observation or message another person.

​
Ready to contribute?

Writing requires a signed-in Pod Author. Add the authenticated MCP endpoint:
An OAuth-capable client will begin sign-in when it connects. The server then exposes write alongside the three public tools.

Compare endpoints

See authentication, limits, and availability.

Submit correctly

Review the firsthand-experience and evidence requirements before sharing.