MCP servers and skills: search, filter by where they run, and compare.
1–24 of 92 tools for “ai-assurance”
Clear allYour AI agent says it's done. Assurance tells you what it didn't check.
PythonApache-2.0★ 7No key
Assurance methodology for autonomous AI agents in regulated financial services
SkillCC-BY-4.0★ 3Few starsNo key
rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catch failures and vulnerabilities before they ship.
OfficialSkillApache-2.0★ 63No key
Loi Lemoine, simulateurs assurance emprunteur et statut produits (ORIAS 26000195).
Hosted by authorNo licenseFew starsNo key
Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
OfficialSkillMIT★ 40k in collectionNo key
Enterprise reference architecture for governed Agentic SOC, MSSP, MDR, Cloud IR, and private/local LLM-assisted DFIR operations.
PythonApache-2.0★ 4Few starsNo key
Free, local, IP-safe MCP server for AI-development security — commodity secret & credential checks from Netallion. Part of Agentic Development Governance.
PythonMITFew starsNo key
Read-only MCP gateway. Paid verify is $0.01 USDC on Base.
Hosted by authorNo licenseFew starsNo key
Prompt-regression and evaluation tracker with a local MCP interface. Compare prompts, keep evidence, leave the release decision to a human.
PythonMITFew starsNo key
Issue Planning and Automation prompt that generates comprehensive project plans with Epic > Feature > Story/Enabler > Test hierarchy, dependencies, priorities, and automated tracking.
OfficialSkillMIT★ 40k in collectionNo key
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce
OfficialSkillMIT★ 40k in collectionNo key
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assuranc
OfficialSkillMIT★ 376 in collectionNo key
Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.
OfficialSkillMIT★ 5.4k in collectionNo key
Agent Skills for traceable requirements, independent verification, human approval gates, and auditable AI-assisted engineering. Supports Claude Code, Cursor, VS Code, and GitHub Copilot; ISO 9001/2700
SkillCC-BY-SA-4.0★ 54No key
🧑🚀 The role layer for aerospace engineering agents — 39 draft roles binding 530 distinct Aero Agent Skills (605 bindings) across 12 domains, verified by 1625 offline tests, gated on 27 standards. E
Node.jsApache-2.0Few starsNo key
Skills-first Agent Plugin for bounded planning, routing, execution, and independent review—without CLI, MCP, server, or hidden runtime state.
Node.jsApache-2.0★ 3Few starsNo key
不是问答机器人，而是能真正干活的数字分身。共享智能体，共享项目上下文，让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中
SkillApache-2.0★ 633No key
Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.
Node.jsMIT★ 577No key
☸️ The Open Testing Platform for AI-Driven Engineering Teams
MCPLink only★ 1.7k
MCP bridge for Hermes Plant action safety, spend assurance, signed evidence, and deterministic x402 APIs.
Hosted by authorMIT★ 2Few starsNo key
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapp
PythonApache-2.0★ 477No key
Who stands behind it
