A2AWire Benchmark: Support Agent Trials - Hard Mode

MCP server: One MCP server.

Ask Jev

@pollinations · External5.2k5,183 GitHub stars.

Evaluate state with typed choice, score, and probability questions.

MCP server: One MCP server.

Polymarket Paper Trader

@agent-next · External453453 GitHub stars.

Polymarket paper trading for AI agents: $10k paper money, real order books, official fees.

MCP server: One MCP server.

Watch Skill

@oxbshw · External438438 GitHub stars.

Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.

MCP server: One MCP server.

Martin LoopRun by its publisher: served from their own domain, namespace checked by the registry.

@keesan12 · External409409 GitHub stars.

One system around coding agents to run, verify, recover, and hand off software work.

MCP server: One MCP server.

Ghost in the DroidRun by its publisher: served from their own domain, namespace checked by the registry.

@ghost-in-the-droid · External383383 GitHub stars.

Give any LLM agent a real Android or iPhone as its body. 62 MCP tools for mobile automation.

MCP server: One MCP server.

OrcaReplayRun by its publisher: served from their own domain, namespace checked by the registry.

@continuum-ai-corp · External283283 GitHub stars.

Read, replay and fork recorded coding-agent runs.

MCP server: One MCP server.

OpikRun by its publisher: served from their own domain, namespace checked by the registry.

@comet-ml · External220220 GitHub stars.

Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

MCP server: One MCP server.

Rubber Duck

@nesquikm · External178178 GitHub stars.

Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more

MCP server: One MCP server.

Official Apple Newsroom: Announcements & Releases — buy per-query in-session (applenewswatch)

@a2awire · External

Apple product announcements & news. $0.01/query. Register in-session — free testnet funds.

MCP server: One MCP server.

Unit 42 Threat Research & Malware Analysis — buy per-query in-session (unit42watch)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

Unit 42 malware analysis & threat research. $0.01/query. Register in-session — free testnet funds.

MCP server: One MCP server.

Finance Ops — Document Review — Northgate Services Group (6e5a2dd9)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

12 synthetic document exception cases: duplicate reimbursements, policy-watch list entries, missing

MCP server: One MCP server.

Accounts Payable — Resume Audit — Verdant Springs Services Group (66514bc8)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

12 synthetic resume exception cases: duplicate payments, important watch list entries, missing rate

MCP server: One MCP server.

Finance Ops — Application Audit — Northgate Services Group (6e0ad047)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

12 synthetic application exception cases: duplicate reimbursements, claim hold list entries, missing

MCP server: One MCP server.

AWS Cloud Service Updates & Announcements — buy per-query (awswhatsnew)

@a2awire · External

AWS cloud service announcements & updates. $0.01/query. Register in-session — free funds.

MCP server: One MCP server.

Clinical Trial & Medical Research Tracker — buy per-query in-session (trialwatch)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

Medical research: new trial results tracker. $0.01/query. Register in-session — free testnet funds.

MCP server: One MCP server.

MIT Research & Science News — buy per-query in-session (mitwatch)Run by its publisher: served from their own domain, namespace checked by the registry.

@a2awire · External

MIT research news: science & engineering. $0.01/query. Register in-session — free testnet funds.