> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runlayer.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Integrations

> Connect your agents and AI tools to Runlayer

Runlayer connects to your agents two ways — pick the one that fits, or use both.

## Connect your agent to MCP servers

Point an agent framework at a Runlayer MCP proxy URL. Your agent calls MCP tools
as usual; Runlayer applies policy, scanning, and identity in the middle.

<CardGroup cols={2}>
  <Card title="Claude Agent SDK" icon="robot" href="/agent-frameworks#claude-agent-sdk">
    Native MCP support via `query()` and `allowedTools`, in TypeScript and Python.
  </Card>

  <Card title="Vercel AI SDK" icon="bolt" href="/agent-frameworks#vercel-ai-sdk">
    MCP tools for `generateText` and `streamText` over HTTP or stdio.
  </Card>

  <Card title="OpenAI Agents SDK" icon="brain" href="/agent-frameworks#openai-agents-sdk">
    Streamable HTTP, stdio, and hosted MCP tools for Python agents.
  </Card>

  <Card title="Google ADK" icon="cubes" href="/agent-frameworks#google-adk">
    MCP servers in ADK agents, plus the MCP Toolbox for 40+ databases.
  </Card>
</CardGroup>

## Govern and monitor what agents do

Stream an agent's full activity — prompts, reasoning, tool calls, and responses —
into Runlayer [Sessions](/platform-sessions), with scanning, policy, and
[AgentGuard](/agentguard) applied across the trajectory.

<CardGroup cols={2}>
  <Card title="Hooks SDK" icon="shield-check" href="/runlayer-hooks-sdk">
    Instrument custom TypeScript and Python agents — stream the whole
    conversation into Sessions and enforce tool calls, with adapters for Claude,
    Vercel, OpenAI, and Google harnesses.
  </Card>

  <Card title="Claude Cowork monitoring" icon="tower-broadcast" href="/claude-cowork-monitoring">
    Export organization-wide Claude Cowork OpenTelemetry session logs to Runlayer
    — no per-machine hook or daemon required.
  </Card>
</CardGroup>