Tavily + OpenAI Dots
Connect Tavily to OpenAI Dots
with OpenAI models and the Agent200 SDK
Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Tavily agent with OpenAI's models and the Agent200 SDK.
On this page
Overview
OpenAI Dots use the plugins connected to a ChatGPT account, and ChatGPT’s custom MCP servers cannot send an API key. To give an always-on agent the Tavily tools, build it with the Agent200 SDK and OpenAI’s models: this guide shows how.
Your agent then calls the Tavily tools reached with your Agent200 API key, with no separate Tavily key to manage.
- Connector
- Tavily
- Works with
- OpenAI Dots · Your own agent code
- Authentication
- Your Agent200 API key
- You need
- An Agent200 API key
- Tools
- 2 tools
- Model in examples
openai/gpt-5.6-sol
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- Tavily enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- A model for your agent. The examples use openai/gpt-5.6-sol, through the same Agent200 API key.
Connect Tavily to OpenAI Dots
-
1
Step 1: Create your Agent200 API key
Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers Tavily and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.
.envConceptual exampleStore the Agent200 API key as an environment variable # Keep the key out of your code, prompts and chats. export AGENT200_API_KEY="paste-your-key-here" -
2
Step 2: Set up the Agent200 SDK
Add the SDK to your project and create a client with the key from the environment.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
3
Step 3: Run with the Tavily tools
Name the user, the model and Tavily in the tools. The model decides when a Tavily tool is needed, and Agent200 executes the call with the user's own connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "What changed in the EU AI Act this month?", tools: ["tavily"], }); console.log(result.output);
Test your connection
Run one request to check everything is wired up.
Ask
What changed in the EU AI Act this month?
What should come back
-
An answer in
result.output, built from Tavily results. -
Behind the scenes, the model calls a Tavily tool, such as
tavily_search, and Agent200 runs it.
If the tools are missing, check that Tavily is enabled for your project in the dashboard.
Get your API key
Create a key in the Agent200 dashboard. It reaches Tavily and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Tavily to OpenAI Dots.
Goal: connect Tavily to OpenAI Dots with Agent200. Guide: https://www.agent200.com/tools/tavily/framework/openai-dots/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Make sure Tavily is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs. 3. Add the Agent200 SDK to the project and create a client with that key. 4. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "tavily" in the tools. The model decides when a Tavily tool is needed; Agent200 executes the call. 5. Check it works with this request: "What changed in the EU AI Act this month?" What should come back: - An answer in `result.output`, built from Tavily results. - Behind the scenes, the model calls a Tavily tool, such as `tavily_search`, and Agent200 runs it. 6. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard, then retry. The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
The whole guide is also available as Markdown, for agents and LLMs: /tools/tavily/framework/openai-dots.md
Tavily tools OpenAI Dots can call
-
Search the web
Readtavily_searchSearch the web and get ranked results with content.
-
Extract a page
Readtavily_extractRead the main content of a web page.
No tool matches that search.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input and the Tavily tools.
-
02
The model picks a tool
The model decides whether a Tavily tool is needed, and with which arguments.
-
03
Agent200 runs the call
It reaches Tavily with your Agent200 API key, within the endpoints your project allows, and returns the result to the model.
-
04
Your app gets the result
Agent200 returns the completed result. Your app decides when the agent runs and what happens next.
Permissions at every level. Your project settings decide which services and endpoints the agent may use.
Troubleshooting
Why not connect Agent200 to a dot directly?
A dot uses the plugins connected to your ChatGPT account, and ChatGPT’s custom MCP servers cannot send an API key. Building the agent with the Agent200 SDK, as on this page, is the route that works.
OpenAI Dots does not use the Tavily tools
Check that Tavily is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Tavily in the request, or in the instructions, also helps the model choose the right tool.
A tool call is refused or returns less than expected
Agent200 runs only what your project allows. Check that the Tavily endpoints the agent needs are enabled in the dashboard's Connectors settings.
The API key was pasted into a chat or committed
Create a new key on the API keys page, update AGENT200_API_KEY wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.