by 61960005qq
AIShield - OWASP MCP Top 10 aligned security scanner. Scan MCP servers, detect tool poisoning, prompt injection, and supply chain risks.
npm:aishield-mcp-server · local package227/wkpublished 9 d ago
Model access, evaluation and agent infrastructure.
AIShield - OWASP MCP Top 10 aligned security scanner. Scan MCP servers, detect tool poisoning, prompt injection, and supply chain risks.
Governed AI development workflows that turn natural-language intent into specifications, tested code, reviews, documentation, and shippable pull requests.
MCP server providing multi-advisor AI consultations via OpenRouter API with advanced caching, rate limiting, and security features
Model Context Protocol server for CogniLead — tools (draft_pitch, score_signal, check_deliverability, ingest_lead, run_campaign, suppress, generate_seo_content), Resources (sends, suppressions, warmed-pool, docs), and Prompts (cold-outbound-sequence, deli
Operating contracts for AI agents. Structured instructions compiled into system prompts.
Compress your AI agent's context and prove its decisions don't change — cache-aware, reversible, certified. JS/TS bridge to the distil CLI + proxy helpers.
Eval-backed discovery for the auxiliar.ai gateway — the best web-access provider per job, measured.
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
MCP server for WebVector: webvector_research (search → read full pages → rank → cited passages), webvector_fetch, webvector_search. Zero-config `npx -y webvector-mcp` (~12 MB, lexical); add @huggingface/transformers or an API key for semantic search.
Model Context Protocol server for ZeroBounce email validation, verification, and intelligence. Provides comprehensive email validation, AI scoring, email finder, domain search, and bulk processing capabilities for AI coding assistants.
Free MCP server for developers adding human review gates, prompt risk checks, FAQ review, and CRM note safety to AI tools.
A simple Spec-Driven Development (SDD) for AI-agent-assisted project workflows.
MCP server exposing public instruction workflows as tools, backed by hidden AI agent skills for requirements, orchestration, quality, research, evaluation, governance, resilience, and physics-inspired analysis
ARGUS-3 stdio MCP with WARDEN firewall: argus_ask, argus_status, argus_capabilities.
Bounded MCP tools, resources, prompts, client callbacks, and authorized Streamable HTTP sessions.
Voyager — the verified-brief organ for coding agents: turns a query into a cited, confidence-scored, OSV-gated, injection-hardened brief, never a raw web response. CLI, library, and MCP server.
Scan a project for leaked secrets, risky MCP configs, and unsafe automation before handing it to an AI coding agent (Claude Code, Cursor, Codex). Zero dependencies, runs locally.
Combines hiring and tech-stack signals into one composite GTM score. Clay-ready output.
Offline security scanner for Node web apps and AI coding agents. OWASP rules with framework-specific fixes for 12 stacks, plus .claude/.cursor/.vscode config scanning. No telemetry.
The governed agent operating system that turns rough product ideas into approved requirements, specifications, delivery, and evidence-backed software.