"How to read PDFs and images" matching MCP servers:

Provides access to Atomic Red Team tests, enabling search, validation, and execution of atomic tests via natural language.

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.

A minimal, dependency-free MCP server that gives AI agents three real, read-only security-orchestration tools: cve_lookup, shodan_host_lookup, and nuclei_scan.

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.

Agent-PLC MCP Server: auto-detect, probe, read, write and diagnose Modbus TCP / FINS / MELSEC / Siemens S7comm PLCs, with transparent proxy and fault-injection listener.

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

Enables LLM agents to query SecurityTrails for DNS history, subdomain enumeration, WHOIS (current and historical), SSL certificates, and IPv4 intelligence via 17 read-only tools.

Publishes four flat, schema-light tools that let AI agents (including strict providers) search, describe, and invoke any of 139 reverse-engineering capabilities behind a persistent REA server. Enables file fingerprinting, inspection, and evidence-linked investigation of shipped software through plain-English requests, read-only by default.

Lets MCP clients browse bug bounty programmes, manage reports, and triage issues on BugSecure with user-approved OAuth permissions, including read-only mode.

Enables AI assistants to perform vulnerability scanning using Grype, supporting scans of directories, container images, and packages via the Model Context Protocol.

Enables AI assistants to query RoboShadow's Rubicon Platform Data API for read-only endpoint security, asset inventory, applications, users, vulnerabilities, and remediation status data.

Enables read-only interaction with YesWeHack hunter accounts via MCP, allowing consultation of programs, scopes, reports, and credits using email/password/TOTP authentication.

A local, read-only MCP server that connects your HackerOne researcher account to Claude Desktop and Claude Code, helping you find targets, analyze program scopes, review reports and earnings, and draft bug reports.

Living off the Land intelligence for AI agents. GTFOBins, LOLBAS, LOOBins, LOLDrivers, LOLRMM, WADComs, LOLC2 and more — unified into a single MCP server.

The most comprehensive steganography analysis toolkit for AI agents, providing 60 tools across 7 categories for detecting and extracting hidden data from images, audio, text, and files, all running 100% offline.

Enables structured robustness and security testing by scanning text for policy/safety issues and generating test suite outlines.

This MCP server lets an agent run local binary inspection on ELF, Mach-O, PE, APK, IPA, ASAR, WebAssembly, and firmware targets — pulling symbols, sections, classified strings, disassembly, and mitigation posture, and flagging dangerous imports and CWE patterns. It exposes eight stdio JSON-RPC tools (with no external API keys) that feed a multi-agent swarm for attack-surface mapping and exploit-chain synthesis.

Enables read-only interaction with HackerOne, providing tools for searching and analyzing reports, exploring programs and scope, accessing earnings, and retrieving public disclosures.

Enables read-only access to HackerOne Hacker API data including program policies, structured scopes, scope exclusions, hacktivity/prior art, and your own reports through MCP clients.

Enables agents to drive an end-to-end reverse-engineering loop on protected binaries: launch and dump live processes, rebuild memory images into file-aligned PEs with repaired imports, map Delphi RTTI methods, scan strings/entropy/xrefs, emulate code, and decompile through Ghidra or .NET. It also supports scripted live x64 and WOW64 debugging with breakpoints, registers, and module dumps exposed as callable tools.