Cordum
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
What is Cordum?
Cordum is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open agent control plane. govern autonomous ai agents with pre-execution policy enforcement, approval gates, and audit trails. works with langchain, crewai, mcp, and any framework.
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The open agent control plane. Govern autonomous AI agents wi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cordum-ioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cordum
Cordum is an open-source agent control plane that governs autonomous AI agents with pre-execution policy enforcement, human-in-the-loop approval gates, and immutable audit trails. It sits between your AI agents and their execution environment, evaluating every action against configurable policies before allowing it to proceed—blocking, approving, or escalating for human review. Teams running LangChain, CrewAI, MCP-based, or custom agent frameworks use Cordum to add safety guardrails, compliance logging, and fleet monitoring without rewriting their agent code.
Prerequisites
- Docker Desktop v4+ (or Docker Engine v20.10+ with Compose v2) with at least 4 GB RAM allocated
- Go 1.24+ for certificate generation and development builds
- curl and jq utilities installed
- An MCP-compatible client or agent framework (LangChain, CrewAI, custom MCP agents)
Clone the repository
Clone the Cordum repository to your machine. All deployment scripts and Helm charts are included.
git clone https://github.com/cordum-io/cordum.git
cd cordumGenerate API credentials
Generate a secure random API key and Redis password. These are required for all inter-service authentication and the dashboard login.
export CORDUM_API_KEY=$(openssl rand -hex 32)
export REDIS_PASSWORD=$(openssl rand -hex 16)Start the stack with Docker Compose
Pull the pre-built images and start all Cordum services: the API gateway, safety kernel, scheduler, workflow engine, dashboard, NATS, and Redis.
docker compose pull && docker compose up -dRun the demo to verify governance
Install the quickstart demo pack and run it to see three governance verdicts in action: ALLOW, DENY, and REQUIRE_APPROVAL.
cordumctl pack install ./demo/quickstart/pack
cordumctl demo run quickstartSubmit a test agent job
Send a test job through the API gateway to confirm your agent payloads are reaching the safety kernel and returning policy verdicts.
curl -sS --cacert ./certs/ca/ca.crt \
-X POST https://localhost:8081/api/v1/jobs \
-H "X-API-Key: $CORDUM_API_KEY" \
-H "X-Tenant-ID: default" \
-H "Content-Type: application/json" \
-d '{"topic":"job.default","prompt":"hello"}'Open the dashboard
Access the Cordum dashboard to monitor agent fleet health, view audit trails, and manage pending approval requests.
Cordum Examples
Client configuration
Configure an MCP client to route through Cordum's Edge compliance firewall, which intercepts Claude Code actions and enforces policies before execution.
{
"mcpServers": {
"cordum": {
"command": "npx",
"args": ["cordum-io"],
"env": {
"CORDUM_GATEWAY": "https://localhost:8081",
"CORDUM_API_KEY": "your_cordum_api_key_here",
"CORDUM_TENANT_ID": "default"
}
}
}
}Prompts to try
These prompts demonstrate how Cordum governance appears in an agent-driven workflow.
- "Run the agent job and show me the policy verdict"
- "List all pending approval requests in the control plane"
- "Show me the audit trail for the last 10 agent actions"
- "Deploy the quickstart demo pack and run a governance test"Troubleshooting Cordum
Docker Compose fails to start with memory errors
Increase Docker Desktop's memory allocation to at least 4 GB in Settings → Resources → Memory. Cordum runs several services (NATS, Redis, safety kernel, gateway) concurrently.
API requests return 401 Unauthorized
Ensure the X-API-Key header matches the CORDUM_API_KEY value set during setup. Re-export the variable if your shell session was reset, or check the .env file generated by docker compose.
Certificate errors when connecting to the API gateway
Use --cacert ./certs/ca/ca.crt in curl commands or trust the generated CA certificate. The quickstart script generates self-signed certs; for production, replace them with certificates from a trusted CA.
Frequently Asked Questions about Cordum
What is Cordum?
Cordum is a Model Context Protocol (MCP) server that open agent control plane. govern autonomous ai agents with pre-execution policy enforcement, approval gates, and audit trails. works with langchain, crewai, mcp, and any framework. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cordum?
Follow the installation instructions on the Cordum GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cordum?
Cordum works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cordum free to use?
Yes, Cordum is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Cordum Alternatives — Similar Security Servers
Looking for alternatives to Cordum? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cordum in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cordum?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.