Cordum MCP
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 MCP?
Cordum MCP 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 cordumConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cordum MCP
Cordum MCP Server is the MCP interface layer of the Cordum open agent control plane, which governs autonomous AI agents with pre-execution policy enforcement, approval gates, and immutable audit trails. By integrating as an MCP server, Cordum intercepts and evaluates agent tool calls before they execute, returning ALLOW, DENY, or REQUIRE_APPROVAL verdicts based on your configured policies. It works across LangChain, CrewAI, and any MCP-compatible framework, giving platform-agnostic governance without modifying 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
- curl and jq for API testing
- An MCP-compatible client or agent framework
Clone and enter the repository
Clone the Cordum repository which contains all service definitions, Helm charts, and the quickstart script.
git clone https://github.com/cordum-io/cordum.git
cd cordumRun the quickstart script
The quickstart script automates certificate generation, environment setup, and stack deployment. It is the fastest way to get Cordum running locally.
./tools/scripts/quickstart.shSet environment variables for MCP integration
Export the credentials that your MCP client will use to authenticate with the Cordum gateway. These were generated during quickstart.
export CORDUM_GATEWAY=https://localhost:8081
export CORDUM_API_KEY=$(grep CORDUM_API_KEY .env | cut -d= -f2)
export CORDUM_TENANT_ID=defaultEnable the Cordum Edge for Claude Code
Use cordumctl to activate the Edge compliance firewall specifically for Claude Code, intercepting all tool calls through the Cordum policy engine.
./bin/cordumctl edge claudeRun the governance demonstration
Install the demo pack and run it to see ALLOW, DENY, and REQUIRE_APPROVAL verdicts applied to sample agent actions.
cordumctl pack install ./demo/quickstart/pack
cordumctl demo run quickstartCordum MCP Examples
Client configuration
MCP client configuration to route agent calls through the Cordum control plane for policy evaluation.
{
"mcpServers": {
"cordum": {
"command": "npx",
"args": ["cordum"],
"env": {
"CORDUM_GATEWAY": "https://localhost:8081",
"CORDUM_API_KEY": "your_cordum_api_key_here",
"CORDUM_TENANT_ID": "default"
}
}
}
}Prompts to try
Agent governance prompts to exercise Cordum's policy enforcement capabilities.
- "Submit a test agent job and show me the policy verdict"
- "List all pending approval requests waiting for human review"
- "Show the audit trail for recent agent actions"
- "Block any agent action that tries to delete files and log the attempt"Troubleshooting Cordum MCP
quickstart.sh fails with certificate generation errors
Ensure Go 1.24+ is installed (`go version`). The quickstart script uses Go to generate TLS certificates for the API gateway.
REQUIRE_APPROVAL verdicts never resolve
Open the Cordum dashboard at http://localhost:8082 and navigate to the Approvals section. Pending requests must be manually approved or denied there.
cordumctl command not found
The cordumctl binary is built during quickstart and placed in ./bin/. Either run it as ./bin/cordumctl or add ./bin to your PATH with `export PATH=$PATH:$(pwd)/bin`.
Frequently Asked Questions about Cordum MCP
What is Cordum MCP?
Cordum MCP 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 MCP?
Follow the installation instructions on the Cordum MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cordum MCP?
Cordum MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cordum MCP free to use?
Yes, Cordum MCP is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Cordum MCP Alternatives — Similar Security Servers
Looking for alternatives to Cordum MCP? 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 MCP 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 MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.