MCP servers and skills: search, filter by where they run, and compare.
Guarded MCP tools for AI-assisted mobile build, Appium testing, security scanning, verification, and fix-retest loops.
DockerMIT★ 11No key
Provider-neutral control plane for persistent AI agents with memory, skills, tools, evaluation, recovery, and governance.
SkillMIT★ 1Few starsNo key
Node.jsMITFew starsNo key
A production-grade AIOps framework focused on model integrity and autonomous reliability. Features a LightGBM-driven multiclass inference engine via FastMCP, validated against data leakage through NMI
SkillMIT★ 2Few starsNo key
Agent payment infrastructure MCP server — charge, refund, escrow, subscriptions, webhooks. 69 tools for autonomous agent payments.
PythonMITFew starsNo key
server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.
Node.jsMITFew starsNo key
Universal external interface engine for AI agents — 123 MCP tools, 18 protocols, Connection Souls, Intelligent Retry, Encrypted Vault
SkillMITFew starsNo key
The Customizable AI Framework that generates, validates, and optimizes production-ready Dockerfiles
PythonMIT★ 1Few starsNo key
Smoke-test MCP servers and write compatibility reports.
SkillMITFew starsNo key
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in co
SkillMIT★ 4Few starsNo key
Triage Gmail by provider with auto-generated labels and importable filters. Skill for Cursor / Claude Agent.
SkillGPL-3.0★ 5No key
AI-powered black-box web pentester. Give the URL, Suvari handles the rest.
SkillMIT★ 2Few starsNo key
Claude Code & MCP operational audit toolkit: scanner, workflow generator, hardening, Skills/hooks/automation reliability
Node.jsMITFew starsNo key
Standalone harness for structured-reasoning evals: register task suites, run any model callable, report accuracy, calibration, and failure taxonomy.
SkillMIT★ 1Few starsNo key
Turn recorded expertise into machine-actionable rules with a local LLM — plus a measured record of every way that LLM lied along the way.
PythonMIT★ 5No key
A control layer that decides how an LLM should speak before it speaks
Node.jsMITFew starsNo key
Turn your AI coding assistant into a DevOps-specialized agent using the CloudBees Unify MCP server. 7 ready-to-use skills for pipeline visibility, build triage, security scanning, release readiness, f
SkillApache-2.0★ 4Few starsNo key
Kiro Power for AWS Resilience Hub + Amazon ARC — GenAI failure-mode assessments, RTO/RPO validation, failover orchestration, and cost-quantified remediation reports, from the IDE.
SkillMIT★ 4Few starsNo key
PythonMIT★ 2Few starsNo key
Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.
SkillApache-2.0★ 5No key
Go orchestrator + Python tool servers MCP-style agent framework: 8 tools over JSON-RPC stdio, schema validation, retry classification, OTel tracing
PythonMIT★ 1Few starsNo key
Tool using agent and physics simulator that recommends thermal drift mitigation strategies for deep space photonic instruments across material and environment combinations. Runs on AWS Bedrock or a se
SkillApache-2.0★ 1Few starsNo key
MCP-A -- the MCP Answers Profile: a specialization of MCP that returns compiled, precise, structured answers. v1.0-beta.
SkillCC-BY-4.0★ 1Few starsNo key
Self-healing and drift recovery for agents. A zero-runtime-dependency TypeScript library and CLI that scores output confidence, detects ungrounded claims with GSAR-style typed grounding, monitors beha
Node.jsApache-2.0Few starsNo key
Who stands behind it
