Klavis AI

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
position: Provider
access: 3rd-Party
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
  - 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: '0.20'
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
      - 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: SDK
        url: https://pypi.org/project/klavis/
      - type: SDK
        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: LLMsTxt
        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.
common:
  - 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: [email protected]