Tavily

Agents can search the public web and extract the content of pages through Tavily, using your own Tavily account. It suits bounded research tasks where you want the agent to cite where each fact came from.

Note: Tavily appears in the catalog on every instance; no experimental setting is needed.

Before you connect

  • A Tavily account with an API key and some usage allowance. You do not paste the key — sign-in picks it for you — but searches draw on that key's credits.
  • A public HTTPS address for your ThinkingMach instance. Tavily refuses to send you back to a local http:// address after sign-in, so a ThinkingMach running only on your own machine cannot complete this setup.

Connect Tavily

  1. Open Connectors and select Tavily.
  2. Read the access line above the main button. It says who the connection belongs to and which agents can use it. To pick a different identity or narrow the agents, select Change.
  3. Select Continue to Tavily and approve access in Tavily's consent screen.

ThinkingMach registers its client with Tavily automatically and asks for the openid and offline_access scopes. There is nothing to configure in a developer console.

Note: Tavily also documents putting an API key in the server address. Do not use that route; sign-in keeps the key out of the URL.

Choose access

Tavily's server offers read actions only: searching the web and extracting page content. There are no actions that change anything in your Tavily account, which makes this one of the lower-stakes connectors to share.

Two things are still worth deciding:

  • Whose credits. At sign-in, Tavily picks the key named mcp_auth_default if your account has one. Otherwise it may use your personal default key or the first key it finds. Check which key and allowance the connection is using, and if you want to control it, create an mcp_auth_default key before you connect.
  • What agents do with results. Search results are outside content. Ask agents to use focused queries, cite source URLs, and keep what they retrieved separate from what they infer. Research is not permission to contact a company or fill in a form on its site. See Set action permissions.

Try it

Search the web with Tavily for three recent articles about a topic we care about, and list them with their links and a one-line summary each.

Open the links. Results you can check confirm the sign-in and the agent's permission.

Note: Illustrative task, not a recorded test result.

Troubleshooting and limitations

Problem Likely cause Fix
Sign-in is refused before it starts ThinkingMach is reached over local HTTP Use a public HTTPS address for ThinkingMach, then connect again
A search fails with a session or request error Tavily's session expired Ask the agent to retry; ThinkingMach starts a new session but does not replay the failed call on its own
Usage comes from an unexpected key Tavily chose a default key at sign-in Create an mcp_auth_default key in Tavily and reconnect
Searches stop working The key's credits ran out Top up in Tavily
Needs attention The grant was revoked or expired Select Reconnect

Limitations: one Tavily account per connection, browser sign-in only, and public web content only.

Sources