Control what your
AI agents can do.

OCC is a system where computations are only executable if they are authorized by a previously committed, cryptographically bound policy.

MCP
Anthropic
Cursor
OpenAI
LangChain
Vercel
CrewAI
Google
LlamaIndex
AutoGen
Cloudflare
GitHub
Paperclip
Composio
OpenClaw
Mastra

Available now

17 integrations
MCP

MCP (any server)

Available

Default-deny policy enforcement for ANY MCP server

npx occ-mcp-proxy --wrap npx <any-mcp-server>
Anthropic

Claude Desktop

Available

Policy-enforced MCP servers in Claude Desktop

Add to claude_desktop_config.json
Cursor

Cursor

Available

Policy-controlled AI edits in your IDE

Add to .cursor/mcp.json
OpenAI

OpenAI

Available

Policy enforcement for OpenAI function calls

npm install occ-openai
OpenAI

OpenAI Agents

Available

Policy-controlled agent tool execution

pip install occ-openai-agents
LangChain

LangChain

Available

Policy enforcement for LangChain tool calls

pip install occ-langchain
LangChain

LangGraph

Available

Policy-controlled node execution in LangGraph

npm install occ-langgraph
Vercel

Vercel AI SDK

Available

Policy enforcement middleware for Vercel AI

npm install occ-vercel
CrewAI

CrewAI

Available

Policy-enforced tools for CrewAI agents

pip install occ-crewai
Google

Google Gemini

Available

Policy enforcement for Gemini function calling

pip install occ-gemini
Google

Google ADK

Available

Policy-controlled Google ADK agents

pip install occ-google-adk
LlamaIndex

LlamaIndex

Available

Policy enforcement for LlamaIndex agents

pip install occ-llamaindex
AutoGen

AutoGen

Available

Policy-enforced multi-agent AutoGen workflows

pip install occ-autogen
OpenClaw

OpenClaw

Available

Policy-controlled local AI with 20+ platforms

pip install occ-openclaw
Mastra

Mastra

Available

Policy enforcement for Mastra AI agents

npm install occ-mastra
Cloudflare

Cloudflare Workers

Available

Policy enforcement at the edge on Cloudflare Workers

npm install occ-cloudflare
GitHub

GitHub Actions

Available

Verify execution proofs in CI

uses: mikeargento/occ-verify-action@v1

Every agent action that executes through OCC produces a proof. The proof authorized the action and is the verifiable record that it happened. Click to expand.

Loading live proofs...

Orchestrators

Agent platforms

OCC plugs into multi-agent orchestration platforms. Define a policy, and every tool call must be authorized by it. Revoke a permission, and the proof record updates accordingly. The proof that allowed the action and the proof that it happened are the same object.

Paperclip

Paperclip

Available

Agent control plane with policy enforcement, revocation, and TEE-attested proofs on every action

Composio

Composio

Coming Soon

250+ tool integrations with cryptographic control on every call

LangChain

LangSmith

Coming Soon

Controlled traces with cryptographic authorization for LangChain

Julep

Julep

Coming Soon

Stateful agent workflows with cryptographic control at every step

AgentOps

AgentOps

Coming Soon

Agent observability with cryptographic control and audit

Relevance AI

Relevance AI

Coming Soon

No-code agent builder with cryptographic control

Letta

Letta (MemGPT)

Coming Soon

Long-term memory agents with cryptographic control

SuperAGI

SuperAGI

Coming Soon

Autonomous agent framework with OCC control layer

Don't see your framework?

OCC is open source. Add cryptographic control to any tool-calling framework in minutes. Contributions welcome.