Skip to main content
Glama

🚧 SecPipe AI is under active development. Expect breaking changes and new features!


πŸš€ Overview

SecPipe AI is an open-source MCP server that enables AI agents (GitHub Copilot, Claude, etc.) to orchestrate security research workflows through the Model Context Protocol (MCP).

SecPipe connects your AI assistant to MCP tool hubs β€” collections of containerized security tools that the agent can discover, chain, and execute autonomously. Instead of manually running security tools, describe what you want and let your AI assistant handle it.

The Core: Hub Architecture

SecPipe acts as a meta-MCP server β€” a single MCP endpoint that gives your AI agent access to tools from multiple MCP hub servers. Each hub server is a containerized security tool (Binwalk, YARA, Radare2, Nmap, etc.) that the agent can discover at runtime.

  • πŸ” Discovery: The agent lists available hub servers and discovers their tools

  • πŸ€– AI-Native: Hub tools provide agent context β€” usage tips, workflow guidance, and domain knowledge

  • πŸ”— Composable: Chain tools from different hubs into automated pipelines

  • πŸ“¦ Extensible: Add your own MCP servers to the hub registry

🎬 Use Case: Firmware Vulnerability Research

Scenario: Analyze a firmware image to find security vulnerabilities β€” fully automated by an AI agent.

User: "Search for vulnerabilities in firmware.bin"

Agent β†’ Binwalk:  Extract filesystem from firmware image
Agent β†’ YARA:     Scan extracted files for vulnerability patterns
Agent β†’ Radare2:  Trace dangerous function calls in prioritized binaries
Agent β†’ Report:   8 vulnerabilities found (2 critical, 4 high, 2 medium)

🎬 Use Case: Rust Fuzzing Pipeline

Scenario: Fuzz a Rust crate to discover vulnerabilities using AI-assisted harness generation and parallel fuzzing.

User: "Fuzz the blurhash crate for vulnerabilities"

Agent β†’ Rust Analyzer:  Identify fuzzable functions and attack surface
Agent β†’ Harness Gen:    Generate and validate fuzzing harnesses
Agent β†’ Cargo Fuzzer:   Run parallel coverage-guided fuzzing sessions
Agent β†’ Crash Analysis:  Deduplicate and triage discovered crashes

⭐ Support the Project

If you find SecPipe useful, please star the repo to support development! πŸš€


✨ Features

Feature

Description

πŸ€– AI-Native

Built for MCP β€” works with GitHub Copilot, Claude, and any MCP-compatible agent

πŸ”Œ Hub System

Connect to MCP tool hubs β€” each hub brings dozens of containerized security tools

πŸ” Tool Discovery

Agents discover available tools at runtime with built-in usage guidance

πŸ”— Pipelines

Chain tools from different hubs into automated multi-step workflows

πŸ”„ Persistent Sessions

Long-running tools (Radare2, fuzzers) with stateful container sessions

🏠 Local First

All execution happens on your machine β€” no cloud required

πŸ”’ Sandboxed

Every tool runs in an isolated container via Docker or Podman


πŸ—οΈ Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                     AI Agent (Copilot/Claude)                   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                            β”‚ MCP Protocol (stdio)
                            β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                     SecPipe MCP Server                           β”‚
β”‚                                                                 β”‚
β”‚  Projects          Hub Discovery         Hub Execution          β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚init_project  β”‚  β”‚list_hub_servers  β”‚  β”‚execute_hub_tool   β”‚  β”‚
β”‚  β”‚set_assets    β”‚  β”‚discover_hub_toolsβ”‚  β”‚start_hub_server   β”‚  β”‚
β”‚  β”‚list_results  β”‚  β”‚get_tool_schema   β”‚  β”‚stop_hub_server    β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                            β”‚ Docker/Podman
                            β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                     MCP Hub Servers                             β”‚
β”‚                                                                 β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚ Binwalk   β”‚  β”‚   YARA    β”‚  β”‚ Radare2   β”‚  β”‚   Nmap    β”‚   β”‚
β”‚  β”‚  6 tools  β”‚  β”‚  5 tools  β”‚  β”‚ 32 tools  β”‚  β”‚  8 tools  β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚ Nuclei    β”‚  β”‚  SQLMap   β”‚  β”‚  Trivy    β”‚  β”‚   ...     β”‚   β”‚
β”‚  β”‚  7 tools  β”‚  β”‚  8 tools  β”‚  β”‚  7 tools  β”‚  β”‚  36 hubs  β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸ”§ MCP Security Hub

SecPipe ships with built-in support for the MCP Security Hub β€” a collection of 36 production-ready, Dockerized MCP servers covering offensive security:

Category

Servers

Examples

πŸ” Reconnaissance

8

Nmap, Masscan, Shodan, WhatWeb

🌐 Web Security

6

Nuclei, SQLMap, ffuf, Nikto

πŸ”¬ Binary Analysis

6

Radare2, Binwalk, YARA, Capa, Ghidra

⛓️ Blockchain

3

Medusa, Solazy, DAML Viewer

☁️ Cloud Security

3

Trivy, Prowler, RoadRecon

πŸ’» Code Security

1

Semgrep

πŸ”‘ Secrets Detection

1

Gitleaks

πŸ’₯ Exploitation

1

SearchSploit

🎯 Fuzzing

2

Boofuzz, Dharma

πŸ•΅οΈ OSINT

2

Maigret, DNSTwist

πŸ›‘οΈ Threat Intel

2

VirusTotal, AlienVault OTX

🏰 Active Directory

1

BloodHound

185+ individual tools accessible through a single MCP connection.

The hub is open source and can be extended with your own MCP servers. See the mcp-security-hub repository for details.


πŸ“¦ Installation

Prerequisites

Quick Install

# Clone the repository
git clone https://github.com/FuzzingLabs/secpipe_ai.git
cd secpipe_ai

# Install dependencies
uv sync
# Clone the MCP Security Hub
git clone https://github.com/FuzzingLabs/mcp-security-hub.git ~/.secpipe/hubs/mcp-security-hub

# Build the Docker images for the hub tools
./scripts/build-hub-images.sh

Or use the terminal UI (uv run secpipe ui) to link hubs interactively.

Configure MCP for Your AI Agent

# For GitHub Copilot
uv run secpipe mcp install copilot

# For Claude Code (CLI)
uv run secpipe mcp install claude-code

# For Claude Desktop (standalone app)
uv run secpipe mcp install claude-desktop

# Verify installation
uv run secpipe mcp status

Restart your editor and your AI agent will have access to SecPipe tools!


πŸ§‘β€πŸ’» Usage

Once installed, just talk to your AI agent:

"What security tools are available?"
"Scan this firmware image for vulnerabilities"
"Analyze this binary with radare2"
"Run nuclei against https://example.com"

The agent will use SecPipe to discover the right hub tools, chain them into a pipeline, and return results β€” all without you touching a terminal.

See the Usage Guide for detailed setup and advanced workflows.


πŸ“ Project Structure

secpipe_ai/
β”œβ”€β”€ secpipe-mcp/           # MCP server β€” the core of SecPipe
β”œβ”€β”€ secpipe-cli/           # Command-line interface & terminal UI
β”œβ”€β”€ secpipe-common/        # Shared abstractions (containers, storage)
β”œβ”€β”€ secpipe-runner/        # Container execution engine (Docker/Podman)
β”œβ”€β”€ secpipe-tests/         # Integration tests
β”œβ”€β”€ mcp-security-hub/        # Default hub: 36 offensive security MCP servers
└── scripts/                 # Hub image build scripts

🀝 Contributing

We welcome contributions from the community!

  • πŸ› Report bugs via GitHub Issues

  • πŸ’‘ Suggest features or improvements

  • πŸ”§ Submit pull requests

  • πŸ”Œ Add new MCP servers to the Security Hub

See CONTRIBUTING.md for guidelines.


πŸ“„ License

BSL 1.1 - See LICENSE for details.


Install Server
F
license - not found
A
quality
F
maintenance

Maintenance

–Maintainers
–Response time
2moRelease cycle
3Releases (12mo)
Issues opened vs closed

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

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/FuzzingLabs/secpipe'

If you have feedback or need assistance with the MCP directory API, please join our Discord server