Exa + Claude Code
Build a Exa agent with Claude Code
Have Claude Code build a Exa agent with the Agent200 SDK: no separate key, ready-made tools and one API key.
On this page
Overview
This guide has Claude Code build a Exa agent with the Agent200 SDK, in your own project. When you finish, your agent can call the Exa tools for each of your users.
Claude Code writes the code from the steps below; Agent200 runs the Exa calls with your Agent200 API key. You do not build or maintain a Exa integration.
- Connector
- Exa
- Works with
- Claude Code ยท Coding agent, with the SDK
- Authentication
- Your Agent200 API key
- You need
- An Agent200 API key
- Tools
- 4 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.
- Exa enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- Claude Code in your project. It writes the code with the Agent200 SDK; you review it.
Connect Exa to Claude Code
-
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 Exa 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: Give this guide to Claude Code
Start Claude Code in your project and paste the agent brief from this page, or give it the address of this guide's Markdown version. Claude Code follows the steps below in order: the SDK, the Exa connection and the first request. Review the code it writes before you run it.
-
3
Step 3: 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, }); -
4
Step 4: Run with the Exa tools
Name the user, the model and Exa in the tools. The model decides when a Exa 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: "Find recent papers on retrieval for long documents", tools: ["exa"], }); console.log(result.output);
Test your connection
Run one request to check everything is wired up.
Ask
Find recent papers on retrieval for long documents
What should come back
-
An answer in
result.output, built from Exa results. -
Behind the scenes, the model calls a Exa tool, such as
exa_search_web, and Agent200 runs it.
If the tools are missing, check that Exa is enabled for your project in the dashboard.
Get your API key
Create a key in the Agent200 dashboard. It reaches Exa 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 Exa to Claude Code.
Goal: connect Exa to Claude Code with Agent200. Guide: https://www.agent200.com/tools/exa/framework/claude-code/ 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 Exa 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 "exa" in the tools. The model decides when a Exa tool is needed; Agent200 executes the call. 5. Check it works with this request: "Find recent papers on retrieval for long documents" What should come back: - An answer in `result.output`, built from Exa results. - Behind the scenes, the model calls a Exa tool, such as `exa_search_web`, 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/exa/framework/claude-code.md
Exa tools Claude Code can call
-
Search the web
Readexa_search_webFind pages that match a query, with filters for domain, date and category.
-
Get page contents
Readexa_get_contentsRead the text, highlights or summary of chosen pages.
-
Find similar pages
Readexa_find_similarFind pages similar to a given URL.
-
Get an answer
Readexa_get_answerAnswer a question from search results, with citations.
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 Exa tools.
-
02
The model picks a tool
The model decides whether a Exa tool is needed, and with which arguments.
-
03
Agent200 runs the call
It reaches Exa 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
Claude Code does not use the Exa tools
Check that Exa is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Exa 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 Exa 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.