"OWASP Dependency-Check" matching MCP servers:

Local, zero-dependency memory MCP for AI agents: agents stage, you promote, every entry has a receipt.

Campaign orchestration MCP server for AI agents — dependency DAGs, parallel fan-out, failure policies, and embedded notes.

A zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.

Enables building and running zero-dependency MCP servers with automatic JSON Schema generation, exposing Python tools to Claude Desktop, Cursor, and autonomous agent fleets.

Code dependency graph and AI context engine. 10 MCP tools that give Claude, Cursor, and any MCP client full codebase context — impact analysis, dependency tracing, architecture summaries, and interactive arc diagram visualization. Supports TypeScript, JavaScript, Python, and Go.

A metacognitive pattern interrupt system that helps prevent AI assistants from overcomplicated reasoning paths by providing external validation, simplification guidance, and learning mechanisms.

Unchallengeable AI agent security audits. MASSAT framework covers all 10 OWASP Agentic Security categories (ASI01-ASI10); audit score 4.3/10 published publicly. Plus the trust layer for the x402 agent economy: ERC-8004 passports, ProofDB delegation chains, on-chain anchoring, x402 + Fedimint payments. Apache-2.0.

Enables AI assistants to check proposed actions against a local ledger of previously ruled-out work, receiving graded alerts with prior verdicts to avoid repeating dead ends.

Enables deterministic dependency reasoning over declared graphs, allowing users and AI agents to validate acyclicity, resolve targets, identify runnable parallel layers, assess impact, and explain blockers.

Enables local AI agents to communicate directly over Unix sockets, allowing multi-agent collaboration across different models and harnesses without any broker or network dependency.

Enables AI clients to programmatically build, validate, run, and test executable agent graphs as nodes and wires through local MCP tools, with SQLite storage and no cloud dependency.

A campaign and task management MCP server for AI coding assistants, enabling dependency tracking, acceptance criteria, testing strategies, and progress monitoring for projects.

Enables AI agents to cross-verify candidate claims against caller-supplied source texts, flagging hallucinations, numerical drift, entity mismatches, contradictions, and unverified assertions. It returns sentence-level verdicts with matched evidence snippets and machine-readable factual grounding confidence scores, exposed over MCP stdio, HTTP REST, and A2A discovery routes.

A security gateway that enforces policies, tracks data taints, and sandboxes tool calls between AI agents and MCP servers. It provides a secure chokepoint to prevent prompt injection and ensure OWASP ASI compliance through audit logging and deterministic execution.

Offline, zero-dependency tool-router for MCP that funnels N tools down to a ranked shortlist for a natural-language query, so the model reads ~8 tools instead of 200.

An MCP security trust-check server that evaluates component installation risks and provides safe-install decisions for autonomous agents.

Custom version of vibecheck

Enables AI agents to vet a developer's shipped products, check fixed pricing and availability, and submit project briefs on behalf of users.

Enables AI agents to check trustworthiness before recommending URLs, products, or organizations, with fail-closed pass/fail verdicts and attested-only recommendations.

Enables autonomous AI agents and penetration testers to conduct authorized security audits with persistent cross-session memory, zero-trust secret scrubbing, dynamic OWASP/ASVS checklists, and hallucination-free exploit PoC generation from captured traffic.