> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aigenda.tech/llms.txt
> Use this file to discover all available pages before exploring further.
# Integrating with an AI agent
> How to give Claude, Cursor, or another agent everything it needs to write an AiGenda integration.
The documentation is available to agents in machine-readable form:
| What | URL |
| - | - |
| The whole documentation in one file | [`https://docs.aigenda.tech/llms-full.txt`](https://docs.aigenda.tech/llms-full.txt) |
| Table of contents with links | [`https://docs.aigenda.tech/llms.txt`](https://docs.aigenda.tech/llms.txt) |
| Any page in Markdown | Add `.md` to the page URL |
A button in the header of every page copies it as Markdown or opens it in ChatGPT, Claude, Cursor, and VS Code.
## Documentation MCP server
Connect the documentation to your agent as an MCP server: the agent finds the right page on its own while it writes code.
```bash Claude Code theme={null}
claude mcp add --transport http aigenda-docs https://docs.aigenda.tech/mcp
```
```json Cursor (.cursor/mcp.json) theme={null}
{
"mcpServers": {
"aigenda-docs": {
"url": "https://docs.aigenda.tech/mcp"
}
}
}
```
```json VS Code (.vscode/mcp.json) theme={null}
{
"servers": {
"aigenda-docs": {
"type": "http",
"url": "https://docs.aigenda.tech/mcp"
}
}
}
```
The server only reads the documentation. It has no access to your AiGenda account.
## Prompt
Copy it and adapt it to your task:
```text Prompt for the agent theme={null}
Write an integration with the AiGenda API: upload a meeting recording, process it, get the protocol.
Documentation: https://docs.aigenda.tech/llms-full.txt. Read it in full before you write any code.
Where the recording is:
Language and stack:
Where to put the result:
Required rules from the documentation:
1. Token: POST /api/token/ with the fields username (email) and password. Header Authorization: Bearer .
2. The recording title ends with the file extension (.mp3, .m4a, .wav, .ogg, .webm, .mp4).
3. The file is uploaded in parts with PUT to the links from the url array; the ETag of each part is passed to complete_upload with its quotes.
4. Before classify, wait for is_uploaded: true in GET .../info/.
5. Poll the result every 15 seconds: 200 + classified: true + success: true = done; 200 + success: false, or 500 for more than 3 minutes = failed; 404 = processing was not started.
6. Do not blindly retry the POST that creates a recording: every call creates a new recording.
7. Take the email and password from the AIGENDA_EMAIL and AIGENDA_PASSWORD environment variables.
8. Meeting bot: always send meeting_service (telemost, zoom, or google_meet) to POST /api/space/{space_id}/meeting/, otherwise the bot is sent as if to Google Meet. Processing of a bot recording starts on its own.
Start with a plan, then the code, then instructions for running it.
```
## Where the agent should start
A complete working Python script is on the [Full example](/en/reference/full-example) page. The easiest path for the agent is to use it as a base and rewrite it for your stack.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.