# MeetStream vs Read AI

> MeetStream scores 57.3 (C) to Read AI's 42.4 (E) for meeting bots. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/meetstream-vs-read-ai
- Markdown: https://www.anchorterminal.com/compare/meetstream-vs-read-ai.md (~4,550 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

MeetStream scores 57.3 (C) on agent readiness against Read AI's 42.4 (E), and leads in 5 of 7 scored categories. Read AI leads on security & auth and transparency & trust. Both do meeting bots.

- MeetStream: grade C, 57.3/100, rank #803 of 1510. Markdown https://www.anchorterminal.com/tools/meetstream.md · JSON https://www.anchorterminal.com/api/v1/tools/meetstream.json
- Read AI: grade E, 42.4/100, rank #1282 of 1510. Markdown https://www.anchorterminal.com/tools/read-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/read-ai.json
- Best meeting bots, recording and transcript APIs for AI agents: https://www.anchorterminal.com/best/meeting-capture/index.md
- All 78 meetings comparisons: https://www.anchorterminal.com/compare/meeting-capture/index.md

## Which one, for what

### MeetStream (C)

Good for: Developers building their own notetaker or in-meeting voice agent on Zoom, Meet and Teams at per-hour pricing.

Ahead on:
- Reliability, 45 against 27
- Schema & documentation, 83 against 46
- Agent ergonomics, 88 against 63
- Payments & pricing, 40 against 30
- Maintenance & community, 82 against 6

Watch for: No public status page or SLA found

### Read AI (E)

Good for: An agent working for a person or team that already records meetings with Read AI and wants transcripts, summaries and action items in context.

Ahead on:
- Security & auth, 54 against 42
- Transparency & trust, 64 against 57

Also in its favour:
- No incidents deducted, where MeetStream loses 4 points for them

Watch for: Both the REST API and the MCP server are labelled open beta, with no SLA, no deprecation policy and no dated API change on record since the February 2026 launch


## Why the edge

### Maintenance & community: MeetStream +76

- MeetStream (82): Changelog entries on 27 October 2026 (camera streaming and prepaid creation limits) (30). Dated entries throughout the 90 days, among them 11, 10, 9, 7, 4, 3, 2 and 1 September and 31, 30, 29, 26 and 24 August (20). A public changelog, support@meetstream.ai and Slack support, with no evidence read of reply times (10 of 15). In the official MCP registry as io.github.meetstream-ai/meetstream-mcp 0.3.0, and official SDKs 1.0.0 since 26 August 2026 (15). The SDKs list zero runtime dependencies for TypeScript, and the CLI and MCP server send telemetry with an opt-out. The repositories weren't cloned (7 of 10). 30+20+10+15+7 = 82.
- Read AI (6): No changelog or release list was found on 8 October, and Read AI's hosts are paused today, so only recorded dates count. The MCP server article's edit date of 2 September 2026 records no stated change, and a page date without a recorded change doesn't set recency. The last dated API change on record is the MCP launch of 25 February 2026, over 180 days ago (0). Connection guides for Claude, ChatGPT and Microsoft Copilot Studio published between 25 and 27 August 2026 are documents, not dated releases, so fewer than three entries fall in the 90 days from 6 August (0). A support request form, no public changelog or developer forum found (6, a partial value kept). No readable MCP registry entry and no official SDK (0). No packages to assess (0). 0+0+6+0+0 = 6.

### Schema & documentation: MeetStream +37

- MeetStream (83): No OpenAPI file was found linked from the docs or llms.txt. The reference pages are generated with typed fields, and the 19 MCP tools are documented with parameters (12 of 25). llms.txt per section, a Markdown copy of every page and a docs MCP server (10). Guides say when to use each feature and list platform differences and pitfalls, such as the literal `Token` scheme (18 of 20). Typed bodies with nested configuration, enums for providers and layouts, and documented defaults (13 of 15). Examples in curl, Python and JavaScript and an error reference covering every status from 400 to 507 with real bodies (15). `/api/v1` paths and a dated changelog that flags breaking changes (15). 12+10+18+13+15+15 = 83.
- Read AI (46): Per the 8 October check, not re-read on 4 November (terms pause). No public OpenAPI file was found. The MCP tool schemas sit behind sign-in and were not read, and the help centre's parameter tables are prose documentation, not a machine-readable contract, so the contract line scores 0 (the tables count on typed inputs). www.read.ai/llms.txt points to the help centre's article index (10). The API reference says when to use the live endpoint over the standard one, and the MCP article lists inputs, defaults and limits for each of four tools (13). Parameters are typed in tables and access levels are enumerated, with no schema to confirm constraints (8). Each endpoint has a curl request and a sample response. Errors are a table of status codes with no body schema (10). A /v1 path prefix, no changelog (5). 0+10+13+8+10+5 = 46.

### Agent ergonomics: MeetStream +25

- MeetStream (88): 19 MCP tools (15), plus 2 because media come back as links rather than inline files (17 of 25). Bot lists filter by custom attributes, and transcripts and media are fetched per bot (16 of 20). Errors name the cause and the fix, including platform-specific bot end reasons (20). Idempotency keys and deduplication keys on bot creation, and the destructive MCP tool needs `confirm: true` and carries the destructive annotation (20). Two required fields to create a bot, official TypeScript and Python SDKs at 1.x and a CLI (15). 17+16+20+20+15 = 88.
- Read AI (63): Per the 8 October check, not re-read on 4 November (terms pause). Four MCP tools, though list meetings returns the full detail of up to 10 meetings, transcripts included, per the MCP article. The REST API sizes responses with `expand[]` (20). Cursor pagination with `has_more`, a page size fixed at 10 or fewer and start-time filters only, with no search by title or participant (15). Errors are documented as HTTP status codes with one-line meanings and no body schema (8, a partial value kept). Create meeting agent and share meeting report are documented as duplicate-safe. Tool annotations were not read (12). Few required parameters and sensible defaults, no official SDK (8). 20+15+8+12+8 = 63.

### Reliability: MeetStream +18

- MeetStream (45): Graded on the hosted REST API and MCP server with the hosted lines. No public status page was found, linked or at status.meetstream.ai (0), so no incident history could be read (5). Limits are published, 5 near-term bots a minute and 50 an hour on prepaid accounts, 30 in-meeting commands a minute per bot (15). 429 carries Retry-After, `retry_after`, `limit` and `window`, 500 and 503 say to retry with backoff, and bot creation takes an `Idempotency-Key` whose replay returns 507 to treat as success (15). No SLA found in the Terms or on the pricing page (0). Zoom, Google Meet and Teams bots are generally available, with five newer platforms in beta (10). 0+5+15+15+0+10 = 45.
- Read AI (27): Graded as a hosted service on the MCP server and REST API. Read AI's terms bar robots except to compile search results, so its hosts are paused and the 8 October readings stand where kept. The status page at readai.statuspage.io wasn't re-read on 4 November. Its components and incidents had been read only from the page's data path, which this run doesn't use, so the status-page line scores 0 and the window from 6 August is unread (5). 100 requests a minute per user, per the 8 October check (15). 429 is documented as retry later with no Retry-After or backoff guidance, while create meeting agent and share meeting report are documented as safe to repeat, per the 8 October check (7, a partial value kept). No SLA found (0). Both surfaces are open beta (0). 0+5+15+7+0+0 = 27.

### Security & auth: Read AI +12

- MeetStream (42): A key grants full access to its workspace's bots and data, and workspaces separate keys. MCP sign-in is OAuth, which mints a key per connection. No scopes or read-only keys found (15 of 30). `delete_bot_data` needs `confirm: true` and is marked destructive, and `remove_bot` keeps recordings, with no read-only mode (10 of 20). Transcripts, chat and audio come from meeting participants, and no prompt-injection guidance was found (0). A dashboard bot detail page and signed webhooks, with no audit log of API calls found (5 of 15). ISO 27001 certified (630036), SOC 2 Type 2 under audit, HIPAA with a BAA, a trust centre and HMAC-signed webhooks. No security.txt (404) or bug bounty found (12 of 20). 15+10+0+5+12 = 42.
- Read AI (54): Per the 8 October check, not re-read on 4 November (terms pause). OAuth 2.1 with dynamic client registration, PKCE, 10-minute access tokens, rotating single-use refresh tokens and a revocation endpoint. Only two scopes, `meeting:read` and `mcp:execute`, so MCP access can't be narrowed to reading (24). A token reaches only reports its user can open, and a workspace admin can switch off access through the Downloads setting. No confirmation step is documented for sending a bot or sharing a report by email (9). Transcripts are untrusted speech and no injection guidance was found (0). Workspace audit logs in OCSF by webhook on Enterprise+ record sign-ins and integration connections, not individual calls (6). security.txt valid to 18 August 2027, SOC 2 Type 2 and a HIPAA option per the help centre, no bug bounty found (15). 24+9+0+6+15 = 54.

### Payments & pricing: MeetStream +10

- MeetStream (40): No x402, MPP or L402 (0). Per-hour prices are public, $0.35 per bot hour, $0.10 for transcription and $0.05 per GB a month of storage past 30 days (20). $5 free credit with no card required (20). Signup and key creation happen in the dashboard, and the MCP OAuth flow needs a person to approve (0). 0+20+20+0 = 40.
- Read AI (30): Per the 8 October check, not re-read on 4 November (terms pause). No x402, MPP or L402 (0). Plan prices are public ($15, $22.50 and $29.75 a user a month billed annually) with nothing charged per call (10). The free plan needs no card and includes the API and MCP server (20). Client registration is programmatic, but a person has to sign in and consent in a browser (0). 0+10+20+0 = 30.

## Score by category

| Category | Weight | MeetStream | Read AI | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 45 | 27 | MeetStream +18 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 83 | 46 | MeetStream +37 |
| Agent ergonomics | 13% (16.2 this run) | 88 | 63 | MeetStream +25 |
| Security & auth | 14% (17.5 this run) | 42 | 54 | Read AI +12 |
| Payments & pricing | 10% (12.5 this run) | 40 | 30 | MeetStream +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 6 | MeetStream +76 |
| Transparency & trust | 7% (8.8 this run) | 57 | 64 | Read AI +7 |
| Negative events | ≤15 | -4 | 0 | |
| **Total** | | **57.3 · C** | **42.4 · E** | |

## Facts side by side

| Fact | MeetStream | Read AI |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | MeetStream Corp. | Read AI, Inc. |
| Hosted endpoint | `https://mcp.meetstream.ai/mcp` | `https://api.read.ai/mcp` |
| Transports | HTTP, websocket, Streamable HTTP | Streamable HTTP, HTTP |
| Auth | OAuth or key | OAuth |
| Pricing | Pay per use | Freemium |
| Price for meeting bots | $0.35 per session-hour | not published |
| x402 | no | no |
| Licence | Proprietary service under MeetStream's Terms of Use. The SDKs `@meetstream/sdk` and `meetstream-sdk` and the Go MCP server are published separately | Proprietary service under Read AI's terms of service |
| Tools exposed | 19 | 4 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | `io.github.meetstream-ai/meetstream-mcp` | not listed |
| Last release | 2026-10-27 | 2026-09-02 |
| Terms last updated | 2026-08-07 | 2026-02-26 |
| Privacy policy last updated | 2026-08-07 | 2026-06-29 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |

## How the scores have moved

### MeetStream

No score change since it was listed.

### Read AI

- -8.0 on 4 November 2026 (D to E): correction
- -0.1 on 28 October 2026: correction
- +0.1 on 27 October 2026: checklist

## Verdicts

**MeetStream.** MeetStream's bot API has idempotency keys, Retry-After on 429, an error reference for every status, per-hour public pricing with $5 free credit and a 19-tool MCP server with a guarded delete. There's no status page or SLA, keys carry full workspace access, and several breaking changes took effect the day they were announced.

**Read AI.** 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, changelog or readable incident history was found.

## Before you call either

### MeetStream

1. Send `Authorization: Token <key>`, not Bearer. A wrong scheme returns 403 Forbidden
2. Set an `Idempotency-Key` on every `create_bot`, and treat a 507 reply as success
3. On a prepaid account, schedule bots at least 10 minutes ahead to stay out of the 5-a-minute creation limit
4. Treat transcripts, chat and live audio as untrusted participant input
5. Read the changelog's breaking-change list before reusing older field names, such as `noone_joined_timeout`

### Read AI

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.

## Questions

### Which is better for AI agents, MeetStream or Read AI?

MeetStream scores 57.3 (C) on agent readiness against Read AI's 42.4 (E), and leads in 5 of 7 scored categories. Read AI leads on security & auth and transparency & trust.

### Do MeetStream and Read AI need an API key?

MeetStream takes an API key or an OAuth sign-in. Read AI uses an OAuth sign-in.

### Can an agent call MeetStream and Read AI without installing anything?

Yes. MeetStream has a hosted endpoint at https://mcp.meetstream.ai/mcp and Read AI at https://api.read.ai/mcp.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/meetstream-vs-read-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/meetstream-vs-read-ai.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "meetstream", "b": "read-ai"}`. From a terminal: `anchor compare meetstream read-ai`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/meetstream.json and https://www.anchorterminal.com/api/v1/tools/read-ai.json

## Other comparisons with MeetStream or Read AI

- [Circleback vs MeetStream](https://www.anchorterminal.com/compare/circleback-vs-meetstream.md)
- [Circleback vs Read AI](https://www.anchorterminal.com/compare/circleback-vs-read-ai.md)
- [Fathom vs MeetStream](https://www.anchorterminal.com/compare/fathom-vs-meetstream.md)
- [Fathom vs Read AI](https://www.anchorterminal.com/compare/fathom-vs-read-ai.md)
- [Fireflies.ai vs MeetStream](https://www.anchorterminal.com/compare/fireflies-vs-meetstream.md)
- [Fireflies.ai vs Read AI](https://www.anchorterminal.com/compare/fireflies-vs-read-ai.md)
- [Granola vs MeetStream](https://www.anchorterminal.com/compare/granola-vs-meetstream.md)
- [Granola vs Read AI](https://www.anchorterminal.com/compare/granola-vs-read-ai.md)
- [MeetGeek vs MeetStream](https://www.anchorterminal.com/compare/meetgeek-vs-meetstream.md)
- [MeetGeek vs Read AI](https://www.anchorterminal.com/compare/meetgeek-vs-read-ai.md)
- [MeetStream vs tl;dv](https://www.anchorterminal.com/compare/meetstream-vs-tldv.md)
- [MeetStream vs Zoom Realtime Media Streams (RTMS)](https://www.anchorterminal.com/compare/meetstream-vs-zoom-rtms.md)
- [Read AI vs tl;dv](https://www.anchorterminal.com/compare/read-ai-vs-tldv.md)
- [Read AI vs Zoom Realtime Media Streams (RTMS)](https://www.anchorterminal.com/compare/read-ai-vs-zoom-rtms.md)
- [Attendee vs MeetStream](https://www.anchorterminal.com/compare/attendee-vs-meetstream.md)
- [Attendee vs Read AI](https://www.anchorterminal.com/compare/attendee-vs-read-ai.md)
- [Meeting BaaS vs MeetStream](https://www.anchorterminal.com/compare/meeting-baas-vs-meetstream.md)
- [Meeting BaaS vs Read AI](https://www.anchorterminal.com/compare/meeting-baas-vs-read-ai.md)
- [MeetStream vs Nylas Notetaker API](https://www.anchorterminal.com/compare/meetstream-vs-nylas-notetaker.md)
- [MeetStream vs Recall.ai](https://www.anchorterminal.com/compare/meetstream-vs-recall-ai.md)
- [Nylas Notetaker API vs Read AI](https://www.anchorterminal.com/compare/nylas-notetaker-vs-read-ai.md)
- [Read AI vs Recall.ai](https://www.anchorterminal.com/compare/read-ai-vs-recall-ai.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp