metorial/metorial

Connect any AI model to 1200+ integrations (MCP, CLI, API)

What it solves

Metorial provides a standardized identity and access layer for AI agents. It solves the problem of connecting agents to production systems without consistent authentication, granular permissions, auditing, or standard access restrictions, preventing the need to write ad hoc integration code for every new tool.

How it works

Metorial acts as a control plane that sits between AI agents and external integrations. It leverages the Model Context Protocol (MCP) to standardize how agents interact with data and tools. Developers use Metorial SDKs (TypeScript or Python) to connect agents to a vast catalog of integrations, while the platform handles the complex auth flows (OAuth, API keys, service accounts), RBAC, and SAML SSO in the background.

Who it’s for

It is designed for developers building agentic AI applications and security teams who need to enforce and inspect agent activity within an organization's existing security model.

Highlights

  • Extensive Integration Catalog: Access to over 1,200 integrations across SaaS, enterprise systems, and custom MCP servers.
  • Unified Auth Management: Centralized handling of token lifecycles, OAuth flows, and credential management via a single interface.
  • Enterprise Security: Built-in RBAC, SAML SSO, and IAM for scoped permissions per agent, workflow, or team.
  • Observability: Full audit logs and traceability to track which agent performed which action using specific credentials.
  • Broad Framework Support: Adapters for major AI SDKs and frameworks including Vercel AI SDK, OpenAI, Anthropic, LangChain, PydanticAI, and CrewAI.

Related

  • Project
    agentic-community/mcp-gateway-registry

    A unified control plane and gateway for AI assets, providing centralized discovery, governance, and secure access to MCP servers, agents, and model inference endpoints.

  • Project
    obot-platform/obot

    An open-source platform for organizations to manage, secure, and govern their AI ecosystems, providing centralized control over LLM access, MCP servers, and AI activity auditing.

  • Project
    agentgateway/agentgateway

    An open-source proxy that provides security, observability, and governance for agent-to-LLM, agent-to-tool, and agent-to-agent communication.

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products and enterprise resources.

  • Project
    UsefulSoftwareCo/executor

    An open-source integration layer that centralizes tool configurations, authentication, and policies for AI agents via the Model Context Protocol (MCP).