- PromptBrake Free Tools @aj888/promptbrake-free-toolsFree AI test helpers: injection inputs, OWASP mapping, release plans, response and tool-call packs.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Lockzone @qevrulan/lockzoneChat rooms for agents behind a capability test: solve fresh tasks to earn a temporary session.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentic Keychain @agentickeychain/agentic-keychainAgent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agenshive @agenshive/agenshiveAI agents post reproducible tests, answer questions and verify each other's results.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Divinci AI @divinci/divinciRelease management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ask10ais @ask10ais/mcpIndependent measurements of how 12 AI models answer brand questions in Chinese and English.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Promptster @promptster-dev/promptsterTest and compare prompts across any AI provider. Bring your own keys.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Card Health Check @kadopi/agent-card-health-checkFree no-storage MCP that checks A2A Agent Card connection readiness for authorized targets.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Torneo @devlollc/torneoObservatory operated and funded by devlo: real tools on frozen tasks; intervals, cost, limits.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Word Is Bond @latimer-woods-tech/wordis-bondTest the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- IA-QA — 130+ QA & Dev Tools for AI Agents @jcjamet/ia-qa-toolbox130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MCP Selection Lab @changhuliu/mcp-selection-labBenchmark MCP tool selection with metadata-only routing, collision, abstention, and holdout checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AIAgora @aiagora/agoraOpen square for AI agents: solve sandbox-tested problems, earn Ed25519-signed proofs.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- fixture.email — Email Testing for Agents @fixture/email-testingDisposable test mailboxes on a real domain: send, receive and assert on real email.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Spann Stays @spannhq/staysRead-only sample stays, booking constraints, and staged reservation actions for review.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rubrkit @rubrkit/rubrkitMCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- IT Security — Access Change Request Recertify — Alder Court Partners (b578285f) @a2awire/benchmark-access-change-request-recertify-2026-09-15-b578285f12 synthetic access change request exception cases: duplicate payments, policy-watch list entries, m33% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Employee Operations — Access Request Review — Larkspur Partners (81479355) @a2awire/benchmark-access-request-review-2026-09-10-8147935512 synthetic access request exception cases: duplicate payments, policy hold list entries, missing p22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Coliseum MCP @nanocorp/agent-coliseum-mcpFree Streamable HTTP MCP arena for 1v1 AI agent skill battles and Gladiator Badges.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AFG: agents hire agents (test money) @afg/afgSandbox marketplace where AI agents hire agents for verified outcomes. Test money only.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- WebhookTest.net @webhooktest/webhook-testerAnonymous webhook capture, inspection, waiting, and response configuration for AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- WealthSchema @wealthschema/mcpCited 2026 U.S. planning figures (IRS, SSA, CMS), synthetic household samples, and an AI benchmark.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ScoreIA La Forge @scoreia/forge3D AI benchmark over MCP: forge a knight, cut posts, duel other AIs; a program referees it.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- FinchNode Synthetic Health Records @finchnode/health-records-demoSynthetic EHR: medications, labs, conditions, allergies, immunizations, FHIR R4. No API key.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
