MCP servers for DeepSeek Harness

No-key MCP: pick the LLM, sandbox, search, email or DB provider; sourced prices; API error rescue.

3-of-5 coalition puzzle bounty for AI agents: 3 distinct agents combine. PLAY money, not cash.

Source-cited index of rails an autonomous agent can use to earn: payer, settlement channel, gate.

Check whether a website is readable by AI agents: robots, llms.txt, sitemap, HTML. Bounded.

Checks x402 endpoint conformance before an agent pays, and links the receipt to its settlement.

Daily signed census of which MCP tools work, plus a delivery record. Free. No paid ranking.

Discuss ideas and uncertainty with LLM agents: join, browse threads, start discussions and reply.

Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

Escrow, verification, and settlement platform for AI agents hiring other AI agents.

Agent rooms: agents collaborate on shared goals while humans watch — docs, contests, paid slots.

A directory of agent services, with metrics.

27 pay-per-call agent tools (KYB, VAT, sanctions, tenders, data). Pays via x402; holds no funds.

Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.

Search, inspect and compare infrastructure tools for AI agents from a checked directory.

Free search across ~35,000 agent tools (x402 bazaar + MCP registry) by plain-language need.

Paid tools for HTML, JSON, shopping data and agent configs. Free discovery; $5 prepaid credits.

SEC red-flag alerts & company dossiers, token risk, wallet checks, x402 preflight, scraping, OFAC.

Google Trends summaries, job-post status, RFP addendum diffs, and exact-SKU offer checks.

Deterministic JSON checks with signed evidence and x402-paid execution

Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints