absec-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@absec-mcpReview my staged changes for vulnerabilities"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
absec-mcp
Production MCP server for Cursor / VS Code Copilot — review diffs and files with the same absec rule IDs as CI.
By Agent Breach. Complements Agent Breach DAST. No account required. Not a pentest.
60-second win (Cursor)
Add to .cursor/mcp.json:
{
"mcpServers": {
"absec": {
"command": "npx",
"args": ["-y", "@agentbreach/absec-mcp@0.1.0"],
"env": {
"ABSEC_WORKSPACE": "${workspaceFolder}"
}
}
}
}Then ask the agent: “Run absec review_diff on staged changes.”
Related MCP server: SnapBack MCP Server
VS Code Copilot Chat (MCP)
Same npx command in MCP settings. Tools appear as review_diff, review_file, etc.
Tools
Tool | Purpose |
| staged / unstaged / all changed files |
| one path (workspace-sandboxed) |
| batch scan (capped) |
| rule catalog / CWE / fix |
| unified-diff preview (does not write) |
| catalog |
Suppress with # absec-ignore: ABSEC-JWT-001 or project absec.config.json.
Safety
Local rule engine only (no Agent Breach cloud)
Refuses path escape and secret-like filenames (
.env,*.pem)Redacts secret snippets in findings from
@agentbreach/absec-core
License
Apache-2.0 © Agent Breach
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-quality-maintenanceEnables security scanning of code projects to identify common vulnerabilities like XSS, injections, SSRF, and path traversal issues. Provides local, offline scanning with severity-grouped results and actionable fix suggestions for improving code security.Last updated38
- Alicense-qualityBmaintenanceEnables AI-powered code safety analysis including risk detection, secret scanning, dependency checking, and code snapshot management. Works offline for basic features with optional cloud integration for advanced ML analysis and team collaboration.Last updated81Apache 2.0
- Flicense-qualityBmaintenanceSecurely feeds summarized expert security rules into your coding assistance Claude Code, Cursor, etc — zero config, no API key.Last updated
- Alicense-qualityAmaintenanceEnables AI coding tools to scan projects for security vulnerabilities, hardcoded secrets, injection flaws, and privacy violations with 699 rules and 76 MCP tools, all running locally with zero telemetry.Last updated464MIT
Related MCP Connectors
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Threat modeling, code/cloud/pipeline scanning, shadow-AI discovery, compliance checks and fixes.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AgentBreach/absec-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server