Metorial

Metorial is agentic infrastructure for AI-native companies — "the Vercel for MCP." It hosts 1,200+ Model Context Protocol (MCP) servers serverlessly, giving AI agents and clients like Claude, ChatGPT, Cursor, Copilot and Codex one place to connect approved apps, tools and shared skills. Its hibernation technology makes every MCP server serverless (sub-second cold starts, pay-per-request), and it handles production OAuth, per-user isolation, tracing, access control (SSO/SAML) and ProtoGuard request safety. Developers integrate through a resource-oriented REST API (api.metorial.com) with official Node.js, Python and Go SDKs, a CLI, and standard MCP URLs. Founded 2025, San Francisco; backed by Y Combinator (F25).

Metorial publishes 1 API on the APIs.io network. Tagged areas include Company, MCP, Model Context Protocol, AI Agents, and Agentic Infrastructure.

Metorial’s developer surface includes documentation, API reference, getting-started guide, pricing, signup flow, engineering blog, CLI, and 23 more developer resources.

🌐 Visit website 📡 Source on GitHub

37.4/100 thin ▬ flat Agent 44/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5

AccessSelf serve

1 APIs 1 MCP Servers

CompanyMCPModel Context ProtocolAI AgentsAgentic InfrastructureIntegrationsDeveloper ToolsServerlessAPI

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 37.4/100 · thin

Contract Quality 0.0 / 25

Developer Ergonomics 16.5 / 20

Commercial Clarity 7.9 / 20

Operational Transparency 3.8 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 44/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/metorial: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

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

Metorial API

Resource-oriented REST API to manage integrations, providers, sessions, portals, skills, identities and MCP access programmatically. Bearer API-key auth, cursor pagination, date...

MCP Servers 1

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

metorial-mcp.yml

MCP SERVER

Rate Limits 1

Documented rate limits and quota policies.

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

SignUp

Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

MCPServer

WellKnown

AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Lifecycle

Conformance

DataModel

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 5

Authentication, authorization, and security posture

TrustCenter

Compliance

SecurityCenter

DomainSecurity

Authentication

Operate 3

Status, limits, changes, and where to get help

StatusPage

StatusPage

Deprecation

Deprecation

RateLimits

RateLimits

Commercial 1

Pricing, plans, and the legal terms of use

Pricing

Pricing

Company 1

The organization behind the API

Blog

Blog

Other 1

Properties that don't map to a standard resource type

APICatalog

APICatalog

Source (apis.yml)

aid: metorial
name: Metorial
description: Metorial is agentic infrastructure for AI-native companies — "the Vercel for MCP." It hosts 1,200+ Model Context
  Protocol (MCP) servers serverlessly, giving AI agents and clients like Claude, ChatGPT, Cursor, Copilot and Codex one place
  to connect approved apps, tools and shared skills. Its hibernation technology makes every MCP server serverless (sub-second
  cold starts, pay-per-request), and it handles production OAuth, per-user isolation, tracing, access control (SSO/SAML) and
  ProtoGuard request safety. Developers integrate through a resource-oriented REST API (api.metorial.com) with official Node.js,
  Python and Go SDKs, a CLI, and standard MCP URLs. Founded 2025, San Francisco; backed by Y Combinator (F25).
url: https://raw.githubusercontent.com/api-evangelist/metorial/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 19
  pass: local-v1
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://metorial.com/logo/logo.svg
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- MCP
- Model Context Protocol
- AI Agents
- Agentic Infrastructure
- Integrations
- Developer Tools
- Serverless
- API
apis:
- name: Metorial API
  description: Resource-oriented REST API to manage integrations, providers, sessions, portals, skills, identities and MCP
    access programmatically. Bearer API-key auth, cursor pagination, date-based versioning; 466 endpoints across 112 resource
    controllers.
  humanURL: https://metorial.com/api
  baseURL: https://api.metorial.com
  properties:
  - type: Documentation
    url: https://metorial.com/docs
  - type: APIReference
    url: https://metorial.com/api
  - type: GettingStarted
    url: https://metorial.com/docs/api-getting-started
  - type: Authentication
    url: authentication/metorial-authentication.yml
  - type: APIIntrospection
    url: https://metorial.com/api/introspection.json
    x-format: introspection-json
    x-note: Proprietary machine-readable API introspection (466 endpoints); no OpenAPI is published.
common:
- type: TrustCenter
  url: security/metorial-trust-center.yml
- type: Compliance
  url: https://metorial.com/security
- type: SecurityCenter
  url: https://metorial.com/security
- type: DomainSecurity
  url: security/metorial-domain-security.yml
- type: DeveloperPortal
  url: https://platform.metorial.com
- type: Documentation
  url: https://metorial.com/docs
- type: APIReference
  url: https://metorial.com/api
- type: GettingStarted
  url: https://metorial.com/docs/api-getting-started
- type: Pricing
  url: https://metorial.com/pricing
- type: SignUp
  url: https://platform.metorial.com
- type: GitHubOrganization
  url: https://github.com/metorial
- type: StatusPage
  url: https://status.metorial.com
- type: Blog
  url: https://metorial.com/blog
- type: LLMsTxt
  url: llms/metorial-llms.txt
- type: Packages
  url: packages/metorial-packages.yml
- type: SDKs
  url: packages/metorial-packages.yml
- type: CLI
  url: cli/metorial-cli.yml
- type: MCPServer
  url: mcp/metorial-mcp.yml
- type: Authentication
  url: authentication/metorial-authentication.yml
- type: Conventions
  url: conventions/metorial-conventions.yml
- type: ErrorCatalog
  url: errors/metorial-problem-types.yml
- type: Lifecycle
  url: lifecycle/metorial-lifecycle.yml
- type: Deprecation
  url: lifecycle/metorial-lifecycle.yml
- type: RateLimits
  url: rate-limits/metorial-rate-limits.yml
- type: Conformance
  url: conformance/metorial-conformance.yml
- type: DataModel
  url: data-model/metorial-data-model.yml
- type: Sandbox
  url: sandbox/metorial-sandbox.yml
- type: WellKnown
  url: well-known/metorial-well-known.yml
- type: APICatalog
  url: well-known/metorial-api-catalog.json
- type: AgentSkill
  url: skills/_index.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io