Read AI is an AI-powered meeting intelligence platform that joins Zoom, Microsoft Teams and Google Meet calls as an authorized notetaker and turns them into structured meeting reports — summaries, chapter summaries, action items, key questions, topics, full speaker-attributed transcripts and engagement metrics — plus enterprise search across email, messaging and calendar. Founded in 2021 in Seattle by the team behind Placed and Foursquare, it reports more than five million monthly active users. For developers, Read AI ships an open-beta public REST API at api.read.ai (v1 meetings, live meetings, cursor pagination, expandable fields), a remote Model Context Protocol server at api.read.ai/mcp listed in the Anthropic and ChatGPT connector directories, HMAC-signed user and workspace webhooks, three provider-authored downloadable Agent Skills, and an OAuth 2.1 authorization server with dynamic client registration. It publishes no OpenAPI.
Read AI is listed with 2 APIs on the APIs.io network. Tagged areas include Company, Meeting Intelligence, Artificial Intelligence, Transcription, and Productivity.
The Read AI catalog on APIs.io includes 1 event-driven AsyncAPI specification.
Read AI’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, pricing, signup flow, and 25 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/read-ai/"><img src="https://apis.io/badge/read-ai/card.svg" alt="Read AI on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card+8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Request/Response Examples+7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
Documented Reversibility+6 pts — a reversal operation in the contract, graded up when a window is documented too
Agentic Commerce Well-Known Document+5 pts — a parsing /.well-known/ucp.json or acp.json declaring a version and at least one service, OR (0.27) a live x402 payment challenge from _data/x402-adoption.json — `self` when its endpoints are on the provider's own domain, `platform` when they are on a vendor's
3 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
Open-beta public REST API for programmatic access to a user's Read AI meeting data. Three documented meeting endpoints — list meetings with cursor pagination and epoch-milliseco...
First-party remote Model Context Protocol server exposing a user's Read AI meeting reports to any MCP client over Streamable HTTP. Two published tools — list_meetings and get_me...
Read AI operates a first-party remote MCP server that exposes a user's meeting reports — metadata, participants, summaries, chapter summaries, action items, key questions, topic...
aid: read-ai
name: Read AI
description: Read AI is an AI-powered meeting intelligence platform that joins Zoom, Microsoft Teams and Google Meet calls
as an authorized notetaker and turns them into structured meeting reports — summaries, chapter summaries, action items,
key questions, topics, full speaker-attributed transcripts and engagement metrics — plus enterprise search across email,
messaging and calendar. Founded in 2021 in Seattle by the team behind Placed and Foursquare, it reports more than five million
monthly active users. For developers, Read AI ships an open-beta public REST API at api.read.ai (v1 meetings, live meetings,
cursor pagination, expandable fields), a remote Model Context Protocol server at api.read.ai/mcp listed in the Anthropic
and ChatGPT connector directories, HMAC-signed user and workspace webhooks, three provider-authored downloadable Agent Skills,
and an OAuth 2.1 authorization server with dynamic client registration. It publishes no OpenAPI.
url: https://raw.githubusercontent.com/api-evangelist/read-ai/refs/heads/main/apis.yml
deliveryModel:
model: saas
open_source: false
commercial: true
callable_host: false
label: Hosted service · you call their endpoint
confidence: medium
source:
- pricing
generated: '2026-08-28'
method: derived
accessModel:
pricing: freemium
onboarding: self-serve
trial: false
try_now: true
public: false
gated: none
gated_source:
- onboarding
label: Freemium · Self-serve signup
confidence: high
source:
- plans
- authentication
- scopes
- rate-limits
- security
generated: '2026-11-06'
method: derived
image: https://kinlane-productions2.s3.amazonaws.com/apis-json/apis-json-logo.jpg
x-type: company
x-source: harvest:secondary-market
specificationVersion: '0.23'
created: '2026-08-05'
modified: '2026-08-05'
tags:
- Company
- Meeting Intelligence
- Artificial Intelligence
- Transcription
- Productivity
- Collaboration
- MCP
- Agents
- Webhook
- Software-as-a-Service
tags_raw:
- Company
- Meeting Intelligence
- Artificial Intelligence
- Transcription
- Productivity
- Collaboration
- Model Context Protocol
- Agents
- Webhooks
- SaaS
apis:
- name: Read AI REST API
description: Open-beta public REST API for programmatic access to a user's Read AI meeting data. Three documented meeting
endpoints — list meetings with cursor pagination and epoch-millisecond time filters, retrieve a meeting by ULID, and retrieve
live data for an in-progress meeting — plus an expand[] projection covering summary, chapter_summaries, action_items,
key_questions, topics, transcript, metrics and recording_download. Read-only; every documented operation is a GET. Bearer-token
authenticated via OAuth 2.1 with dynamic client registration.
humanURL: https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference
baseURL: https://api.read.ai/
image: https://kinlane-productions2.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- Meetings
- Transcription
- Meeting Intelligence
- REST
properties:
- type: Documentation
url: https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference
- type: APIReference
url: https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference
- type: GettingStarted
url: https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview
- type: Authentication
url: authentication/read-ai-authentication.yml
- type: OAuthScopes
url: scopes/read-ai-scopes.yml
- type: ErrorCatalog
url: errors/read-ai-problem-types.yml
- type: RateLimits
url: rate-limits/read-ai-rate-limits.yml
- type: Conventions
url: conventions/read-ai-conventions.yml
- type: DataModel
url: data-model/read-ai-data-model.yml
x-evidence:
verified: '2026-08-05'
docs_describe: Method + path, query parameters, request examples, response examples, pagination contract and an error-code
table for GET /v1/meetings, GET /v1/meetings/{id} and GET /v1/meetings/{id}/live.
endpoint_check: GET https://api.read.ai/v1/meetings -> 401 {"detail":"Not authenticated"}
openapi: None published. /openapi.json, /docs and /redoc are 301-redirected by the ALB to https://www.read.ai/; /openapi.yaml,
/swagger.json, /v1/openapi.json, /api-docs return {"detail":"Not Found"}.
- name: Read AI MCP Server
description: First-party remote Model Context Protocol server exposing a user's Read AI meeting reports to any MCP client
over Streamable HTTP. Two published tools — list_meetings and get_meeting_by_id — return meeting metadata, participants,
summaries, chapter summaries, action items, key questions, topics, full transcripts, metrics and a recording download
URL. Listed in the Anthropic connector directory and the ChatGPT app directory; protected by OAuth 2.1 with RFC 9728 protected-resource
metadata and the mcp:execute and meeting:read scopes.
humanURL: https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server
baseURL: https://api.read.ai/mcp
image: https://kinlane-productions2.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
- MCP
- Agents
- Meetings
tags_raw:
- Model Context Protocol
- Agents
- Meetings
properties:
- type: MCPServer
url: mcp/read-ai-mcp.yml
- type: ToolCrosswalk
url: mcp/read-ai-tool-crosswalk.yml
- type: Documentation
url: https://support.read.ai/hc/en-us/articles/49381158409491-MCP-Server
- type: Authentication
url: authentication/read-ai-authentication.yml
x-evidence:
verified: '2026-08-05'
docs_describe: Server URI, transport, OAuth 2.1 authentication, compatible clients, and the two available tools with the
data each returns.
endpoint_check: 'POST https://api.read.ai/mcp (initialize) -> 401 invalid_token with WWW-Authenticate resource_metadata=
https://api.read.ai/.well-known/oauth-protected-resource/mcp (server: uvicorn)'
tools_list: OAuth-gated; tool names taken from Read AI's own published skill bundles.
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
- FN: APIs.json
email: info@apis.io
common:
- type: DomainSecurity
url: security/read-ai-domain-security.yml
- type: Website
url: https://www.read.ai/
- type: DeveloperPortal
url: https://support.read.ai/hc/en-us/sections/49378920415891-API-and-MCP
- type: Documentation
url: https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference
- type: APIReference
url: https://support.read.ai/hc/en-us/articles/49381161088659-API-Reference
- type: GettingStarted
url: https://support.read.ai/hc/en-us/articles/49379985941523-Read-AI-API-and-MCP-Overview
- type: Support
url: https://support.read.ai/hc/en-us
- type: Blog
url: https://www.read.ai/blog
- type: GitHubOrganization
url: https://github.com/Read-AI-Inc
- type: Pricing
url: https://www.read.ai/plans-pricing
- type: SignUp
url: https://app.read.ai/
- type: TermsOfService
url: https://www.read.ai/tos
- type: PrivacyPolicy
url: https://www.read.ai/privacy-policy
- type: TrustCenter
url: security/read-ai-trust-center.yml
- type: Compliance
url: https://support.read.ai/hc/en-us/articles/25702259763091-Security-Privacy-Overview
- type: StatusPage
url: https://status.read.ai/
- type: Integrations
url: https://www.read.ai/integrations
- type: LLMsTxt
url: llms/read-ai-llms.txt
- type: WellKnown
url: well-known/read-ai-well-known.yml
- type: MCPServer
url: mcp/read-ai-mcp.yml
- type: ToolCrosswalk
url: mcp/read-ai-tool-crosswalk.yml
- type: AgentSkill
url: skills/_index.yml
- type: Authentication
url: authentication/read-ai-authentication.yml
- type: OAuthScopes
url: scopes/read-ai-scopes.yml
- type: Conventions
url: conventions/read-ai-conventions.yml
- type: ErrorCatalog
url: errors/read-ai-problem-types.yml
- type: RateLimits
url: rate-limits/read-ai-rate-limits.yml
- type: Lifecycle
url: lifecycle/read-ai-lifecycle.yml
- type: Conformance
url: conformance/read-ai-conformance.yml
- type: DataModel
url: data-model/read-ai-data-model.yml
- type: Packages
url: packages/read-ai-packages.yml
- type: Webhooks
url: asyncapi/read-ai-webhooks.yml
- type: Plans
url: plans/read-ai-plans.yml
x-enrichment:
date: '2026-08-05'
status: enriched
artifacts_added: 25
pass: local-v1
Read AI API — frequently asked questions
Does Read AI have an API?
Yes. APIs.io lists 2 APIs from Read AI, including Read AI REST API and Read AI MCP Server.
How do I authenticate with the Read AI API?
Read AI documents its authentication (oauth2/openIdConnect · 2 schemes). The details are profiled on APIs.io as Read Ai Authentication.
How much does the Read AI API cost?
Read AI publishes its prices; its Free plan is $0 as of 2026-10-28. APIs.io lists 4 pricing plans for Read AI, with each plan's price, limits and inclusions under Pricing on this page.
Does Read AI have an MCP server?
Yes. APIs.io lists 1 MCP server for Read AI: Read AI operates a first-party remote MCP server that exposes a user's meeting reports — metadata, participants, summaries, chapter summaries, action items, key questions, topics, full transcripts, en
Is the Read AI API ready for AI agents?
Read AI has a Kin Score of 59.0 out of 100 (strong) and an Agent Readiness score of 53.6 (agent-ready), scored by API Evangelist on 2026-11-06.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.