"How to use Canva" matching MCP servers:

Security for the MCP servers you use: detects tool poisoning, rug pulls, shadowing, secrets and supply-chain risk (OWASP MCP Top 10), with runtime guards and approved-server policy. Runs locally.

Enables AI agents to perform read-only forensic triage of Windows disk images over MCP stdio, currently offering MD5/SHA-256 hash calculation and verification confined to an evidence root. Every returned finding carries six-field provenance metadata, while a code-enforced security contract guarantees read-only evidence access, no network or shell use at runtime, structured errors, and an append-only JSONL audit trail.

Connects AI assistants to AttackForge's Self-Service API with full endpoint coverage, response size optimization, and local caching for efficient use in long conversations.

Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.

A self-hostable, vulnerable-by-design MCP server for learning how object-level authorization bugs (BOLA/IDOR) appear in multi-tenant tools.

Enables AI agents to perform pay-per-call security verification of wallets, tokens, contracts, dApps, agents, and more via a remote endpoint with no installation.

Enables grading a website's security headers with per-gap fixes and a README badge, and analyzing logs, code, configs or suspicious messages to determine what happened, how severe it is, and what to fix first. Requests are masked for sensitive data and automatically retried across multiple AI providers when one refuses, subject to a defensive-use-only policy.

Provides DNS and network-reconnaissance tools that let agents run lookups for records, reverse DNS, ping, passive subdomain discovery, shared nameservers, geolocation, reverse IP, ASN, HTTP headers, subnet arithmetic and page links, plus key-gated WHOIS, MTR and traceroute. Responses are parsed into structured JSON with verbatim raw text, and it runs either through a hosted gateway or as a local stdio server.

Enables AI coding agents to audit Supabase or Postgres databases for Row Level Security and multi-tenant isolation holes, reading tables, grants, policies and functions for static findings and optionally probing those policies inside a rolled-back transaction. It reports each hole with an explanation and a fix, so an agent can verify the migrations it just wrote before declaring them done.

Connects MCP clients to a Kali Linux terminal for executing security tools and commands, enabling AI-assisted penetration testing and CTF solving.

Enables AI assistants to drive OWASP ZAP for authorized penetration testing and bug-bounty workflows, including authenticated scans and vulnerability triage through 67 curated safety-gated tools.

A stateful debugging and binary research system for LLM agents, integrating GDB + pwndbg with MCP for deterministic exploit workflows and multi-session support.

Enables AI agents to dynamically instrument Android and iOS apps through Frida 17, exposing 40 tools for exploring apps, hooking Java/ObjC/native methods, tracing calls, bypassing SSL pinning, capturing TLS keys and plaintext, and inspecting memory. Results use Ghidra/IDA-style module+offset addresses and carry an evidence envelope, with optional UI automation through mobile-mcp.

Enables authorized AI pentest agents to use typed HTTP, DNS, TCP, TLS, and finding tools through a scope-enforcing gateway that quarantines hostile target content and records hash-chained evidence.

Enables querying aggregated vulnerability records from CIRCL's Vulnerability-Lookup, resolving IDs across multiple feeds such as MITRE CVE, NVD, GitHub Security Advisories, PySec, and vendor CSAF, with tools for lookup, search, and recent records.

An MCP server that measures how effectively hashing tool definitions detects unauthorized changes, evaluating 20 policies across field sets and canonicalization methods. It demonstrates that approval-dialog-based pins miss most attacks, with structural/semantic normalization being free but text folding trading detection for fewer false alarms.

Enables AI clients to calculate, explain, and inspect CVSS 4.0 vectors and metrics through local stdio or authenticated hosted MCP connections, supporting private severity assessments.

A proxy server that wraps any MCP server, adding behavioral profiling, security scanning, risk gating, and safe execution to its tools.

Enables AI agents to plan and run authorized offensive security assessments across 150+ integrated tools, with full activity logging of every scan.

Enables AI assistants to analyze and manipulate Unity IL2CPP applications via Frida, supporting disassembly, class/method listing, and heap analysis.

Enables AI coding agents to audit websites for PHP runtime vulnerabilities, compile a live Zero-PHP Next.js App Router replacement preview from a WordPress/PHP site, and retrieve remediation guidance.

Generates syscall code (C, C++, Rust, NIM) using various hooking methods, and includes an MCP server for AI assistants to produce syscall stubs.

Enables AI agents to look up known open-source vulnerabilities in the OSV.dev database, covering individual packages and versions, specific git commits, single vulnerability IDs, and batch SBOM-style dependency scans. Queries are keyless and return compact summaries or full vulnerability details with affected ranges and references.

Enables searching and retrieving public vulnerability reward program directory data across Bugcrowd, YesWeHack, and HackerOne, including bounty ranges, scope assets, launch dates, and wildcard eligibility.

A rogue MCP server (~90 lines) that demonstrates prompt injection via tool responses to achieve remote code execution on a developer's machine.

Enables MCP-compatible agent hosts to delegate governed, read-only security audits and reviews of code, applications, agents, prompts, MCP configurations, and cloud environments through evidence-first findings and stable schemas.

Enables AI agents to perform internet reconnaissance through the Shodan and CVEDB APIs — searching internet-connected devices, inspecting host ports, banners, TLS certificates and DNS records, and pulling CVE, CPE, EPSS and KEV vulnerability intelligence. Supports both stdio and HTTP streaming transports for use with Claude Code, Codex, Gemini CLI and Claude Desktop.

AI-orchestrated security testing via 6 Python tools (recon, port scan, subdomain hunting, frontend scanning, API fuzzing, and nemesis orchestrator) exposed as MCP tools for use by AI agents.

Enables AI agents to control and analyze RFID hardware through natural language: read, crack, emulate, and clone cards via MCP tools, with safety gates, offline dump analysis, and a host-side card library.

Enables AI assistants to perform Volatility 3 memory forensics through natural language, including process and network analysis, injection detection, and shellcode extraction from memory dumps.

MCP server for Frida dynamic instrumentation, enabling AI agents to enumerate devices/processes, attach, inject JavaScript, hook functions, read memory, and collect results via MCP tools.

Enables scanning any website's HTTP security headers to obtain Mozilla Observatory grades, detailed pass/fail test results with remediation guidance, and grade distribution context.

Connects LLMs to a Kali Linux host over SSH for authorized penetration testing, exposing tools organized by pentest phases (recon, enumeration, exploitation) with scope guardrails.

Enables agents to probe a live host's TLS handshake, read the actual SubjectPublicKeyInfo from the served certificate, and corroborate that exact key against Certificate Transparency logs to learn how long it has been harvestable. Exposes typed tools for ranking watches by urgency, recording triage decisions, replaying audit chains, and exporting OpenSSL migration configs, runbooks and sealed JSON dossiers.

Enables searching past scans and submitting URLs for scanning via urlscan.io, with both keyless and key-based operations.

Enables querying OWASP security standards, including Top 10 lists for web, API, LLM, and mobile, ASVS 5.0 verification requirements, and defensive cheat sheets via MCP tools or plain-language questions.

Enables querying Shodan InternetDB for IP address intelligence, such as open ports, services, and vulnerabilities, through natural language.

Enables MCP clients to inspect and automate a running binary-analysis session, with tools for program, memory, function, and listing operations.

Wraps common web penetration testing tools in a Docker container and exposes them as Claude tools for educational use in controlled lab environments.

Enables querying the CVE-Search API to browse vendors and their products, retrieve vulnerabilities for a vendor/product pair, look up individual CVE IDs, and fetch the latest 30 CVEs with CAPEC, CWE and CPE expansions. It also reports which databases are in use and when they were last updated.