"Coolify - An Open-source Self-hosting Platform" matching MCP servers:

Enables an AI agent to reverse-engineer a compiled program with Ghidra — inspecting decompiled code, instructions, callers, memory bytes, and strings — without any source code. Every reply is labelled as fact, computed, or guess, and each claim traces back to hash-checked saved evidence.

Wraps multiple bug bounty platform APIs (HackerOne, Bugcrowd, etc.) behind a uniform MCP tool surface, enabling LLM agents to query programs, scope, and briefs across platforms through a single interface.

Connects AI assistants to the watchTowr Platform for real-time access to external attack surface data, findings, and threat intelligence. Provides 113 tools for querying and managing assets, findings, hunts, and more.

Enables static AST-based dataflow analysis to trace untrusted sources to sensitive sinks, supporting automated code review and security auditing through MCP.

Enables static AST-based taint flow tracing from untrusted sources to sensitive sinks, supporting AI code review and security analysis via MCP.

Enables AI assistants to search and analyze vulnerabilities and exploits from multiple intelligence sources, including NVD, CISA KEV, ExploitDB, Metasploit, and more, with tools for CVE research, exploit analysis, and report generation.

Enables AI assistants and agents to search bug bounty programs, retrieve policies and scopes, and check targets against active scope across HackerOne, YesWeHack, and Intigriti using personal API credentials.

AI-powered security scanning MCP server that exposes 25+ professional tools, enabling penetration testing and security assessments through natural language interaction with AI agents like Claude Desktop.

Enables AI assistants and security analysts to inspect PCAP/PCAPNG captures through MCP tools or REST endpoints, reassembling TCP/UDP streams, extracting payload artifacts, detecting CTF flags, credential leaks and network anomalies, and generating formal PDF or Markdown forensic reports. Every finding is bound to exact frame numbers, timestamps and endpoints with SHA-256 deduplicated evidence provenance.

Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.

MCP server for AgentMinds collective intelligence platform, enabling AI agents to scan websites for security/SEO/performance issues, pull personalized recommendations, and share findings across the network.

An MCP server that lets an AI agent probe a live URL and confirm whether sensitive files (e.g., .git, .env, source maps) are genuinely served by fetching and validating the content, avoiding false positives.

Exports vulnerability and asset data from Rapid7 Command Platform via the Bulk Export API into a local DuckDB database, enabling AI assistants to run natural language queries and SQL analysis with sandboxed security.

Offers a control surface for AI agent security with four independent checks: source-code scanning, tenant isolation, LLM content verification, and deploy gating. Currently in pre-release, with no functional scanning engines yet.

Enables AI coding assistants to scan projects for security issues such as leaked API keys, missing Supabase RLS, open Firebase rules, unauthenticated routes, and hallucinated packages, then fix and verify the results.

Open behavioral litmus for MCP servers — grades A–F across tool-output injection, egress, sensitive-data, and adversarial-input, with reproducible, content-addressed evidence. Tools: run_litmus, verify_attestation.

14 atomic MCP tools for AppSec and AI Security engineers: source/schema/prompt audit primitives, JWT inspect, HTTP diff, pentest atoms (default creds, GraphQL introspect, phpggc, interactsh OOB), and a defensive helpers library that fixes the bugs the detectors flag. SARIF output, PyPI Trusted Publishing with Sigstore provenance.

Self-hosted MCP engine for private code reviews, providing deterministic static analysis and AST-level search over diffs, with findings passed to a review agent of your choice.

MCP server that enables Claude Code to drive the Konsulto cybersecurity audit platform from the CLI, including reading and writing findings, managing evidence, and handling scope and assets.

Connects an AI assistant to an already-running mitmweb session so it can read, search, diff, replay, and generate code from the same network flows shown in the UI.

MCP server that guides LLM security reviews step-by-step, tracking progress and ensuring all assigned source code is read before completing each plan step.

Gives AI assistants access to the Exploit Intelligence Platform for vulnerability and exploit intelligence. Supports searching CVEs, exploits, and generating pentest findings.

An MCP server that audits zero-knowledge circuits (Circom, Noir, Halo2) for soundness and constraint bugs, powered by the Cysic Minimax model.

Enables interaction with NowSecure Platform for listing applications, retrieving remediation findings, and generating remediation PDFs via REST and GraphQL APIs.

Enables AI assistants to vet open-source repositories and dependencies by running OpenSSF Scorecard, Trivy, and Syft checks for repository health, vulnerabilities, licenses, and SBOMs, with background jobs and status polling.

MCP server integrating Rizin reverse engineering, RzGhidra decompiler, and capa for binary analysis, enabling LLMs to open binaries, identify capabilities, extract function addresses, and decompile to C pseudocode.

Lets an AI assistant drive a self-hosted Sn1per install over local stdio, launching orchestrated scans and reading back structured findings, ports, subdomains and technologies. Enforces configured target scope, redacts secrets, and writes an audit log of every scan, cancel, delete and export request.

Penthera checks your repo, dependencies, AI agent config (hooks, MCP servers, skills) and your own live site, on your machine. Rules decide every finding; a model never does. Your agent gets a short brief: what to act on, what to check first, what's likely noise and what wasn't checked. Free and open source (MIT), offline by default, no account, no telemetry.

Enables MCP clients to launch authorized autonomous penetration tests, monitor run status, list campaigns, and retrieve vulnerability findings and severity statistics from a self-hosted dashboard API.

Enables interaction with the APVISO AI-powered penetration testing platform to manage targets, initiate scans, and retrieve vulnerability findings. It allows developers to integrate security testing workflows directly into MCP-compatible tools like Claude Code and Cursor.

Connects MCP-compatible AI clients to a MITRE Caldera adversary emulation platform, enabling natural language construction of attack scenarios, agent inspection, and operation management.

Enables AI coding tools to unpack WeChat Mini Program packages, capture requests, analyze signature and encryption parameters, and export self-contained local Node.js signing scripts for authorized security analysis and API integration.

Safe, self-hosted OWASP ZAP operator for guided AI security scans, findings, and reports. Requires a separately running OWASP ZAP daemon.

A Model Context Protocol (MCP) server for the YesWeHack bug bounty platform that lets Claude query private and public programs, reports, and the hacktivity feed directly from a conversation.

An MCP server that exposes Prof. Null, an uncensored cybersecurity professor, as a set of specialized tools for learning hacking, CTFs, and security concepts through Q\&A, roadmaps, cheatsheets, labs, and more.

Exposes a pentest toolbox (sqlmap, nuclei, ffuf, etc.) via Docker to an LLM orchestrator for authorized security audits, with strict whitelisting and timeout controls.

Enables users to deterministically audit MCP servers for security issues across manifests, source, runtime responses, multi-call state, identity, and install scripts, and to run an inline gateway that gates tool calls and scans responses before returning them.

Keeps bug-hunting AI agents within an authorized scope by checking every target against declarative allow/deny rules, refusing out-of-scope findings, and scrubbing secrets from evidence. It also computes CVSS v3.1 base scores and records findings in an append-only ledger.

CyberSecurity MCP Server extends Claude with real-time cybersecurity reconnaissance capabilities that Claude doesn't have by default. Instead of manually running 5 different tools across different terminals, just tell Claude "analyze google.com" and get a complete security breakdown instantly. Tools included: * WHOIS Lookup — registrar, ownership, creation/expiry dates * DNS Enumeration — A,

Enables MCP-compatible agents to query structured penetration testing engagement state captured from tmux sessions, including credentials, hosts, and command provenance with exact source bytes.