Search

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

MCP server for autonomous API logic penetration testing — OWASP API Top 10 / BOLA-IDOR detection via LLM-driven analysis

Unbranded, free MCP (Model Context Protocol) server verifier — detects tool poisoning, typosquats, hidden unicode, base64 payloads, exposed transports, and skill-manifest attacks. Same engine as the VyriAI control plane, no account required.

Hosted CVE-intelligence MCP: exploitation-first ranking and a fact-checker for hallucinated CVEs

Tenuo TypeScript SDK — authorization decisions run in the Rust core (WASM).

Measure whether an LLM gateway sends raw personal data to its upstream, and whether it restores it in the response.

Three-layer firewall for MCP servers — content inspection, egress policy and action policy. Catches prompt injection, tool poisoning, exfiltration and leaked secrets before they reach your agent.

MCP server inventory and risk scanner. Implements ACRF-03 defense pattern.

A firewall for LLM traffic: detect prompt injection, jailbreaks, and secret/PII leaks. Zero-dependency Python library + CLI + MCP server.

Test that a streaming redactor or LLM guardrail cannot leak a secret split across chunks.

Modality MCP Kit - Schema conversion utilities for MCP tool development with multi-library support

An API server that implements the official MCP Registry API, providing standardised access to MCP servers from multiple backends, including file-based and other API-compliant registries.

A Model Context Protocol server for Shodan API queries.

An MCP server that is the strongroom control plane: its tools mint scoped, expiring, revocable leases and hand agents a lease-backed base URL — so API keys never enter agent context. Part of Own Your Stack.

Feature-rich MCP server for Black Duck Polaris — trigger SAST/SCA/DAST scans, query findings, generate reports (SBOM, SPDX, CycloneDX), manage policies, triage issues, and more. Works with Claude Code, Claude Desktop, GitHub Copilot, Cursor, and any MCP-c

Cryptographic execution evidence for AI-agent tool calls: signed manifests, admission decisions, and tamper-evident receipts.

Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration

Static documentation generator based on docco

A drop-in MCP proxy that makes the lethal trifecta structurally impossible.

Zero-trust, risk-aware gateway proxy for the Model Context Protocol