# Connect FreeAgent to Muse Prepare a grounded billing review briefing

> Read invoices with Muse and Agent200. Prepare a billing review briefing using the connected user’s own FreeAgent account.

- Page: https://www.agent200.com/connectors/freeagent/framework/muse/
- Connector: [FreeAgent](https://www.agent200.com/connectors/freeagent.md)
- Framework: Muse
- Updated: 2026-11-17

## Instructions for AI agents

Goal: connect FreeAgent to Muse with Agent200, through its MCP server.
Guide: https://www.agent200.com/connectors/freeagent/framework/muse/

1. The user needs an Agent200 API key. If they have none, send them to https://agent200.com/platform/apikeys/ to choose "Create an API key". They paste it into Muse's settings themselves: never ask for it in chat and never write it into files you share.
2. Make sure FreeAgent is enabled for their project in the Agent200 dashboard (Connectors), with the tools the task needs.
3. Add Agent200's MCP server to Muse: URL https://api.agent200.com/mcp/, transport streamable HTTP, header "Authorization: Bearer <the user's Agent200 API key>". Follow the setup steps on the guide page for Muse's exact menus or commands.
4. The first FreeAgent request returns an authorization link if the user has not connected FreeAgent yet: show it to them and continue once they have approved access on FreeAgent's own page.
5. 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.
6. 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.

## Overview

Use Muse to prepare a short billing review briefing for review. Put the Agent200 key in Muse’s secure credential interface, then inspect the source before sharing the result.

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](https://dev.freeagent.com/docs/invoices).

- **Connector:** [FreeAgent](https://www.agent200.com/connectors/freeagent/)
- **Works with:** Muse · Agent app, through MCP
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [5 tools](https://www.agent200.com/connectors/freeagent/framework/muse/#tools)
- **MCP server:** `https://api.agent200.com/mcp/`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) 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.
- **Muse, with custom MCP servers allowed.** Muse creates custom connectors from a chat, and your key goes into its secure credentials sheet, never into the chat. Muse Code reads servers from its settings file.

## Connect FreeAgent to Muse

### Step 1: Create your Agent200 API key

Create a key on the [API keys page](https://agent200.com/platform/apikeys/) and store it securely.

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Create the custom connector

Connect to `https://api.agent200.com/mcp/` over Streamable HTTP with an Authorization: Bearer header. Enter the key in Muse’s secure credential interface.

File `Muse chat`:

```text
Create a Custom Connector for the Agent200 remote MCP server and connect to it:
Name: Agent200
Transport: remote streamable HTTP
URL: https://api.agent200.com/mcp/
Auth: API key sent in the Authorization header as "Bearer <key>"
Open the secure credentials store so I can enter the API key there, not in this chat.
Then list its tools to confirm the connection works.
```

### Step 3: Inspect read tools

Confirm the FreeAgent operations and schemas advertised by the connection.

### Step 4: Authorize FreeAgent

Connect the intended user and test one accessible invoice.

## Test your connection

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.

## FreeAgent tools Muse can call

- **List invoices** (`freeagent_list_invoices`, read): Find invoices in the authorized FreeAgent account.
- **Read an invoice** (`freeagent_get_invoice`, read): Retrieve one invoice by its resource URL.
- **List contacts** (`freeagent_list_contacts`, read): Find available contact records.
- **Read a contact** (`freeagent_get_contact`, read): Retrieve one identified contact.
- **List expenses** (`freeagent_list_expenses`, read): Review recorded expenses in scope.

## How it works

1. **You ask Muse.** In your own words, for something in FreeAgent.
2. **Muse picks a tool.** It sees the FreeAgent tools on the Agent200 MCP server and calls the one the request needs.
3. **Agent200 runs the call.** With your own FreeAgent connection, within the tools and scopes your project allows.
4. **Muse answers.** It gets the result back from the MCP server and uses it in its reply or its next step.

**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.

## Use FreeAgent with another framework

- [FreeAgent + Claude](https://www.agent200.com/connectors/freeagent/framework/claude.md)
- [FreeAgent + ChatGPT](https://www.agent200.com/connectors/freeagent/framework/chatgpt.md)
- [FreeAgent + Claude Code](https://www.agent200.com/connectors/freeagent/framework/claude-code.md)
- [FreeAgent + Grok Bot](https://www.agent200.com/connectors/freeagent/framework/grok-bot.md)
- [FreeAgent + OpenAI Dots](https://www.agent200.com/connectors/freeagent/framework/openai-dots.md)
- [FreeAgent + Claude Duet](https://www.agent200.com/connectors/freeagent/framework/claude-duet.md)
- [FreeAgent + Hermes Agent](https://www.agent200.com/connectors/freeagent/framework/hermes-agent.md)
- [FreeAgent + OpenClaw](https://www.agent200.com/connectors/freeagent/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
