Klavis AI website screenshot

Klavis AI

Klavis AI is an open-source MCP integration platform that lets AI agents reliably use external tools at production scale. The product line is organized around Strata (intelligent connectors that compress and route tool context), 100+ prebuilt MCP integrations with OAuth, and an MCP Sandbox for live agent training and evaluation. Target customers are AI agent companies, RL teams, and enterprises that need long-horizon multi-app environments with seeded state, resets, and verifiable outcomes, plus SOC 2 Type II and GDPR posture. SDKs are available for Python and TypeScript/JavaScript, integrations cover Claude, OpenAI, Gemini, Cohere, Mistral, LangChain/LangGraph, LlamaIndex, CrewAI, Mastra, Agno, Fireworks, Together, and Google ADK, and the project is Apache-2.0 on GitHub.

Klavis AI publishes 4 APIs on the APIs.io network, including MCP Servers API, Sandbox API, Tools API, and 1 more. Tagged areas include MCP, MCP Servers, MCP Hosting, Connectors, and Authentication.

Klavis AI’s developer surface includes authentication, documentation, engineering blog, pricing, and 12 more developer resources.

47.2/100 developing ▬ flat Agent 20/100 agent aware open core · Apache-2.0 Full breakdown ↓
scored 2026-09-14 · rubric v0.22.0
AccessFreeSelf serve⚡ Free to try
1 APIs
MCPMCP ServersMCP HostingConnectorsAuthenticationSandboxesAgent TrainingReinforcement LearningWhite LabelOpen-SourceStrata

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-09-14 · rubric v0.22.0
Open Source Surface applies to this provider. This product is open source and we read its repository directly, so Open Source Surface carries 10 points of the composite. It is scored from what the repository actually publishes — a security policy, a contribution guide, a release history, a code of conduct — read live from the provider rather than inferred from our own catalog pointers. This facet adds; nothing was taken away to make room for it. An open-source project is not excused from the commercial facets, because exemption would strip it of the points it does earn. If we have the wrong repository, or this product is not open source, say so on your provider repo and we will drop the facet rather than have you publish against it.
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.
The six quality facets above are damped to 80 points between them, because the conditional facet above carries the other 20. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 80% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
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/klavis: 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 5

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

Klavis MCP Platform API

The Klavis API manages hosted MCP servers, OAuth flows for 50+ integrated services, Strata multi-tool servers, and live sandbox environments. Endpoints cover MCP server CRUD and...

Klavis AI MCP Servers API

Create and manage hosted MCP server instances

Klavis AI Sandbox API

Acquire and manage isolated sandbox VMs

Klavis AI Tools API

List and invoke MCP server tools

Klavis AI Users API

End-user metadata for agent integrations

Open Collections 6

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Pricing Plans 1

Published pricing tiers and plan structures.

Klavis Plans Pricing

1 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Klavis Rate Limits

2 limits

RATE LIMITS

FinOps 1

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

Security Posture 2

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

Klavis Authentication

http · 1 scheme

SECURITY

Klavis Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Klavis Agentic Access

5 operations · 3 acting

5 operations · 3 acting

AGENTIC

Resources

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Build 2

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 3

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: klavis
name: Klavis AI
description: Klavis AI is an open-source MCP integration platform that lets AI agents reliably use external tools at production
  scale. The product line is organized around Strata (intelligent connectors that compress and route tool context), 100+ prebuilt
  MCP integrations with OAuth, and an MCP Sandbox for live agent training and evaluation. Target customers are AI agent companies,
  RL teams, and enterprises that need long-horizon multi-app environments with seeded state, resets, and verifiable outcomes,
  plus SOC 2 Type II and GDPR posture. SDKs are available for Python and TypeScript/JavaScript, integrations cover Claude,
  OpenAI, Gemini, Cohere, Mistral, LangChain/LangGraph, LlamaIndex, CrewAI, Mastra, Agno, Fireworks, Together, and Google
  ADK, and the project is Apache-2.0 on GitHub.
type: Index
deliveryModel:
  model: open-core
  license: Apache-2.0
  open_source: true
  commercial: true
  callable_host: true
  label: Open core · an OSS project plus a commercial hosted product
  confidence: high
  source:
  - license
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: free
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Free · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/klavis.png
tags:
- MCP
- MCP Servers
- MCP Hosting
- Connectors
- Authentication
- Sandboxes
- Agent Training
- Reinforcement Learning
- White Label
- Open-Source
- Strata
tags_raw:
- MCP
- Model Context Protocol
- MCP Servers
- MCP Hosting
- Connectors
- OAuth
- Sandboxes
- Agent Training
- Reinforcement Learning
- White Label
- Open Source
- Strata
url: https://raw.githubusercontent.com/api-evangelist/klavis/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-23'
specificationVersion: '0.23'
apis:
- aid: klavis:mcp-platform
  name: Klavis MCP Platform API
  description: The Klavis API manages hosted MCP servers, OAuth flows for 50+ integrated services, Strata multi-tool servers,
    and live sandbox environments. Endpoints cover MCP server CRUD and tool invocation, sandbox VM acquisition and reset,
    data initialization and export, user and integration management, and white-label OAuth branding.
  humanURL: https://www.klavis.ai/docs
  baseURL: https://api.klavis.ai
  tags:
  - MCP Servers
  - Strata
  - Sandboxes
  - Authentication
  - Integration
  - White Label
  - User
  tags_raw:
  - MCP Servers
  - Strata
  - Sandboxes
  - OAuth
  - Integrations
  - White Label
  - Users
  properties:
  - type: Documentation
    url: https://www.klavis.ai/docs
  - type: APIReference
    url: https://www.klavis.ai/docs/api-reference
  - type: GettingStarted
    url: https://www.klavis.ai/docs/quickstart
  - type: Signup
    url: https://www.klavis.ai/home
  - type: SDKs
    url: https://pypi.org/project/klavis/
  - type: SDKs
    url: https://www.npmjs.com/package/klavis
  - type: GitHubRepository
    url: https://github.com/Klavis-AI/klavis
  - type: GitHubOrganization
    url: https://github.com/Klavis-AI
  - type: Pricing
    url: https://www.klavis.ai/pricing
  - type: LlmsText
    url: https://www.klavis.ai/docs/llms.txt
  features:
  - name: Hosted MCP Servers
    description: Create, manage, and call 100+ prebuilt MCP servers via REST endpoints.
  - name: Strata Unified Server
    description: Single MCP endpoint that intelligently routes across multiple tool integrations to fit LLM context windows.
  - name: OAuth for 50+ Services
    description: Built-in OAuth flows for Gmail, Slack, Salesforce, HubSpot, Notion, GitHub, and more.
  - name: White-Label OAuth
    description: Brand OAuth screens and bring your own credentials for customer-facing apps.
  - name: MCP Sandbox
    description: Scalable, isolated VMs with seeded state, resets, parallel isolation, and snapshot export for agent training.
  - name: Realistic Task Environments
    description: Long-horizon multi-app scenarios spanning browser, code, SaaS, and MCP servers with verifiable outcomes.
  - name: User & Integration Management
    description: Manage end users, stored credentials, and which integrations are exposed per agent.
  - name: Open Source Core
    description: Apache-2.0 codebase covering 100+ MCP servers and Strata.
  - name: Compliance
    description: SOC 2 Type II and GDPR posture for regulated deployments.
  useCases:
  - name: Production Agent Integrations
    description: Connect agents to Gmail, Slack, Salesforce, HubSpot, GitHub, Notion, and more without writing per-tool glue.
  - name: Agent RL and Evals
    description: Run reinforcement learning and evaluations in realistic multi-app sandboxes with verifiable outcomes.
  - name: White-Label MCP for SaaS
    description: Embed MCP-powered tools into your own product under your own brand.
  - name: Tool Context Optimization
    description: Use Strata to expose hundreds of tools to an LLM without overflowing context.
  - name: Self-Hosted MCP
    description: Deploy the open-source servers on your own infrastructure.
  integrations:
  - name: Claude
  - name: OpenAI
  - name: Gemini
  - name: Cohere
  - name: Mistral
  - name: LangChain
  - name: LangGraph
  - name: LlamaIndex
  - name: CrewAI
  - name: Mastra
  - name: Agno
  - name: Fireworks AI
  - name: Together AI
  - name: Google ADK
  - name: Claude Desktop
  - name: Cursor
  - name: VS Code
  - name: Continue
  authentication:
  - type: API Key
    description: 'Account API keys passed via the `Authorization: Bearer` header authenticate REST and SDK calls.'
  - type: OAuth2
    description: Built-in OAuth 2.0 flows handle credentials for 50+ third-party services on behalf of end users.
- aid: klavis:klavis-mcp-servers-api
  name: Klavis AI MCP Servers API
  description: Create and manage hosted MCP server instances
  humanURL: https://www.klavis.ai/docs
  baseURL: https://api.klavis.ai
  tags:
  - MCP Servers
  properties:
  - type: OpenAPI
    url: openapi/klavis-mcp-servers-api-openapi.yml
- aid: klavis:klavis-sandbox-api
  name: Klavis AI Sandbox API
  description: Acquire and manage isolated sandbox VMs
  humanURL: https://www.klavis.ai/docs
  baseURL: https://api.klavis.ai
  tags:
  - Sandbox
  properties:
  - type: OpenAPI
    url: openapi/klavis-sandbox-api-openapi.yml
- aid: klavis:klavis-tools-api
  name: Klavis AI Tools API
  description: List and invoke MCP server tools
  humanURL: https://www.klavis.ai/docs
  baseURL: https://api.klavis.ai
  tags:
  - Tools
  properties:
  - type: OpenAPI
    url: openapi/klavis-tools-api-openapi.yml
- aid: klavis:klavis-users-api
  name: Klavis AI Users API
  description: End-user metadata for agent integrations
  humanURL: https://www.klavis.ai/docs
  baseURL: https://api.klavis.ai
  tags:
  - User
  tags_raw:
  - Users
  properties:
  - type: OpenAPI
    url: openapi/klavis-users-api-openapi.yml
common:
- type: IssueTracker
  url: https://github.com/Klavis-AI/klavis/issues
- type: Releases
  url: https://github.com/Klavis-AI/klavis/releases
- type: ContributionGuide
  url: https://github.com/Klavis-AI/klavis/blob/main/CONTRIBUTING.md
- type: License
  name: Apache-2.0
  url: https://github.com/Klavis-AI/klavis/blob/main/LICENSE
- type: AgenticAccess
  url: agentic-access/klavis-agentic-access.yml
- type: DomainSecurity
  url: security/klavis-domain-security.yml
- type: Authentication
  url: authentication/klavis-authentication.yml
- type: Website
  url: https://www.klavis.ai
- type: Documentation
  url: https://www.klavis.ai/docs
- type: Blog
  url: https://www.klavis.ai/blog
- type: GitHubOrganization
  url: https://github.com/Klavis-AI
- type: GitHubRepository
  url: https://github.com/Klavis-AI/klavis
- type: Pricing
  url: https://www.klavis.ai/pricing
- type: Contact
  url: https://www.klavis.ai/contact
- type: TermsOfService
  url: https://www.klavis.ai/terms
- type: PrivacyPolicy
  url: https://www.klavis.ai/privacy
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

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/klavis"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/klavis/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/klavis/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.

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