# Read AI (slim)

> Read AI is a meeting assistant that records Zoom, Google Meet and Microsoft Teams calls and produces transcripts, summaries and action items. Outside agents reach the reports through a remote MCP server and a REST API, both in open beta.

- Full: https://www.anchorterminal.com/tools/read-ai.md (~7,450 tokens) · this version ~1,930 tokens · JSON https://www.anchorterminal.com/tools/read-ai.json · canonical https://www.anchorterminal.com/tools/read-ai
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-08

**D · 50.4/100 · rank #517 of 629 · #5 in Meeting capture & meeting infrastructure · not agent-ready · confidence medium**


Assessment: Four MCP tools and three REST endpoints return transcripts, summaries, action items and recording links, and the MCP server can send a bot to a named meeting. Both surfaces are in open beta. Access needs a browser sign-in, access tokens last 10 minutes, and no OpenAPI file or changelog was found.

## Facts

- Kind: MCP server · vendor: Read AI, Inc. · category: Meeting capture & meeting infrastructure · legal entity: Read AI, Inc. · provenance 81/100
- Endpoint: `https://api.read.ai/mcp` (Streamable HTTP, HTTP)
- Auth: OAuth · pricing: Freemium · x402: no · licence: Proprietary service under Read AI's terms of service
- Probe metrics: not measured yet (probes haven't run)
- MCP server: https://api.read.ai/mcp, remote, Streamable HTTP, OAuth 2.1. Open beta. Listed as a Claude connector and a ChatGPT app, with a guide for Microsoft Copilot Studio
- MCP tools: Get meeting by id, list meetings (up to 10 a page, date-range filter), create meeting agent (meeting URL, or platform plus meeting ID and password, optional start time and title), share meeting report (email, access level of recap viewer, full viewer or editor, optional message and notify flag)
- REST API: Base https://api.read.ai. GET /v1/meetings, GET /v1/meetings/{id}, GET /v1/meetings/{id}/live. Read-only. Open beta
- Expandable fields: summary, chapter_summaries, action_items, key_questions, topics, transcript, metrics, recording_download. The live endpoint expands only transcript and chapter_summaries
- Credentials: OAuth 2.1 authorisation code grant with PKCE and dynamic client registration. Scopes `meeting:read` and `mcp:execute`. Access tokens 10 minutes, rotating single-use refresh tokens, revocation endpoint at https://authn.read.ai/oauth2/revoke
- Rate limits: 100 requests a minute per user, HTTP 429 above that
- Pagination: Cursor-based. `limit` defaults to 10 and can't exceed 10, `cursor` is the ID of the last meeting on the previous page, `has_more` marks further pages. Filters are `start_time_ms.gt`, `.gte`, `.lt` and `.lte`
- Errors: HTTP status codes 400, 401, 403, 404, 422, 429 and 500 with one-line meanings. No error body schema is documented
- Webhooks: User webhooks (meeting_end) and workspace webhooks (meeting_start, meeting_end). HMAC SHA-256 signature in `X-Read-Signature` for webhooks created after 17 March 2026, `request_id` for duplicates, retries with exponential backoff, stopped after 25 consecutive failures. Pro plans and above
- Live data: Live transcript and chapter summaries are returned only while someone has the live dashboard open during the meeting. An account-wide setting is planned for general availability
- Not exposed: Ask Read, Coaching, file upload for transcription, removing or controlling a bot in a meeting, and calendar management, per the vendor's list of feature gaps and the documented tools
- Consent: Read joins as a visible participant, posts a chat notice naming who invited it, and leaves and deletes the recording when a participant types opt out in the chat. Workspaces can email external invitees an advance notice with an opt-out link
- Audit: Workspace audit logs in OCSF format, delivered by webhook only, on Enterprise+. They cover sign-ins, access changes and integration connections, not individual API or MCP calls
- Certifications: SOC 2 Type 2 and a HIPAA option on Enterprise+, per the help centre. Reports and the DPA are held in the Trust Centre at https://trust.read.ai
- Status: https://readai.statuspage.io (Atlassian Statuspage), with an API component and separate components for Zoom, Google Meet and Microsoft Teams meeting bots
- Data regions: United States by default. EU and Canada deployments announced 2 February 2026, arranged through sales
- Prices: Pro $15 per seat per month; Enterprise $22.50 per seat per month; Enterprise+ $29.75 per seat per month

- Scores: Reliability 52, Performance pending, Schema & documentation 51, Agent ergonomics 63, Security & auth 54, Payments & pricing 30, Task success pending, Maintenance & community 31, Transparency & trust 63 · total over the 7 assessed categories
- Why: Reliability, Graded as a hosted service on the MCP server and REST API. · Schema & documentation, No public OpenAPI file was found, and requests to api.read.ai/openapi.json and /docs got no response. · Agent ergonomics, Four MCP tools, though list meetings returns the full detail of up to 10 meetings, transcripts included, per the MCP article. · Security & auth, OAuth 2.1 with dynamic client registration, PKCE, 10-minute access tokens, rotating single-use refresh tokens and a revocation endpoint. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, No changelog or release list was found, so dates come from the help centre. · Transparency & trust, Closed service with published terms, last updated 26 February 2026 (15).
- Sources: 18, open questions: 7, both in the full twin
- Capabilities: meetings.bot, meetings.transcript, meetings.summary, meetings.recording
- JSON: https://www.anchorterminal.com/api/v1/tools/read-ai.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/read-ai.svg` or a link to https://www.anchorterminal.com/tools/read-ai from a page on read.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Persist the new refresh token after every refresh. Access tokens expire after 10 minutes and each refresh token works once.
2. Request only the fields needed with `expand[]` on the REST API. Transcripts and other expansions slow the response.
3. Stay under 100 requests a minute per user and back off on 429. No Retry-After header is documented.
4. Confirm with the user before calling create meeting agent or share meeting report. Sharing emails the recipient unless notify is set to no.
5. Ask a workspace admin to enable Downloads in Reports & Sharing first. Without it the API and MCP server return nothing for workspace members.

## Connect

```bash
curl "https://api.read.ai/v1/meetings?limit=5&start_time_ms.gte=1733700000000" \
  -H "Authorization: Bearer $READ_AI_ACCESS_TOKEN" \
  -H "Accept: application/json"
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/read-ai

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Fireflies.ai | C | 60.6 | meetings.transcript, meetings.summary, meetings.recording, meetings.bot | https://www.anchorterminal.com/tools/fireflies.min.md |
| Meeting BaaS | B | 62 | meetings.bot, meetings.transcript, meetings.recording | https://www.anchorterminal.com/tools/meeting-baas.min.md |
| Recall.ai | C | 59.5 | meetings.bot, meetings.recording, meetings.transcript | https://www.anchorterminal.com/tools/recall-ai.min.md |
| tl;dv | D | 51 | meetings.transcript, meetings.summary, meetings.recording | https://www.anchorterminal.com/tools/tldv.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)