ZeroPath MCP Server
Interact with your product security findings using natural language.
ZeroPath MCP Server
Interact with your product security findings using natural language.
This open-source MCP server allows developers to query SAST issues, secrets, patches, and more from ZeroPath directly inside AI-assisted tools like Claude Desktop, Cursor, Windsurf, and other MCP-compatible environments.
No dashboards. No manual ticket triage. Just security context where you're already working.
Blog Post
Learn more about why we built this and how it fits into the evolving AI development ecosystem:
📄 Chat With Your AppSec Scans: Introducing the ZeroPath MCP Server
Installation
1. Generate API Key
Generate an API key from your ZeroPath organization settings at https://zeropath.com/app/settings/api
2. Configure Environment Variables
Set up your environment variables with the API key:
export ZEROPATH_TOKEN_ID=your_token_id
export ZEROPATH_TOKEN_SECRET=your_token_secret
3. Retrieve Your Organization ID
Run the following command to get your organization ID:
curl -X POST https://zeropath.com/api/v1/orgs/list \
-H "X-ZeroPath-API-Token-Id: $ZEROPATH_TOKEN_ID" \
-H "X-ZeroPath-API-Token-Secret: $ZEROPATH_TOKEN_SECRET" \
-H "Content-Type: application/json" \
-d '{}'
4. Install uv
We use uv for dependency management:
curl -LsSf https://astral.sh/uv/install.sh | sh
5. Clone and Setup
git clone https://github.com/ZeroPathAI/zeropath-mcp-server.git
cd zeropath-mcp-server
uv sync
export ZEROPATH_ORG_ID=your_org_id
Configuration
Add this entry to your MCP config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"zeropath-mcp-server": {
"command": "uv",
"args": [
"run",
"--project",
"<absolute cloned directory path>/zeropath-mcp-server",
"<absolute cloned directory path>/zeropath-mcp-server/main.py"
]
}
}
}
Replace <absolute cloned directory path> with the absolute path to the repo.
Environment Variables
Before running the server, export the following:
export ZEROPATH_TOKEN_ID=your_token_id
export ZEROPATH_TOKEN_SECRET=your_token_secret
export ZEROPATH_ORG_ID=your_org_id
These can be generated from your ZeroPath dashboard.
Available Tools
Once connected, the following tools are exposed to your AI assistant:
search_vulnerabilities(search_query: str)
Query SAST issues by keyword.
Prompt example:
"Show me all SSRF vulnerabilities in the user service."
get_issue(issue_id: str)
Fetch full metadata, patch suggestions, and code context for a specific issue.
Prompt example:
"Give me the details for issue
abc123."
approve_patch(issue_id: str)
Approve a patch (write action). Optional depending on your setup.
Prompt example:
"Approve the patch for
xyz456."
Development Mode
Use ./dev_mode.bash to test the tools locally without a client connection.
Contributing
We welcome contributions from the security, AI, and developer tools communities.
- Found a bug? Open an issue
- Want to improve a tool or add a new one? Submit a pull request
- Have feedback or questions? Join us on Discord
Related Servers
Rubber Duck MCP
A tool that applies rubber duck debugging techniques to AI development environments.
MCP Java Bridge
A bridge for the MCP Java SDK that enables TCP transport support while maintaining stdio compatibility for clients.
WOOFi Pro
Provides over 40 comprehensive trading tools for WOOFi Pro and Orderly Network integration.
GDB MCP Server
An MCP server that enables LLM clients to interact with GDB for debugging and binary analysis.
Website Generator MCP
An example MCP server designed for deployment on Cloudflare Workers, supporting both remote and local setups.
Code Summarizer
A command-line tool that summarizes code files in a directory using Gemini Flash 2.0.
DeepSeek-Claude MCP Server
Enhance Claude's reasoning capabilities by integrating DeepSeek's advanced engine.
Tencent Cloud Code Analysis
An official MCP server for Tencent Cloud Code Analysis (TCA) to quickly start code analysis and obtain reports.
Image MCP Server
An MCP server for AI image generation using OpenAI and Replicate APIs.
mcp-graphql
A GraphQL server that supports the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with GraphQL APIs through schema introspection and query execution.