"OCR agent" matching MCP servers:

Security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.

Enables users to scan AI agent skills and configuration files for hidden Unicode instructions, prompt injection, download-and-execute payloads, exfiltration patterns, and overly broad permissions before installation. It provides static audit tools for skill files, agent configs, and revealing hidden text without executing or fetching the input.

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.

Agent-native "safe to ship?" security gate for AI-generated code. Uses real parsers and inter-rocedural taint analysis (JS/TS, Python, Go) to flag the classes AI coding agents get wrong — secrets, SQL injection, SS, SSRF, path traversal, command injection, weak JWT/CORS — and ranks findings by confidence. Exposes a scan tool over MCP.

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.

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.

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.

Provides security audit primitives for MCP servers, agent tool schemas, and system prompts, along with pentest utilities like JWT inspection and HTTP diffing.

Two-way Burp Suite MCP bridge enabling AI agents to capture traffic, analyze endpoints, queue scans, and send findings back to Burp.

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 interaction with Picus Security's Breach & Attack Simulation API, allowing natural language queries for simulations, threat library searches, and agent management through MCP-compatible clients.

A security gate MCP server that audits agent extensions (skills, MCP servers, tools) by scanning for risks, adversarial analysis, and sandbox execution, returning a trust verdict of allow, quarantine, or block.

Enables MCP-native multi-agent security audits for Google Antigravity, orchestrating subagents for 0day research, static analysis, PoC verification, exploit chaining, reporting, and code remediation.

A read-only MCP server that lets an agent browse the HackerOne Hacker API using an authenticated hacker account, exposing programs, policies, scope, reports, and payments. It cannot create, update, or submit reports.

Security scanning for AI coding tools (Claude Code, Cursor, Windsurf) including secrets detection, MCP config vulnerabilities, agent instruction checks, threat modeling, prompt injection testing, pre-commit security checks, and dependency vulnerability scanning.

A MCP-enabled asset mapping and vulnerability scanning agent with AI self-reflection, allowing natural language queries and automated scanning decisions.

Performs static security analysis of Solana programs and generates x402 payment invoices for automated agent-to-agent audit workflows.

A security scanner for AI coding agents and autonomous assistants that scans code for vulnerabilities, detects hallucinated packages, blocks prompt injection, and provides LLM-powered semantic code review via MCP or CLI.

An intentionally vulnerable MCP server for security training, simulating a fictional company with 28 vulnerable tools and 38 challenges to learn AI agent attack and defense.

Wraps the recon CLIs security researchers already use (subfinder, httpx, nmap, ffuf, nuclei) into a single MCP server so an LLM agent can plan and execute reconnaissance itself — passive subdomain/DNS/wayback discovery, active port scanning, WAF detection and origin-bypass checks, endpoint fuzzing, and nuclei scans. Structured JSON results carry scan tokens that let the agent chain one step's output into the next without re-typing targets.