canonical: https://jentic.com/apis/intermind.com/intermind

# InterMIND API

The InterMIND API schedules meetings on behalf of a user and returns the recaps and speaker-labelled transcripts InterMIND produces after each call, across a meeting space that understands 20+ languages. It lists the user's meetings, searches recap summaries for a phrase, and runs a passage search across recaps, transcripts, channel chats, and shared files. It also reads and posts messages in the user's channels, returns the extracted text of documents shared in meetings, and lets a tool subscribe a webhook that fires when a recap is ready.

## For AI agents

Create InterMIND meeting links, read meeting recaps and Markdown transcripts, search an account's meeting knowledge, and post in channels as the key's user.

## Scope

Does not handle calendar sync for other providers, live call audio streaming, or meeting recording downloads. Use for InterMIND meetings, recaps, transcripts, and channel messages only.

## Capabilities

- Create an ad-hoc InterMIND meeting link or schedule one at a starts_at time with invitees
- Read the latest finalized transcript of a meeting as Markdown grouped by speaker
- Search recap summaries for a phrase and list the newest recaps of hosted meetings
- Find the best-matching passages across recaps, transcripts, chats, and shared files with a date range
- Read a page of channel chat and post a message as the key's user
- Subscribe a target_url to the recap.ready event so a tool is notified without polling

## Use cases

### AI meeting assistant that reads recaps and follows up

A developer's agent connected through Jentic searches by intent, loads the InterMIND recap and channel operations with their input schemas, and calls them with the bearer token injected at execution time. After a call ends, the agent reads the recap, pulls action items from the transcript, and posts a summary into the team channel, all as the key's user and without the token entering the agent's context.

Example prompt: Call GET /recaps with limit 1 to find the newest recap, read GET `/meetings/{id}/transcript` for that meeting, then POST `/channels/{id}/messages` with a three-bullet summary in the text field

### Scheduling meetings from a chat or calendar request

When a user asks to set up a call, a tool can create an InterMIND meeting link immediately or place it at a chosen time. The create call accepts a title, starts_at, duration_min, time_zone, and an invitees list, so one request returns a joinable link that lands in the user's calendar.

Example prompt: POST /meetings with title 'Q3 planning', starts_at set to next Tuesday 15:00, duration_min 45, time_zone 'Europe/Dublin', and two invitee emails, then return the meeting link

### Searching what was decided across meetings

Teams lose decisions in long call histories. The InterMIND knowledge search returns the best-matching passages from recaps, transcripts, chats, and shared files, filterable by meeting_id and a from/to date range, while recap search finds summaries containing an exact phrase. A tool can answer 'when did we agree on the launch date' with the passage and its meeting.

Example prompt: Call GET `/knowledge/search` with q 'launch date' and from set to the first of last month, then return the top three passages with their meetings

### Recap-ready notifications into another tool

A CRM or notes tool can react the moment a meeting recap is ready instead of polling. The webhook subscription takes a target_url and an event, the list call shows active subscriptions, and a subscription is removed by id when the integration is disconnected.

Example prompt: POST /webhooks with target_url 'https://example.org/hooks/recap' and event recap.ready, then confirm the subscription appears in GET /webhooks

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/meetings` | Create or schedule a meeting link |
| GET | `/meetings` | List the user's meetings |
| GET | `/meetings/{id}/transcript` | Get a meeting's Markdown transcript |
| GET | `/recaps` | List newest meeting recaps |
| GET | `/knowledge/search` | Search recaps, transcripts, chats, and files |
| POST | `/channels/{id}/messages` | Post a channel message |
| POST | `/webhooks` | Subscribe a webhook to an event |

## Key resources

- **Meetings** — Create ad-hoc or scheduled meeting links and list meetings the user hosts or belongs to
- **Recaps and transcripts** — Newest recaps, phrase search over recap summaries, and the finalized Markdown transcript of a meeting
- **Channels** — Channels and inboxes the user belongs to, paged chat history, and posting a message
- **Documents and knowledge** — Files shared in meetings, their extracted text, and passage search across recaps, transcripts, chats, and files
- **Webhooks** — Subscribe, list, and delete REST hook subscriptions for recap events

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 63 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 67 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 47 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 69 / 100
- **View full report:** https://jentic.com/apis/intermind.com/intermind/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring InterMIND by hand means minting an imk_ bearer key, knowing that older keys return 403 on most routes, and stitching recaps, transcripts, and channels together yourself. Through Jentic you install once, import InterMIND from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** InterMIND puts the channel id in the URL path (`/channels/{id}/messages`), so a rule can pin your agent to one channel's chat. You choose the operations it may call, so actions like posting messages or deleting a webhook subscription are not included unless you add them.
- **Credential handling:** Your InterMIND API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'get a meeting transcript' or 'search meeting recaps', and Jentic returns the matching InterMIND operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Fireflies.ai** — Meeting transcription and notes for calls held on other conferencing tools
- **Zoom Meetings** — Create and manage Zoom meetings, webinars, and recordings
- **Slack** — Team messaging where meeting summaries are often shared
- **Calendly** — Booking pages that decide when a meeting happens

## FAQ

### What authentication does the InterMIND API use?

Per its OpenAPI spec, the InterMIND API authenticates every request with a bearer token in the Authorization header: either a personal API key created under InterMIND Settings, API keys (prefixed imk_), or a token minted by an OAuth connection. Keys created before v1.1 open only /me, POST /meetings, /recaps, and /webhooks, so other endpoints answer 403 until a new key is created. Through Jentic the token is stored by your own instance and attached at call time.

### Can I get a meeting transcript with the InterMIND API?

Yes. GET `/meetings/{id}/transcript` returns the latest finalized transcript of a meeting as Markdown grouped by speaker. You can pass a session to pick a specific session and max_chars to cap the length, which keeps long calls inside an agent's working budget.

### What are the rate limits for the InterMIND API?

The OpenAPI spec does not specify rate limits. Check the InterMIND documentation at https://intermind.com for current limits before running bulk transcript or recap reads.

### Is there an InterMIND MCP server?

You don't need an MCP server to give your agent InterMIND. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the meeting, recap, and channel operations it needs, discovered on demand rather than loaded into its context up front.

### Can I limit what my agent is allowed to do with InterMIND?

Yes. For example, write a rule that allows GET /recaps, GET `/meetings/{id}/transcript`, and POST `/channels/{id}/messages` for a single channel id, so the agent can read recaps and post summaries to that one channel and nothing else, and every call it makes is logged.

### How do I post a meeting summary to a channel through Jentic?

Import InterMIND from the Jentic API Directory and store your API key once. Your agent then searches for 'post a message in a channel', gets POST `/channels/{id}/messages` with its schema, and sends the summary in the text field. To run it on your own infrastructure, install Jentic One from its GitHub repo.