Compliant LLM
Build Secure and Compliant AI agents and MCP Servers. YC W23
What is Compliant LLM?
Compliant LLM is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to build secure and compliant ai agents and mcp servers. yc w23
Build Secure and Compliant AI agents and MCP Servers. YC W23
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Build Secure and Compliant AI agents and MCP Servers. YC W23
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx compliant-llmConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Compliant LLM
Compliant LLM is a security and compliance platform (backed by YC W23) that lets you test and harden AI agents and MCP servers against real-world attack strategies including prompt injection, jailbreaking, and context manipulation. It evaluates your AI systems against industry frameworks such as NIST, ISO, OWASP, GDPR, and HIPAA, and supports a wide range of LLM providers via LiteLLM. Teams use it to validate agent security posture before deploying AI in regulated or sensitive environments.
Prerequisites
- Python 3.9 or higher installed
- pip package manager available
- An AI provider API key (OpenAI, Anthropic, Gemini, Mistral, Groq, or others supported via LiteLLM)
- An MCP client such as Claude Desktop or Claude Code
Install Compliant LLM via pip
Install the compliant-llm Python package globally using pip. This installs the CLI and dashboard tooling.
pip install compliant-llmLaunch the dashboard
Start the interactive Compliant LLM dashboard, which allows you to configure your LLM provider, set up test targets, and review results.
compliant-llm dashboardConfigure your LLM provider
Inside the dashboard, connect your AI provider (OpenAI, Anthropic, Azure, Ollama, etc.). Compliant LLM uses LiteLLM under the hood, so you provide the relevant API key for your chosen provider.
Run security and compliance tests
Select your target agent, MCP server, or prompt system and execute the security test suite. The platform runs 8+ attack strategies including prompt injection, jailbreaking, and context manipulation, then evaluates results against your selected compliance frameworks (NIST, ISO, OWASP, GDPR, HIPAA).
Review reports
After testing completes, review the generated compliance and vulnerability reports in the dashboard. Each finding includes the attack strategy used, the framework violated, and recommended mitigations.
Configure as an MCP server
Add Compliant LLM to your Claude Desktop or Claude Code MCP configuration so Claude can invoke security tests directly from your AI workflow.
npx compliant-llmCompliant LLM Examples
Client configuration
Add Compliant LLM to your Claude Desktop config. The server is invoked via npx.
{
"mcpServers": {
"compliant-llm": {
"command": "npx",
"args": ["compliant-llm"]
}
}
}Prompts to try
Once connected, use these prompts in Claude to trigger compliance and security analysis on your AI systems.
- "Run a prompt injection security test on my customer support agent"
- "Evaluate my MCP server against OWASP AI security guidelines"
- "Check if my AI system complies with GDPR requirements"
- "Run all 8 attack strategies against my current agent configuration"Troubleshooting Compliant LLM
Dashboard does not start after pip install
Ensure your Python environment is active and that pip installed the package to the correct environment. Try running 'python -m compliant_llm dashboard' as an alternative, or reinstall with 'pip install --upgrade compliant-llm'.
LLM provider connection fails during testing
Verify your API key is correctly entered in the dashboard. For Anthropic, the key should begin with 'sk-ant-'. For OpenAI it begins with 'sk-'. Check that your API key has sufficient permissions and quota.
To opt out of anonymized telemetry
Set the environment variable DISABLE_COMPLIANT_LLM_TELEMETRY=true before launching the dashboard: 'export DISABLE_COMPLIANT_LLM_TELEMETRY=true && compliant-llm dashboard'.
Frequently Asked Questions about Compliant LLM
What is Compliant LLM?
Compliant LLM is a Model Context Protocol (MCP) server that build secure and compliant ai agents and mcp servers. yc w23 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Compliant LLM?
Follow the installation instructions on the Compliant LLM GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Compliant LLM?
Compliant LLM works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Compliant LLM free to use?
Yes, Compliant LLM is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Compliant LLM Alternatives — Similar Security Servers
Looking for alternatives to Compliant LLM? 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 Compliant LLM 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 Compliant LLM?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.