- Elite Reasoning @snehgabani/elite-reasoning-mcpEvidence-gated verification, selection, and measurement MCP for coding agents.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Rules MCP @akr1166/rules-mcpMCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Dungbeetle MCP @dungbeetle/mcpVisual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Arc Security @arcself/arc-securityScan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- TypeSafe Jev @perrylink/jevcoreMCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SandboxAPIs @sandboxapis/mcpDrop-in read-only replicas of GitHub, Jira, Slack and 18 more, preloaded with one fake company.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Tada: automated QA for AI-written code @taada/tadaYour coding agent asks Tada to work through a feature in a real browser and gets back a verdict.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Canary @dorianchn/agent-canaryFree V1: inert MCP decoys and canary tokens detect AI-agent compromise signals. Local stdio server.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- DidWork @didwork/didworkVerify that an agent's claimed outcome actually happened, using independently gathered evidence5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Assurly MCP @assurly/mcp-serverPre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Laserbrain @degibug-del/laserbrainThe drift harness as an MCP server. Offline, no key — a fixed reference an agent checks against.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Evalgate @ipezygj/evalgateStatistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Sheetspec @helloo1568/sheetspecContract testing and quality gates for spreadsheets created by AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BugBrain MCP @bugbrain/mcpBugBrain QA platform for AI coding tools: autonomous exploratory testing, test plans, a11y audits.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Openclaw Output Vetter @temurkhan13/openclaw-output-vetter-mcpVerify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Model Radar @srclight/model-radarPing 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Braintrust @braintrustdata/braintrustAI evaluation and observability platform — query experiments, logs, datasets, and prompts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Agent Security Scanner @mikehzp/agentvulnScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- agent-check @basenull/agent-checkProcess monitoring for AI agents: start runs, submit per-task evidence, complete runs.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- APIThreshold @apithreshold/apithresholdQuality scoring and progressive gates for AI-generated API tests. Stripe/Twilio profiles. Free tier.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
