Relevance AI

Relevance AI is an agent platform for building, testing and running specialist AI agents and multi-agent "workforces" — teams of agents that coordinate on a shared goal. Domain experts build agents in a no-code visual builder, hold them to pass/fail quality bars with a built-in evals system, and connect them to 1,000+ integrations across sales, marketing, customer success, operations and HR. Developers reach the same platform three ways: a 566-operation REST API served from regional hosts in the US, EU and Australia; a first-party JavaScript/TypeScript SDK on npm and JSR; and a hosted, OAuth-protected MCP server at mcp.relevanceai.com that exposes agents, tools, workforces, knowledge tables, evals and analytics to any MCP client. Enterprise governance covers RBAC, human-in-the-loop approvals, SSO/SAML, PII masking, version control with rollback, multi-region data residency, and OpenTelemetry audit-log and trace streaming to the customer's own S3 bucket. Operated by OnSearch Pty Ltd T/A Relevance AI; SOC 2 Type II and GDPR compliant.

Relevance AI publishes 1 API on the APIs.io network. Tagged areas include AI Agents, AI Automation, Multi-Agent Systems, Agent Platform, and MCP.

The Relevance AI catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Relevance AI’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, pricing, signup flow, and 34 more developer resources.

🌐 Visit website 📡 Source on GitHub

72.4/100 exemplar ▬ flat Agent 60/100 agent native saas Full breakdown ↓
scored 2026-09-15 · rubric v0.22.0

AccessFreemiumSelf serveFree trial

2 APIs 1 MCP Servers

AI Agents AI Automation Multi-Agent Systems Agent Platform MCP agent-native Workflow-AutomationLLM OrchestrationKnowledge-Management Observability Sales AutomationGTM Engineering

Kin Score

Kin Score How this is scored →
scored 2026-09-15 · rubric v0.22.0

Composite quality — 72.4/100 · exemplar

Contract Quality 9.4 / 23

Developer Ergonomics 12.9 / 18

Access Clarity 18.0 / 18

Operational Transparency 7.7 / 12

Contract Governance 2.0 / 11

Discoverability 6.8 / 9

Create-or-Update Ergonomics 10.0 / 10

Agent readiness — 60/100 · agent native

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 9 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 8 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 6 / 6

Protected Resource Metadata 5 / 5

Registration Without a Human 6 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/relevance-ai: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

Individual APIs this provider publishes, each with its own machine-readable definition.

Relevance AI API

REST API for the Relevance AI agent platform — 521 paths and 566 operations covering agents, tools (called "studios" in the API), multi-agent workforces, knowledge tables, conve...

Relevance AI MCP Server

First-party hosted MCP server exposing a Relevance AI project's agents, tools, workforces, knowledge tables, evals, analytics, folders and triggers to any MCP-compatible client ...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Relevance AI MCP Server

Relevance AI runs a first-party remote MCP server that exposes a project's agents, tools, workforces, knowledge tables, evals, analytics and triggers to any MCP-compatible clien...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Relevance Ai Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Relevance Ai Rate Limits

10 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Relevance Ai Finops

FINOPS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Relevance Ai Events

ASYNCAPI

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Relevance Ai Authentication

apiKey/oauth2 · 2 schemes

SECURITY

Relevance Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Relevance Ai Trust Center

SOC 2 Type II, GDPR

SECURITY

Scopes 1

OAuth scopes governing access to this provider's APIs.

Relevance Ai Scopes

OAuth 2.0 · no documented scopes

0 scopes

SCOPES

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Login

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer

AgentSkill

LLMsTxt

WellKnown

Design & Contract 8

Pagination, idempotency, versioning, errors, and events

Conformance

Lifecycle

Conventions

Idempotency

ErrorCatalog

Components

Webhooks

DataModel

Scroll for all 8

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

ToolCrosswalk

Access & Security 5

Authentication, authorization, and security posture

TrustCenter

Compliance

Authentication

OAuthScopes

DomainSecurity

Operate 4

Status, limits, changes, and where to get help

Support

StatusPage

ChangeLog

RateLimits

Commercial 5

Pricing, plans, and the legal terms of use

Pricing

TermsOfService

PrivacyPolicy

Plans

FinOps

Company 3

The organization behind the API

Website

Website

Blog

Blog

LinkedIn

Other 2

Properties that don't map to a standard resource type

AgentCard

AgentCard

Overlay

Overlay

Source (apis.yml)

aid: relevance-ai
name: Relevance AI
description: 'Relevance AI is an agent platform for building, testing and running specialist AI agents and multi-agent "workforces"
  — teams of agents that coordinate on a shared goal. Domain experts build agents in a no-code visual builder, hold them to
  pass/fail quality bars with a built-in evals system, and connect them to 1,000+ integrations across sales, marketing, customer
  success, operations and HR. Developers reach the same platform three ways: a 566-operation REST API served from regional
  hosts in the US, EU and Australia; a first-party JavaScript/TypeScript SDK on npm and JSR; and a hosted, OAuth-protected
  MCP server at mcp.relevanceai.com that exposes agents, tools, workforces, knowledge tables, evals and analytics to any MCP
  client. Enterprise governance covers RBAC, human-in-the-loop approvals, SSO/SAML, PII masking, version control with rollback,
  multi-region data residency, and OpenTelemetry audit-log and trace streaming to the customer''s own S3 bucket. Operated
  by OnSearch Pty Ltd T/A Relevance AI; SOC 2 Type II and GDPR compliant.'
type: Index
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  - mcp
  generated: '2026-08-29'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: true
  try_now: false
  public: false
  label: Freemium with self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-08-29'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/relevance-ai.png
tags:
- AI Agents
- AI Automation
- Multi-Agent Systems
- Agent Platform
- MCP
- agent-native
- Workflow-Automation
- LLM Orchestration
- Knowledge-Management
- Observability
- Sales Automation
- GTM Engineering
tags_raw:
- AI Agents
- AI Automation
- Multi-Agent Systems
- Agent Platform
- MCP
- agent-native
- Workflow Automation
- LLM Orchestration
- Knowledge Management
- Observability
- Sales Automation
- GTM Engineering
url: https://raw.githubusercontent.com/api-evangelist/relevance-ai/refs/heads/main/apis.yml
created: '2026-03-27'
modified: '2026-08-29'
specificationVersion: '0.23'
apis:
- aid: relevance-ai:relevance-ai
  name: Relevance AI API
  description: 'REST API for the Relevance AI agent platform — 521 paths and 566 operations covering agents, tools (called
    "studios" in the API), multi-agent workforces, knowledge tables, conversations, triggers, evals, analytics, the template
    marketplace, projects, organizations and billing. Authenticated with an `Authorization: project:api_key` header. Served
    from a regional host chosen at client construction: api-bcbe5a (US), api-d7b62b (EU) or api-f1db6c (AU).'
  humanURL: https://api-f1db6c.stack.tryrelevance.com/latest/documentation
  baseURL: https://api-{region}.stack.tryrelevance.com/latest
  tags:
  - AI Agents
  - AI Automation
  - Multi-Agent Systems
  - Workflow-Automation
  tags_raw:
  - AI Agents
  - AI Automation
  - Multi-Agent Systems
  - Workflow Automation
  properties:
  - type: OpenAPI
    url: openapi/relevance-ai-openapi.json
  - type: Documentation
    url: https://relevanceai.com/docs
  - type: APIReference
    url: https://api-f1db6c.stack.tryrelevance.com/latest/documentation
  - type: Authentication
    url: authentication/relevance-ai-authentication.yml
  - type: ErrorCatalog
    url: errors/relevance-ai-problem-types.yml
  - type: Overlay
    url: overlays/relevance-ai-openapi-overlay.yaml
  - type: DataModel
    url: data-model/relevance-ai-data-model.yml
- aid: relevance-ai:relevance-ai-mcp
  name: Relevance AI MCP Server
  description: First-party hosted MCP server exposing a Relevance AI project's agents, tools, workforces, knowledge tables,
    evals, analytics, folders and triggers to any MCP-compatible client (Claude, ChatGPT, Cursor, VS Code, Codex, Windsurf,
    Zed and others). Streamable HTTP transport behind OAuth 2.0 with PKCE and dynamic client registration; a session binds
    to one project and is bounded server-side by the caller's project role, with an opt-in Run-Only mode that strips write
    and destructive tools.
  humanURL: https://relevanceai.com/docs/integrations/mcp/mcp-server
  baseURL: https://mcp.relevanceai.com/
  tags:
  - MCP
  - agent-native
  - AI Agents
  properties:
  - type: MCPServer
    url: mcp/relevance-ai-mcp.yml
  - type: ToolCrosswalk
    url: mcp/relevance-ai-tool-crosswalk.yml
  - type: Documentation
    url: https://relevanceai.com/docs/integrations/mcp/mcp-server
  - type: OAuthScopes
    url: scopes/relevance-ai-scopes.yml
common:
- type: Website
  url: https://relevanceai.com
- type: DeveloperPortal
  url: https://relevanceai.com/docs
- type: Documentation
  url: https://relevanceai.com/docs
- type: APIReference
  url: https://api-f1db6c.stack.tryrelevance.com/latest/documentation
- type: GettingStarted
  url: https://relevanceai.com/docs/get-started/quick-start-guide
- type: Support
  url: https://relevanceai.com/docs/get-started/support
- type: Blog
  url: https://relevanceai.com/blog
- type: GitHubOrganization
  url: https://github.com/RelevanceAI
- type: LinkedIn
  url: https://www.linkedin.com/company/relevanceai
- type: Pricing
  url: https://relevanceai.com/pricing
- type: SignUp
  url: https://relevanceai.com/signup
- type: Login
  url: https://app.relevanceai.com/
- type: TermsOfService
  url: https://relevanceai.com/terms-and-conditions
- type: PrivacyPolicy
  url: https://relevanceai.com/privacy-policy
- type: StatusPage
  url: https://status.relevanceai.com/
- type: TrustCenter
  url: https://trust.relevanceai.com/
- type: Compliance
  url: security/relevance-ai-trust-center.yml
- type: Conformance
  url: conformance/relevance-ai-conformance.yml
- type: ChangeLog
  url: changelog/relevance-ai-changelog.yml
- type: Lifecycle
  url: lifecycle/relevance-ai-lifecycle.yml
- type: Authentication
  url: authentication/relevance-ai-authentication.yml
- type: OAuthScopes
  url: scopes/relevance-ai-scopes.yml
- type: Conventions
  url: conventions/relevance-ai-conventions.yml
- type: Idempotency
  url: conventions/relevance-ai-conventions.yml
- type: ErrorCatalog
  url: errors/relevance-ai-problem-types.yml
- type: Packages
  url: packages/relevance-ai-packages.yml
- type: SDKs
  url: packages/relevance-ai-packages.yml
- type: Components
  url: components/relevance-ai-components.yml
- type: MCPServer
  url: mcp/relevance-ai-mcp.yml
- type: ToolCrosswalk
  url: mcp/relevance-ai-tool-crosswalk.yml
- type: AgentCard
  url: a2a/relevance-ai-a2a.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/relevance-ai-llms.txt
- type: WellKnown
  url: well-known/relevance-ai-well-known.yml
- type: Webhooks
  url: asyncapi/relevance-ai-events.yml
- type: Overlay
  url: overlays/relevance-ai-openapi-overlay.yaml
- type: DataModel
  url: data-model/relevance-ai-data-model.yml
- type: Plans
  url: plans/relevance-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/relevance-ai-rate-limits.yml
- type: FinOps
  url: finops/relevance-ai-finops.yml
- type: DomainSecurity
  url: security/relevance-ai-domain-security.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
x-enrichment:
  date: '2026-08-29'
  status: enriched
  artifacts_added: 35
  pass: local-v1

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/relevance-ai"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/relevance-ai/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/relevance-ai/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.