- Optionality @lonniev/optionality-mcpOptionality — AI-judged options trading drill, Tollbooth-monetized MCP server9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- PuzzleTide @catorch/puzzletideWord search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Deep Agentic Core MCP @deepagentlabs/deep-agentic-core-mcpUnified MCP server for AgenticLens and Agentic Chaos capabilities.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ConvergeQA Compare (Due Diligence) @convergeqa/compareCompare one prompt across a multi-model panel side by side, with public verification receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Keel @tdalbanmoreynas/keelCatches your AI coding agent when it games the tests - locked-test hashes, tamper detection.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Scorecard MCP @scorecard/mcpMCP server providing access to the Scorecard API to evaluate and optimize LLM systems.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- LLMTest @tjacquesson/llmtest-mcpBenchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Hive A/B Test @srotzin/hive-mcp-abtestA/B experiment runner for the A2A network with x402 micropayments on Base USDC.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Hive Evaluator @srotzin/hive-mcp-evaluatorMCP server: NEED + YIELD + CLEAN-MONEY gates with EIP-3009 attestations · Hive Civilization9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- operant-mcp @saagpatel/operant-mcpRead-only MCP server for the OPERANT AI operating-agent calibration benchmark.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Vivarium @rongchang726-png/vivariumA science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Qwen MCP @rocnubie/chat-mcpQwen AI Chat guide to Qwen3.6-Plus and qwen3.6-flash with practical notes on 1M context, coding7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- DeepSeek FR MCP @rocnubie/deepseekfr-mcpIndependent French workspace for evaluating DeepSeek-V3-class chat and DeepSeek-R1 reasoning.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Golden Dataset @nipunkhanderia/golden-dataset-mcpVersion-controlled golden datasets and RAG evaluation, no API key needed.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Replay @mdfifty50-boop/agent-replayRecord and replay AI agent execution for debugging6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Qc Validator @mdfifty50-boop/qc-validatorOutput quality control and validation for AI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Audit @joepangallo/mcp-audit-serverThin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cowork Qa @insideos-designs/cowork-qaGoal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AI Workbench MCP @hrishikesh-thakre/ai-workbench-mcpGoose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Codabench @harshitagr/codabench-mcpMCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- redline @gowtham0992/redlineRun local prompt regression checks from prompt-response logs in AI coding assistants.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Eval Runner @dbsectrainer/mcp-eval-runnerA standardized testing harness for MCP servers and agent workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Engine @cicicalex/engineAIN bias & stability engine: finance, gaming, AI, crypto. 68 tools across 11 categories.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Modelwatch @bch1212/modelwatchContinuous behavioral drift monitoring for LLM apps — catches silent provider model updates.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
