{ "data": { "similar": [ { "grade": "C", "json": "https://www.anchorterminal.com/tools/fireflies.json", "name": "Fireflies.ai", "score": 60.6, "shared": [ "meetings.transcript", "meetings.summary", "meetings.recording", "meetings.bot" ], "slug": "fireflies" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/meeting-baas.json", "name": "Meeting BaaS", "score": 62, "shared": [ "meetings.bot", "meetings.transcript", "meetings.recording" ], "slug": "meeting-baas" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/recall-ai.json", "name": "Recall.ai", "score": 59.5, "shared": [ "meetings.bot", "meetings.recording", "meetings.transcript" ], "slug": "recall-ai" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/tldv.json", "name": "tl;dv", "score": 51, "shared": [ "meetings.transcript", "meetings.summary", "meetings.recording" ], "slug": "tldv" } ], "tool": { "slug": "read-ai", "name": "Read AI", "vendor": "Read AI, Inc.", "vendorUrl": "https://www.read.ai", "kind": "mcp", "category": "meeting-capture", "summary": "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.", "url": "https://www.anchorterminal.com/tools/read-ai", "markdownUrl": "https://www.anchorterminal.com/tools/read-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/read-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/read-ai.json", "license": "Proprietary service under Read AI's terms of service", "transports": [ "streamable-http", "http" ], "remoteUrl": "https://api.read.ai/mcp", "packages": [], "auth": "oauth", "authNotes": "OAuth 2.1 only, with a browser sign-in to a Read AI account. A client registers itself at https://api.read.ai/oauth/register (dynamic client registration) and runs the authorisation code grant with PKCE against authn.read.ai. Scopes are `meeting:read` for the REST API and `mcp:execute` for the MCP server. Access tokens last 10 minutes and refresh tokens are single-use and rotate. Static API keys and client credentials are not supported in the beta. Workspace members need the Downloads setting enabled by an admin, and a token reaches only the reports its user can open.", "pricing": "freemium", "pricingNotes": "The API and MCP server are available on every plan, including Free (5 meeting transcripts a month, no card). Paid plans billed annually are Pro at $15, Enterprise at $22.50 and Enterprise+ at $29.75 a user a month ($19.75, $29.75 and $39.75 billed monthly). Enterprise+ needs five or more licences. Webhooks need Pro or above, and recording playback needs Enterprise or above. No per-call charge is published (checked 2026-10-08).", "priceSummary": "$15 / seat-mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API reference, the MCP server article, the overview or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview", "llmsTxt": "https://www.read.ai/llms.txt", "capabilities": [ "meetings.bot", "meetings.transcript", "meetings.summary", "meetings.recording" ], "tags": [ "official", "hosted", "mcp", "oauth", "closed-source", "beta", "no-card", "llms-txt", "webhooks", "status-page", "soc2" ], "lastRelease": "2026-09-02", "graded": true, "anchor": { "graded": true, "score": 50.4, "grade": "D", "agentReady": false, "rank": 517, "ranked": true, "rankOf": 629, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 31, "payments": 30, "reliability": 52, "schema": 51, "security": 54, "transparency": 63 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 52, "points": 10.4, "reason": "Graded as a hosted service on the MCP server and REST API. Statuspage at readai.statuspage.io with an API component and per-platform bot components (20). From 10 July to 8 October 2026 the API component has no incident. The bots have one critical incident (Zoom meetings not joined, 3 August, about three hours) and one major (23 July, under an hour), and Ask Read, which the API doesn't expose, has two majors (10). 100 requests a minute per user (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 (7). No SLA found (0). Both surfaces are open beta (0)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 51, "points": 8.29, "reason": "No public OpenAPI file was found, and requests to api.read.ai/openapi.json and /docs got no response. The MCP tool schemas sit behind sign-in and were not read, so 5 of 25 for the published parameter tables. www.read.ai/llms.txt points to a help centre JSON API that returns every article (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)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 63, "points": 10.24, "reason": "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 bare HTTP status codes with one-line meanings, though the 401 from the MCP endpoint carries a clear recovery message (8). 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)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 54, "points": 9.45, "reason": "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)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 30, "points": 3.75, "reason": "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)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 31, "points": 2.71, "reason": "No changelog or release list was found, so dates come from the help centre. The MCP server article was last edited on 2 September 2026, 36 days before the check (20). Connection guides for Claude, ChatGPT and Microsoft Copilot Studio were published between 25 and 27 August 2026, which are documents and not dated releases (5 of 20). A support request form and a status page updated through October, no public changelog or developer forum found (6). Not in the official MCP registry on a search for read.ai, read-ai and readai, and no official SDK (0). No packages to assess (0)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 63, "points": 5.51, "note": "editorial 45, provenance 81", "reason": "Closed service with published terms, last updated 26 February 2026 (15). The privacy policy of 29 June 2026 keeps audio and video for no longer than two years and paid accounts' data until payment stops or deletion is requested. The help centre says model training is opt-in, while the terms grant a licence to train subject to opt-in or opt-out settings, and the DPA sits in a Trust Centre we couldn't read (20). No deprecation policy for the beta API (0). A sub-processor list is linked at trust.read.ai/subprocessors but didn't render for us, and EU and Canada data regions were announced on 2 February 2026 (10)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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 bare HTTP status codes with one-line meanings, though the 401 from the MCP endpoint carries a clear recovery message (8). 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).", "maintenance": "No changelog or release list was found, so dates come from the help centre. The MCP server article was last edited on 2 September 2026, 36 days before the check (20). Connection guides for Claude, ChatGPT and Microsoft Copilot Studio were published between 25 and 27 August 2026, which are documents and not dated releases (5 of 20). A support request form and a status page updated through October, no public changelog or developer forum found (6). Not in the official MCP registry on a search for read.ai, read-ai and readai, and no official SDK (0). No packages to assess (0).", "payments": "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).", "reliability": "Graded as a hosted service on the MCP server and REST API. Statuspage at readai.statuspage.io with an API component and per-platform bot components (20). From 10 July to 8 October 2026 the API component has no incident. The bots have one critical incident (Zoom meetings not joined, 3 August, about three hours) and one major (23 July, under an hour), and Ask Read, which the API doesn't expose, has two majors (10). 100 requests a minute per user (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 (7). No SLA found (0). Both surfaces are open beta (0).", "schema": "No public OpenAPI file was found, and requests to api.read.ai/openapi.json and /docs got no response. The MCP tool schemas sit behind sign-in and were not read, so 5 of 25 for the published parameter tables. www.read.ai/llms.txt points to a help centre JSON API that returns every article (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).", "security": "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).", "transparency": "Closed service with published terms, last updated 26 February 2026 (15). The privacy policy of 29 June 2026 keeps audio and video for no longer than two years and paid accounts' data until payment stops or deletion is requested. The help centre says model training is opt-in, while the terms grant a licence to train subject to opt-in or opt-out settings, and the DPA sits in a Trust Centre we couldn't read (20). No deprecation policy for the beta API (0). A sub-processor list is linked at trust.read.ai/subprocessors but didn't render for us, and EU and Canada data regions were announced on 2 February 2026 (10)." }, "sources": [ { "what": "API and MCP overview, prerequisites and known limitations", "url": "https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview", "seen": "2026-10-08" }, { "what": "MCP server details and tools", "url": "https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server", "seen": "2026-10-08" }, { "what": "REST API reference", "url": "https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference", "seen": "2026-10-08" }, { "what": "OAuth flow and token lifetimes", "url": "https://support.read.ai/hc/en-us/articles/49380809380371-API-Keys-Authentication", "seen": "2026-10-08" }, { "what": "OAuth authorisation server metadata", "url": "https://authn.read.ai/.well-known/oauth-authorization-server", "seen": "2026-10-08" }, { "what": "MCP protected resource metadata", "url": "https://api.read.ai/.well-known/oauth-protected-resource/mcp", "seen": "2026-10-08" }, { "what": "webhooks", "url": "https://support.read.ai/hc/en-us/articles/16352415827219-Getting-Started-with-Webhooks", "seen": "2026-10-08" }, { "what": "workspace audit logs", "url": "https://support.read.ai/hc/en-us/articles/49590381021843-Workspace-Audit-Logs", "seen": "2026-10-08" }, { "what": "security and privacy overview", "url": "https://support.read.ai/hc/en-us/articles/25702259763091-Security-Privacy-Overview", "seen": "2026-10-08" }, { "what": "status incidents", "url": "https://readai.statuspage.io/api/v2/incidents.json", "seen": "2026-10-08" }, { "what": "plans and pricing", "url": "https://www.read.ai/plans-pricing", "seen": "2026-10-08" }, { "what": "terms of service", "url": "https://www.read.ai/termsofservice", "seen": "2026-10-08" }, { "what": "privacy policy", "url": "https://www.read.ai/privacy-policy", "seen": "2026-10-08" }, { "what": "security.txt", "url": "https://www.read.ai/.well-known/security.txt", "seen": "2026-10-08" }, { "what": "llms.txt", "url": "https://www.read.ai/llms.txt", "seen": "2026-10-08" }, { "what": "MCP launch post, 25 February 2026", "url": "https://www.read.ai/post/read-ai-mcp-your-meetings-just-became-your-most-powerful-dev-tool", "seen": "2026-10-08" }, { "what": "official MCP registry search, no result", "url": "https://registry.modelcontextprotocol.io/v0/servers?search=read.ai", "seen": "2026-10-08" }, { "what": "advance notice and opt-out of recording", "url": "https://support.read.ai/hc/en-us/articles/55230546830995", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: the MCP tool definitions, input schemas and annotations, which need a signed-in Read AI account", "unchecked: the Trust Centre at trust.read.ai (SOC 2 report, DPA, sub-processor list), which renders only with JavaScript", "unchecked: whether api.read.ai publishes an OpenAPI file. Requests to /openapi.json and /docs got no response", "No changelog was found, so lastRelease is the edit date of the MCP server help article (2 September 2026) and may not match the last server change", "The webhook article gives two retry figures, up to 5 retries per request in the FAQ and 25 tries in the main text", "The date when create meeting agent and share meeting report were added to the MCP server was not established", "No date was found for general availability of the API and MCP server" ] }, "negative": 0, "verdict": "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.", "bestFor": "An agent working for a person or team that already records meetings with Read AI and wants transcripts, summaries and action items in context.", "strengths": [ "The remote MCP server has four tools, covering list meetings, get meeting, create meeting agent and share meeting report", "The API and MCP server are open to every plan, including the free plan of five meeting transcripts a month with no card", "OAuth 2.1 with dynamic client registration, 10-minute access tokens, rotating single-use refresh tokens and a revocation endpoint", "Creating a meeting agent twice for one meeting returns the existing record, and re-sharing a report sends no duplicate invite", "Webhooks carry an HMAC SHA-256 signature in `X-Read-Signature` and a `request_id` for discarding duplicates" ], "weaknesses": [ "Both the REST API and the MCP server are labelled open beta, with no SLA and no deprecation policy found", "No static API keys or client credentials. A person signs in through a browser, and a broken refresh chain needs that person again", "No public OpenAPI file, changelog or official SDK was found. The reference is one help centre article", "List calls return at most 10 meetings a page, and the only filter is start time", "The bot can be sent to a meeting through MCP, but no tool removes it, reports its state or controls it during the call" ], "agentNotes": [ "Persist the new refresh token after every refresh. Access tokens expire after 10 minutes and each refresh token works once.", "Request only the fields needed with `expand[]` on the REST API. Transcripts and other expansions slow the response.", "Stay under 100 requests a minute per user and back off on 429. No Retry-After header is documented.", "Confirm with the user before calling create meeting agent or share meeting report. Sharing emails the recipient unless notify is set to no.", "Ask a workspace admin to enable Downloads in Reports \u0026 Sharing first. Without it the API and MCP server return nothing for workspace members." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.4 } ], "editorialScores": { "ergonomics": 63, "maintenance": 31, "payments": 30, "reliability": 52, "schema": 51, "security": 54, "transparency": 45 }, "provenanceScore": 81 }, "connect": { "http": "curl \"https://api.read.ai/v1/meetings?limit=5\u0026start_time_ms.gte=1733700000000\" \\\n -H \"Authorization: Bearer $READ_AI_ACCESS_TOKEN\" \\\n -H \"Accept: application/json\"" }, "letme": { "capability": "https://letme.dev/meetings.bot", "tool": "https://letme.dev/read-ai" }, "notable": [ "The MCP server is remote at https://api.read.ai/mcp over Streamable HTTP with OAuth 2.1, and is described as an open beta release (https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server)", "Four MCP tools are documented. Get meeting by id, list meetings, create meeting agent (Zoom, Google Meet and Microsoft Teams) and share meeting report (https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server)", "The REST API has three read endpoints, GET /v1/meetings, GET /v1/meetings/{id} and GET /v1/meetings/{id}/live, with eight expandable fields including transcript and recording_download (https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference)", "Known limitations listed by the vendor include no static API keys, 10-minute access tokens, a limit of 100 requests a minute per user and reported failures with some MCP clients such as VS Code and Notion (https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview)", "Webhooks push the report on meeting_end (and meeting_start for workspace webhooks), with up to 20 webhooks per user, on Pro plans and above (https://support.read.ai/hc/en-us/articles/16352415827219-Getting-Started-with-Webhooks)", "The status page lists a critical incident on 27 April 2026 named Issues with connecting to Read MCP/API Server, resolved in about 90 minutes (https://readai.statuspage.io/api/v2/incidents.json)", "www.read.ai/llms.txt points agents to the help centre's JSON API, which returns every article without authentication (https://www.read.ai/llms.txt)" ], "area": "voice", "details": [ { "label": "MCP server", "value": "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" }, { "label": "MCP tools", "value": "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)" }, { "label": "REST API", "value": "Base https://api.read.ai. GET /v1/meetings, GET /v1/meetings/{id}, GET /v1/meetings/{id}/live. Read-only. Open beta" }, { "label": "Expandable fields", "value": "summary, chapter_summaries, action_items, key_questions, topics, transcript, metrics, recording_download. The live endpoint expands only transcript and chapter_summaries" }, { "label": "Credentials", "value": "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" }, { "label": "Rate limits", "value": "100 requests a minute per user, HTTP 429 above that" }, { "label": "Pagination", "value": "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`" }, { "label": "Errors", "value": "HTTP status codes 400, 401, 403, 404, 422, 429 and 500 with one-line meanings. No error body schema is documented" }, { "label": "Webhooks", "value": "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" }, { "label": "Live data", "value": "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" }, { "label": "Not exposed", "value": "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" }, { "label": "Consent", "value": "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" }, { "label": "Audit", "value": "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" }, { "label": "Certifications", "value": "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" }, { "label": "Status", "value": "https://readai.statuspage.io (Atlassian Statuspage), with an API component and separate components for Zoom, Google Meet and Microsoft Teams meeting bots" }, { "label": "Data regions", "value": "United States by default. EU and Canada deployments announced 2 February 2026, arranged through sales" } ], "unitPrices": [ { "item": "Pro", "unit": "seat-month", "usd": 15, "note": "billed annually, $19.75 billed monthly" }, { "item": "Enterprise", "unit": "seat-month", "usd": 22.5, "note": "billed annually, $29.75 billed monthly" }, { "item": "Enterprise+", "unit": "seat-month", "usd": 29.75, "note": "billed annually, $39.75 billed monthly, five or more licences" } ], "provenance": { "legalEntity": "Read AI, Inc.", "domain": "read.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://www.read.ai/termsofservice", "privacy": "https://www.read.ai/privacy-policy", "statusPage": "https://readai.statuspage.io", "changelog": "", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The terms of service (last updated 26 February 2026) name Read AI, Inc., 999 Third Ave, Suite 3300, Seattle, WA 98104.", "The privacy policy was last updated on 29 June 2026.", "The REST API and MCP server answer at api.read.ai and the authorisation server at authn.read.ai, both read.ai subdomains.", "www.read.ai/.well-known/security.txt is RFC 9116 format, expires 18 August 2027 and names vulnerabilities@read.ai and trust.read.ai.", "RDAP for read.ai gives a registration date of 2017-12-16 and a transfer on 2021-01-12.", "No changelog for the API or MCP server was found. The dates used are the help centre articles' own edit dates.", "The Trust Centre at trust.read.ai is a Vanta page that renders only with JavaScript, so its documents and sub-processor list were not read." ], "score": 81, "checks": [ { "check": "Legal entity named", "value": "Read AI, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "read.ai, registered 2017-12-16 (8 years)", "points": 11, "max": 15, "state": "part" }, { "check": "Endpoint on the vendor's domain", "value": "api.read.ai", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points", "points": 5.1, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 8 of the 8 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "readai.statuspage.io", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://www.read.ai/termsofservice", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-02-26", "words": 11129, "points": 5.1, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last Updated: February 26, 2026", "says": "Last updated 2026-02-26" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "Any dispute arising from these Terms and your use of our Services will be governed by and construed and enforced in accordance with the laws of the State of Washington, except to the extent preempted by U.S.", "says": "The law of the State of Washington" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "(b) In any event, the total liability of Read AI and the other Read AI Parties for any claim arising out of or relating to these Terms or our Services, regardless of the form of the action, is limited to $100 USD.", "says": "Capped at $100" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "…to charge your account as authorized by you when you enrolled in a Recurring Subscription, Read AI may in its sole discretion (i) bill you for your Services and suspend your access to the Services until payment is received, or (ii) seek to update your account information through third-party sources (i.e., your bank or…" }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "If we make changes, we will provide you with notice of such changes, such as by sending an email, providing a notice through our Services, or updating the date at the top of these Terms.", "says": "Says it gives notice of a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "In order for us to provide our Services, you agree that we may process, transfer, and store information about you in the United States and other countries, where you may not have the same rights and protections as you do under local law." }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "training.optout", "label": "Says it may use customer content to train or improve models, and gives an opt-out", "found": true, "quote": "…limitations described in our Privacy Policy and any applicable opt-in or opt-out mechanisms, Read AI may use your User Content to train, develop, and improve its artificial intelligence and machine learning technologies (\"AI/ML Models\")." }, { "key": "terms.automated", "label": "Restricts automated access", "found": true, "quote": "Use any data mining, robots or similar data-gathering or extraction methods designed to scrape or extract data from our Services except in accordance with instructions contained in our robot.txt file and only to compile search results", "costsPoints": true }, { "key": "terms.nonotice", "label": "Says the terms or the service can change without notice", "found": true, "quote": "Read AI reserves the right, including without prior notice, to limit the available quantity of or discontinue making available any Service;", "costsPoints": true }, { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "We reserve the right, without prior notice, to refuse service to any customer or reject any order at any time and refund any money you have paid for such order." }, { "key": "terms.arbitration", "label": "Requires arbitration or waives class actions", "found": true, "quote": "PLEASE READ THESE TERMS CAREFULLY, INCLUDING THE MANDATORY ARBITRATION PROVISION IN SECTION 16 WHICH REQUIRES THAT DISPUTES BE RESOLVED BY FINAL AND BINDING ARBITRATION ON AN INDIVIDUAL BASIS, NOT A CLASS-WIDE OR CONSOLIDATED BASIS." } ], "notes": [ { "date": "2026-10-08", "text": "Total liability for any claim is limited to 100 US dollars.", "quote": "In any event, the total liability of Read AI and the other Read AI Parties for any claim arising out of or relating to these Terms or our Services, regardless of the form of the action, is limited to $100 USD." }, { "date": "2026-10-08", "text": "Read AI disclaims all liability for actions its agentic functions take on the user's behalf, including the consequences of those actions.", "quote": "Read AI expressly disclaims all liability arising out of or related to actions taken by Agentic Features, including but not limited to any consequences resulting from such actions." }, { "date": "2026-10-08", "text": "A subscription that is not cancelled renews automatically at the price current at renewal, for the same length as the first term.", "quote": "If you do not cancel, your Recurring Subscription will automatically renew at the then-current price at the time of renewal and for the same duration as the initial subscription term" } ] }, { "kind": "privacy", "url": "https://www.read.ai/privacy-policy", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-06-29", "words": 6348, "points": 10, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last Updated: June 29, 2026", "says": "Last updated 2026-06-29" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "The information we collect about you depends on how you interact with us or use our Sites and Services." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "We store your audio and video information, including information derived therefrom, in accordance with our internal policies, but in no case for longer than 2 years.", "says": "Names a period of 2 years" }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "For information on how third parties that integrate our Services use your information, please review the third parties’ disclosures." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "In order to advertise our Services to you and better understand, improve, and personalize our interactions with you, we share and sell the following categories of personal information to the following categories of third parties:" }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "These include the right to access, rectify or delete your personal data, the right to request a restriction of processing or object to our processing of your personal data, and the right to request data portability." }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "Requests to opt out of such uses or disclosures of Personal Data should be sent to us privacy@read.ai.", "says": "privacy@read.ai" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "Data Privacy Frameworks and the UK Extension to the EU-U.S.", "says": "Relies on the Data Privacy Framework" } ], "toKnow": [ { "key": "training.optout", "label": "Says it may use customer content to train or improve models, and gives an opt-out", "found": true, "quote": "Provide, maintain, and improve (consistent with your account settings) our Services, including maintaining user accounts with us and using information to train and improve our models within our Services;" }, { "key": "privacy.sells", "label": "Says it sells personal data or shares it for advertising", "found": true, "quote": "Some of our advertising and analytics activities may constitute “sharing” or “selling” or use of personal information for “targeted advertising” under certain State Privacy Laws." } ], "notes": [ { "date": "2026-10-08", "text": "Google Workspace data collected through a connected Google account may be passed to third party AI tools.", "quote": "Any user data collected via Google Workspace APIs may be transferred to third party AI tools in connection with the Services." }, { "date": "2026-10-08", "text": "Read AI infers demographic characteristics of users from audio, video and language, and uses them to improve its models.", "quote": "Demographics: We also use audio and visual information, as well as other information like language, to infer certain demographic characteristics about users, which we use to improve our models and increase the accuracy of their output." } ] } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/read-ai.json", "live": { "slug": "read-ai", "probe": { "target": "https://api.read.ai/mcp", "method": "mcp-initialize", "lastAt": "2026-10-08T19:08:56.697595719Z", "lastOk": true, "lastStatus": 401, "lastMs": 265, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 256, "p95ms24h": 283, "samples24h": 42, "samples30d": 42, "days": [ { "date": "2026-10-08", "probes": 42, "ok": 42 } ] }, "vendorStatus": { "page": "https://readai.statuspage.io", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-08T19:06:57.316694134Z" }, "securityTxt": { "url": "https://read.ai/.well-known/security.txt", "state": "valid", "expires": "2027-08-18T00:00:00.000Z", "checkedAt": "2026-10-08T15:38:31.550067753Z" }, "pages": [ { "url": "https://www.read.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:29:50.104562884Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "21db8189c8d4" }, { "url": "https://www.read.ai/termsofservice", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:29:52.153406668Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "51a9251fff6d" } ], "updatedAt": "2026-10-08T19:08:56.697595719Z" } }, "verify": { "accepts": "a page on read.ai or one of its subdomains", "badgeUrl": "https://www.anchorterminal.com/badges/read-ai.svg", "body": { "slug": "read-ai", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/read-ai", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/read-ai\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/read-ai.svg\" alt=\"Read AI on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Read AI on Anchor Terminal](https://www.anchorterminal.com/badges/read-ai.svg)](https://www.anchorterminal.com/tools/read-ai)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/read-ai\"\u003eRead AI on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/read-ai", "json": "https://www.anchorterminal.com/tools/read-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/read-ai.md", "slim": "https://www.anchorterminal.com/tools/read-ai.min.md" }, "markdown": "## Overview\n\n**Grade D · 50.4/100 · rank #517 of 629 · #5 in Meeting capture \u0026 meeting infrastructure · not agent-ready · confidence medium**\n\n\n## Assessment\n\nFour 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.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Read AI, Inc. (https://www.read.ai) |\n| Kind | MCP server |\n| Category | Meeting capture \u0026 meeting infrastructure (https://www.anchorterminal.com/categories/meeting-capture) |\n| Transport | Streamable HTTP, HTTP |\n| Endpoint | `https://api.read.ai/mcp` |\n| Auth | OAuth · OAuth 2.1 only, with a browser sign-in to a Read AI account. A client registers itself at https://api.read.ai/oauth/register (dynamic client registration) and runs the authorisation code grant with PKCE against authn.read.ai. Scopes are `meeting:read` for the REST API and `mcp:execute` for the MCP server. Access tokens last 10 minutes and refresh tokens are single-use and rotate. Static API keys and client credentials are not supported in the beta. Workspace members need the Downloads setting enabled by an admin, and a token reaches only the reports its user can open. |\n| Pricing | Freemium ($15 / seat-mo) · The API and MCP server are available on every plan, including Free (5 meeting transcripts a month, no card). Paid plans billed annually are Pro at $15, Enterprise at $22.50 and Enterprise+ at $29.75 a user a month ($19.75, $29.75 and $39.75 billed monthly). Enterprise+ needs five or more licences. Webhooks need Pro or above, and recording playback needs Enterprise or above. No per-call charge is published (checked 2026-10-08). |\n| x402 | No · No x402, MPP or L402 in the API reference, the MCP server article, the overview or the pricing page (checked 2026-10-08). |\n| Licence | Proprietary service under Read AI's terms of service |\n| Tools exposed | 4 |\n| Docs | https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview |\n| llms.txt | https://www.read.ai/llms.txt |\n| Last release | 2026-09-02 |\n| 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 |\n| 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) |\n| REST API | Base https://api.read.ai. GET /v1/meetings, GET /v1/meetings/{id}, GET /v1/meetings/{id}/live. Read-only. Open beta |\n| Expandable fields | summary, chapter_summaries, action_items, key_questions, topics, transcript, metrics, recording_download. The live endpoint expands only transcript and chapter_summaries |\n| 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 |\n| Rate limits | 100 requests a minute per user, HTTP 429 above that |\n| 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` |\n| Errors | HTTP status codes 400, 401, 403, 404, 422, 429 and 500 with one-line meanings. No error body schema is documented |\n| 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 |\n| 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 |\n| 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 |\n| 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 |\n| 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 |\n| 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 |\n| Status | https://readai.statuspage.io (Atlassian Statuspage), with an API component and separate components for Zoom, Google Meet and Microsoft Teams meeting bots |\n| Data regions | United States by default. EU and Canada deployments announced 2 February 2026, arranged through sales |\n| Capabilities | meetings.bot, meetings.transcript, meetings.summary, meetings.recording |\n| Tags | official, hosted, mcp, oauth, closed-source, beta, no-card, llms-txt, webhooks, status-page, soc2 |\n| JSON | https://www.anchorterminal.com/api/v1/tools/read-ai.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 52 | 10.4 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 51 | 8.3 |\n| Agent ergonomics | 13% | 16.2 | 63 | 10.2 |\n| Security \u0026 auth | 14% | 17.5 | 54 | 9.4 |\n| Payments \u0026 pricing | 10% | 12.5 | 30 | 3.8 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 31 | 2.7 |\n| Transparency \u0026 trust (editorial 45, provenance 81) | 7% | 8.8 | 63 | 5.5 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **50.4 → D** |\n\n### Why each score\n\n- Reliability 52: Graded as a hosted service on the MCP server and REST API. Statuspage at readai.statuspage.io with an API component and per-platform bot components (20). From 10 July to 8 October 2026 the API component has no incident. The bots have one critical incident (Zoom meetings not joined, 3 August, about three hours) and one major (23 July, under an hour), and Ask Read, which the API doesn't expose, has two majors (10). 100 requests a minute per user (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 (7). No SLA found (0). Both surfaces are open beta (0).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 51: No public OpenAPI file was found, and requests to api.read.ai/openapi.json and /docs got no response. The MCP tool schemas sit behind sign-in and were not read, so 5 of 25 for the published parameter tables. www.read.ai/llms.txt points to a help centre JSON API that returns every article (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).\n- Agent ergonomics 63: 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 bare HTTP status codes with one-line meanings, though the 401 from the MCP endpoint carries a clear recovery message (8). 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).\n- Security \u0026 auth 54: 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).\n- Payments \u0026 pricing 30: 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).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 31: No changelog or release list was found, so dates come from the help centre. The MCP server article was last edited on 2 September 2026, 36 days before the check (20). Connection guides for Claude, ChatGPT and Microsoft Copilot Studio were published between 25 and 27 August 2026, which are documents and not dated releases (5 of 20). A support request form and a status page updated through October, no public changelog or developer forum found (6). Not in the official MCP registry on a search for read.ai, read-ai and readai, and no official SDK (0). No packages to assess (0).\n- Transparency \u0026 trust 63: Closed service with published terms, last updated 26 February 2026 (15). The privacy policy of 29 June 2026 keeps audio and video for no longer than two years and paid accounts' data until payment stops or deletion is requested. The help centre says model training is opt-in, while the terms grant a licence to train subject to opt-in or opt-out settings, and the DPA sits in a Trust Centre we couldn't read (20). No deprecation policy for the beta API (0). A sub-processor list is linked at trust.read.ai/subprocessors but didn't render for us, and EU and Canada data regions were announced on 2 February 2026 (10).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (17 items): https://www.anchorterminal.com/fixes/read-ai.md (JSON https://www.anchorterminal.com/fixes/read-ai.json)\n\n### What we couldn't check\n\n- unchecked: the MCP tool definitions, input schemas and annotations, which need a signed-in Read AI account\n- unchecked: the Trust Centre at trust.read.ai (SOC 2 report, DPA, sub-processor list), which renders only with JavaScript\n- unchecked: whether api.read.ai publishes an OpenAPI file. Requests to /openapi.json and /docs got no response\n- No changelog was found, so lastRelease is the edit date of the MCP server help article (2 September 2026) and may not match the last server change\n- The webhook article gives two retry figures, up to 5 retries per request in the FAQ and 25 tries in the main text\n- The date when create meeting agent and share meeting report were added to the MCP server was not established\n- No date was found for general availability of the API and MCP server\n\n### Sources\n\n- API and MCP overview, prerequisites and known limitations: \u003chttps://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview\u003e (seen 2026-10-08)\n- MCP server details and tools: \u003chttps://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server\u003e (seen 2026-10-08)\n- REST API reference: \u003chttps://support.read.ai/hc/en-us/articles/49381161088659-API-Reference\u003e (seen 2026-10-08)\n- OAuth flow and token lifetimes: \u003chttps://support.read.ai/hc/en-us/articles/49380809380371-API-Keys-Authentication\u003e (seen 2026-10-08)\n- OAuth authorisation server metadata: \u003chttps://authn.read.ai/.well-known/oauth-authorization-server\u003e (seen 2026-10-08)\n- MCP protected resource metadata: \u003chttps://api.read.ai/.well-known/oauth-protected-resource/mcp\u003e (seen 2026-10-08)\n- webhooks: \u003chttps://support.read.ai/hc/en-us/articles/16352415827219-Getting-Started-with-Webhooks\u003e (seen 2026-10-08)\n- workspace audit logs: \u003chttps://support.read.ai/hc/en-us/articles/49590381021843-Workspace-Audit-Logs\u003e (seen 2026-10-08)\n- security and privacy overview: \u003chttps://support.read.ai/hc/en-us/articles/25702259763091-Security-Privacy-Overview\u003e (seen 2026-10-08)\n- status incidents: \u003chttps://readai.statuspage.io/api/v2/incidents.json\u003e (seen 2026-10-08)\n- plans and pricing: \u003chttps://www.read.ai/plans-pricing\u003e (seen 2026-10-08)\n- terms of service: \u003chttps://www.read.ai/termsofservice\u003e (seen 2026-10-08)\n- privacy policy: \u003chttps://www.read.ai/privacy-policy\u003e (seen 2026-10-08)\n- security.txt: \u003chttps://www.read.ai/.well-known/security.txt\u003e (seen 2026-10-08)\n- llms.txt: \u003chttps://www.read.ai/llms.txt\u003e (seen 2026-10-08)\n- MCP launch post, 25 February 2026: \u003chttps://www.read.ai/post/read-ai-mcp-your-meetings-just-became-your-most-powerful-dev-tool\u003e (seen 2026-10-08)\n- official MCP registry search, no result: \u003chttps://registry.modelcontextprotocol.io/v0/servers?search=read.ai\u003e (seen 2026-10-08)\n- advance notice and opt-out of recording: \u003chttps://support.read.ai/hc/en-us/articles/55230546830995\u003e (seen 2026-10-08)\n\n## Who's behind it (provenance 81/100, checked 2026-10-08)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Read AI, Inc. | 20/20 |\n| Domain age | read.ai, registered 2017-12-16 (8 years) | 11/15 |\n| Endpoint on the vendor's domain | api.read.ai | 15/15 |\n| Terms of service | read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points | 5.1/10 |\n| Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 |\n| Status page | readai.statuspage.io | 10/10 |\n| Changelog | not found | 0/10 |\n| security.txt | valid | 10/10 |\n\nThe terms of service (last updated 26 February 2026) name Read AI, Inc., 999 Third Ave, Suite 3300, Seattle, WA 98104.\n\nThe privacy policy was last updated on 29 June 2026.\n\nThe REST API and MCP server answer at api.read.ai and the authorisation server at authn.read.ai, both read.ai subdomains.\n\nwww.read.ai/.well-known/security.txt is RFC 9116 format, expires 18 August 2027 and names vulnerabilities@read.ai and trust.read.ai.\n\nRDAP for read.ai gives a registration date of 2017-12-16 and a transfer on 2021-01-12.\n\nNo changelog for the API or MCP server was found. The dates used are the help centre articles' own edit dates.\n\nThe Trust Centre at trust.read.ai is a Vanta page that renders only with JavaScript, so its documents and sub-processor list were not read.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://www.read.ai/termsofservice), read 2026-10-08, dated 2026-02-26, states 6 of the 7 things a reader expects.\n\n- To know. Says it may use customer content to train or improve models, and gives an opt-out. \"…limitations described in our Privacy Policy and any applicable opt-in or opt-out mechanisms, Read AI may use your User Content to train, develop, and improve its artificial intelligence and machine learning technologies (\"AI/ML Models\").\"\n- To know. Restricts automated access (costs points). \"Use any data mining, robots or similar data-gathering or extraction methods designed to scrape or extract data from our Services except in accordance with instructions contained in our robot.txt file and only to compile search results\"\n- To know. Says the terms or the service can change without notice (costs points). \"Read AI reserves the right, including without prior notice, to limit the available quantity of or discontinue making available any Service;\"\n- To know. Says access can be ended without notice or for any reason. \"We reserve the right, without prior notice, to refuse service to any customer or reject any order at any time and refund any money you have paid for such order.\"\n- To know. Requires arbitration or waives class actions. \"PLEASE READ THESE TERMS CAREFULLY, INCLUDING THE MANDATORY ARBITRATION PROVISION IN SECTION 16 WHICH REQUIRES THAT DISPUTES BE RESOLVED BY FINAL AND BINDING ARBITRATION ON AN INDIVIDUAL BASIS, NOT A CLASS-WIDE OR CONSOLIDATED BASIS.\"\n- Gives the date it was last updated. Last updated 2026-02-26.\n- Names the governing law or courts. The law of the State of Washington.\n- States a limit on its liability. Capped at $100.\n- Says how changes to the terms are announced. Says it gives notice of a change.\n- Not found in the text. Refers to a service level or uptime commitment.\n- Also in the text (2026-10-08). Total liability for any claim is limited to 100 US dollars. \"In any event, the total liability of Read AI and the other Read AI Parties for any claim arising out of or relating to these Terms or our Services, regardless of the form of the action, is limited to $100 USD.\"\n- Also in the text (2026-10-08). Read AI disclaims all liability for actions its agentic functions take on the user's behalf, including the consequences of those actions. \"Read AI expressly disclaims all liability arising out of or related to actions taken by Agentic Features, including but not limited to any consequences resulting from such actions.\"\n- Also in the text (2026-10-08). A subscription that is not cancelled renews automatically at the price current at renewal, for the same length as the first term. \"If you do not cancel, your Recurring Subscription will automatically renew at the then-current price at the time of renewal and for the same duration as the initial subscription term\"\n\n**Privacy policy** (https://www.read.ai/privacy-policy), read 2026-10-08, dated 2026-06-29, states 8 of the 8 things a reader expects.\n\n- To know. Says it may use customer content to train or improve models, and gives an opt-out. \"Provide, maintain, and improve (consistent with your account settings) our Services, including maintaining user accounts with us and using information to train and improve our models within our Services;\"\n- To know. Says it sells personal data or shares it for advertising. \"Some of our advertising and analytics activities may constitute “sharing” or “selling” or use of personal information for “targeted advertising” under certain State Privacy Laws.\"\n- Gives the date it was last updated. Last updated 2026-06-29.\n- Says how long data is kept. Names a period of 2 years.\n- Gives a privacy contact. privacy@read.ai.\n- Says where data is transferred or stored. Relies on the Data Privacy Framework.\n- Also in the text (2026-10-08). Google Workspace data collected through a connected Google account may be passed to third party AI tools. \"Any user data collected via Google Workspace APIs may be transferred to third party AI tools in connection with the Services.\"\n- Also in the text (2026-10-08). Read AI infers demographic characteristics of users from audio, video and language, and uses them to improve its models. \"Demographics: We also use audio and visual information, as well as other information like language, to infer certain demographic characteristics about users, which we use to improve our models and increase the accuracy of their output.\"\n\n## Live (updated 2026-10-08 19:08 UTC)\n\n- Right now: up, HTTP 401, 265 ms, checked 2026-10-08 19:08 UTC (mcp-initialize on `https://api.read.ai/mcp`, asks for auth)\n- Uptime 24h 100.0% (42 probes) · 30 days 100.0% (42 probes) · p50 256 ms · p95 283 ms\n- Vendor status page: none, All Systems Operational\n- security.txt: valid, expires 2027-08-18T00:00:00.000Z\n- Watching privacy \u003chttps://www.read.ai/privacy-policy\u003e\n- Watching terms \u003chttps://www.read.ai/termsofservice\u003e\n- Always current: https://www.anchorterminal.com/api/v1/live/read-ai.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Pro | $15 | per seat per month | billed annually, $19.75 billed monthly |\n| Enterprise | $22.50 | per seat per month | billed annually, $29.75 billed monthly |\n| Enterprise+ | $29.75 | per seat per month | billed annually, $39.75 billed monthly, five or more licences |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- The remote MCP server has four tools, covering list meetings, get meeting, create meeting agent and share meeting report\n- The API and MCP server are open to every plan, including the free plan of five meeting transcripts a month with no card\n- OAuth 2.1 with dynamic client registration, 10-minute access tokens, rotating single-use refresh tokens and a revocation endpoint\n- Creating a meeting agent twice for one meeting returns the existing record, and re-sharing a report sends no duplicate invite\n- Webhooks carry an HMAC SHA-256 signature in `X-Read-Signature` and a `request_id` for discarding duplicates\n\n## Weaknesses\n\n- Both the REST API and the MCP server are labelled open beta, with no SLA and no deprecation policy found\n- No static API keys or client credentials. A person signs in through a browser, and a broken refresh chain needs that person again\n- No public OpenAPI file, changelog or official SDK was found. The reference is one help centre article\n- List calls return at most 10 meetings a page, and the only filter is start time\n- The bot can be sent to a meeting through MCP, but no tool removes it, reports its state or controls it during the call\n\n## Before you call it (notes for agents)\n\n1. Persist the new refresh token after every refresh. Access tokens expire after 10 minutes and each refresh token works once.\n2. Request only the fields needed with `expand[]` on the REST API. Transcripts and other expansions slow the response.\n3. Stay under 100 requests a minute per user and back off on 429. No Retry-After header is documented.\n4. Confirm with the user before calling create meeting agent or share meeting report. Sharing emails the recipient unless notify is set to no.\n5. Ask a workspace admin to enable Downloads in Reports \u0026 Sharing first. Without it the API and MCP server return nothing for workspace members.\n\n## Connect\n\nFirst request:\n\n```bash\ncurl \"https://api.read.ai/v1/meetings?limit=5\u0026start_time_ms.gte=1733700000000\" \\\n -H \"Authorization: Bearer $READ_AI_ACCESS_TOKEN\" \\\n -H \"Accept: application/json\"\n```\n\nThrough letme (picks today, calling later): https://letme.dev/read-ai. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Fireflies.ai | C | 60.6 | 347 | meetings.transcript, meetings.summary, meetings.recording, meetings.bot | no | https://www.anchorterminal.com/tools/fireflies.md |\n| Meeting BaaS | B | 62 | 312 | meetings.bot, meetings.transcript, meetings.recording | no | https://www.anchorterminal.com/tools/meeting-baas.md |\n| Recall.ai | C | 59.5 | 378 | meetings.bot, meetings.recording, meetings.transcript | no | https://www.anchorterminal.com/tools/recall-ai.md |\n| tl;dv | D | 51 | 512 | meetings.transcript, meetings.summary, meetings.recording | no | https://www.anchorterminal.com/tools/tldv.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- The MCP server is remote at https://api.read.ai/mcp over Streamable HTTP with OAuth 2.1, and is described as an open beta release (source: \u003chttps://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server\u003e)\n- Four MCP tools are documented. Get meeting by id, list meetings, create meeting agent (Zoom, Google Meet and Microsoft Teams) and share meeting report (source: \u003chttps://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server\u003e)\n- The REST API has three read endpoints, GET /v1/meetings, GET /v1/meetings/{id} and GET /v1/meetings/{id}/live, with eight expandable fields including transcript and recording_download (source: \u003chttps://support.read.ai/hc/en-us/articles/49381161088659-API-Reference\u003e)\n- Known limitations listed by the vendor include no static API keys, 10-minute access tokens, a limit of 100 requests a minute per user and reported failures with some MCP clients such as VS Code and Notion (source: \u003chttps://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview\u003e)\n- Webhooks push the report on meeting_end (and meeting_start for workspace webhooks), with up to 20 webhooks per user, on Pro plans and above (source: \u003chttps://support.read.ai/hc/en-us/articles/16352415827219-Getting-Started-with-Webhooks\u003e)\n- The status page lists a critical incident on 27 April 2026 named Issues with connecting to Read MCP/API Server, resolved in about 90 minutes (source: \u003chttps://readai.statuspage.io/api/v2/incidents.json\u003e)\n- www.read.ai/llms.txt points agents to the help centre's JSON API, which returns every article without authentication (source: \u003chttps://www.read.ai/llms.txt\u003e)\n\n## Compare\n\n- [Fireflies.ai vs Read AI](https://www.anchorterminal.com/compare/fireflies-vs-read-ai.md): C 60.6 vs D 50.4\n- [Read AI vs tl;dv](https://www.anchorterminal.com/compare/read-ai-vs-tldv.md): D 50.4 vs D 51\n- [Meeting BaaS vs Read AI](https://www.anchorterminal.com/compare/meeting-baas-vs-read-ai.md): B 62 vs D 50.4\n- [Read AI vs Recall.ai](https://www.anchorterminal.com/compare/read-ai-vs-recall-ai.md): D 50.4 vs C 59.5\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on read.ai or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"read-ai\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/read-ai\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/read-ai.svg\" alt=\"Read AI on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Read AI on Anchor Terminal](https://www.anchorterminal.com/badges/read-ai.svg)](https://www.anchorterminal.com/tools/read-ai)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/read-ai\"\u003eRead AI on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Read AI is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/read-ai-dark.png\n- Light: https://www.anchorterminal.com/assets/share/read-ai-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Meeting capture \u0026 meeting infrastructure", "url": "https://www.anchorterminal.com/categories/meeting-capture" }, { "name": "Read AI", "url": "" } ], "description": "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.", "facts": [ "rank #517 of 629", "OAuth auth", "0 desk reviews" ], "h1": "Read AI", "image": "https://www.anchorterminal.com/assets/og/tools-read-ai.png", "path": "/tools/read-ai", "published": "2026-10-01", "section": "tools", "title": "Read AI review for AI agents, grade D (50.4/100) | Anchor Terminal", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/tools/read-ai" }, "tokens": { "markdown": 7450, "slim": 1930 }, "version": 1 }