FreeAgent + ChatGPT
Build a FreeAgent reader with ChatGPT
Prepare a grounded billing review briefing
Use ChatGPT to build a separate read-only FreeAgent assistant with Agent200. Ground the billing review briefing in returned source data.
On this page
Overview
Build a separate billing review briefing application with Agent200. Use the runtime’s real schemas and preserve the authenticated user. This is an architecture guide, not a native installation in ChatGPT.
Start with one identified invoice. Preserve returned invoice, contact, status and amount fields; report missing data and keep the workflow read-only.
Provider reference: FreeAgent API.
- Connector
- FreeAgent
- Works with
- ChatGPT · Your own agent code
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 5 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.
- FreeAgent enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a FreeAgent account. They approve access once, on FreeAgent's own page.
- A model for your agent. The examples use openai/gpt-5.6-sol, through the same Agent200 API key.
Connect FreeAgent to ChatGPT
-
1
Step 1: Create your Agent200 API key
Create a key on the API keys page and store it securely.
.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: Inspect the real tool definitions
Confirm the actual FreeAgent read operations and input schemas in your runtime.
-
3
Step 3: Connect the user’s FreeAgent account
Preserve the same stable user identity during authorization and later requests.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own FreeAgent account, once. const connection = await agent200 .user("user_123") .connect("freeagent"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
4
Step 4: Build and test the read-only answer
Prepare the billing review briefing only from returned source data. The code example illustrates a sequence, not an SDK installation contract.
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: "Which FreeAgent invoices are still unpaid", tools: ["freeagent"], }); console.log(result.output);
Test your connection
Run one request to check everything is wired up.
Ask
Read the FreeAgent invoice I identify and prepare a billing review briefing. Name the source and use only invoice, contact, status and amount fields. State access gaps; do not change records.
What should come back
- The selected invoice is identified.
- Only the returned invoice, contact, status and amount fields are reported.
- Access gaps and missing context are explicit; no source data is changed.
Check the selected invoice ID, account scope, read permission and pagination. Sandbox records are test data. Do not present a sandbox result as production revenue or an invoice status as a bank reconciliation.
Get your API key
Create a key in the Agent200 dashboard. It reaches FreeAgent 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 FreeAgent to ChatGPT.
Goal: connect FreeAgent to ChatGPT with Agent200. Guide: https://www.agent200.com/connectors/freeagent/framework/chatgpt/ 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 FreeAgent 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. Give every request a stable id for the end user. Agent200 uses only that user's own connections. 5. Connect the user's FreeAgent account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on FreeAgent. 6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "freeagent" in the tools. The model decides when a FreeAgent tool is needed; Agent200 executes the call. 7. Check it works with this request: "Read the FreeAgent invoice I identify and prepare a billing review briefing. Name the source and use only invoice, contact, status and amount fields. State access gaps; do not change records." What should come back: - The selected invoice is identified. - Only the returned invoice, contact, status and amount fields are reported. - Access gaps and missing context are explicit; no source data is changed. 8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in FreeAgent, 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: /connectors/freeagent/framework/chatgpt.md
FreeAgent tools ChatGPT can call
-
List invoices
Readfreeagent_list_invoicesFind invoices in the authorized FreeAgent account.
-
Read an invoice
Readfreeagent_get_invoiceRetrieve one invoice by its resource URL.
-
List contacts
Readfreeagent_list_contactsFind available contact records.
-
Read a contact
Readfreeagent_get_contactRetrieve one identified contact.
-
List expenses
Readfreeagent_list_expensesReview recorded expenses in scope.
No tool matches that search.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input, the end user's id and the FreeAgent tools.
-
02
The model picks a tool
The model decides whether a FreeAgent tool is needed, and with which arguments.
-
03
Agent200 runs the call
It uses that user's own FreeAgent connection, within the endpoints and scopes 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.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's FreeAgent account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and FreeAgent enforces what its API grants.
Troubleshooting
The source cannot be read
Check the selected invoice ID, account scope, read permission and pagination. Sandbox records are test data. Do not present a sandbox result as production revenue or an invoice status as a bank reconciliation.
FAQ
How do I verify this result?
Compare the named invoice and returned invoice, contact, status and amount fields with the source. Treat missing information as missing, not as a fact.
Is this a native product integration?
This describes a separate application built with Agent200 and ChatGPT; it does not install a connector into the ChatGPT app.
