Task contract, evidence check and done gate for AI coding agents. Read-only, no sign-in.
- Passed: Handshake
- Passed: Tools listed
- Passed: Updated recently
Median latency 546 ms · Last checked
Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesFind a server for your workflow, with connection evidence you can inspect.
Task contract, evidence check and done gate for AI coding agents. Read-only, no sign-in.
Median latency 546 ms · Last checked
Coordinate multi-specialist A2A agent swarms with cryptographic handshakes and x402 settlement.
Finance & CryptoPayments & trading
Median latency 547 ms · Last checked
Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and
Median latency 548 ms · Last checked
curlymolelabsVerified
Multilingual semantic SVG icon search with previews for AI coding agents. 20,000+ icons.
Median latency 549 ms · Last checked
A persistent AI world where agents walk, build, own things, talk, and make agreements.
Median latency 550 ms · Last checked
agencygrowth.comVerified
A growing library of AI agents and growth tools for agencies, in any AI assistant.
Median latency 551 ms · Last checked
pith.scienceVerified
Reviews of arXiv papers for AI agents: verdicts, claims, flaws, compiled records, citation graphs.
Developer ToolsKnowledge & memory
Median latency 552 ms · Last checked
Between 31 Aug–6 Sep and 25 Sep–1 Oct, anthropic's PyPI downloads grew 25% and openai's 14%,.
Developer ToolsAI / LLM tooling
Median latency 555 ms · Last checked
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Median latency 555 ms · Last checked
Ask a named human, Geoff, a question your agent cannot compute and fetch his answer later.
Median latency 558 ms · Last checked
humanfn.comVerified
Qualified human outcomes for AI agents: attorney review of SaaS Terms/Privacy, on-site checks.
Median latency 559 ms · Last checked
odilelabs.comVerified
Odile Labs: AI agents reach businesses by phone number (Direct); Gate keys, audit. Agentforce-ready.
Median latency 561 ms · Last checked
XRPL-UtilitiesVerified
XRPL data tools for AI agents: wallet classifier, signals, RWA tracker, ETF flows. Pay via x402.
Finance & CryptoPayments & trading
Median latency 561 ms · Last checked
claude-opus-4-5-20251101-high-32k is #49 overall but #14 in coding. gpt-5.6-terra-xhigh is #52.
Developer ToolsAI / LLM tooling
Median latency 562 ms · Last checked
memoryplugin.comVerified
Give every AI you use one shared, permanent memory. Store once, recall in whichever AI you open.
Median latency 562 ms · Last checked
graunt.comVerified
The agent-native marketplace for AI data: search listings and read their price and rights.
Median latency 563 ms · Last checked
On 11 Sept 2026, Claude's best model rates 40 points above OpenAI's and 16 above Gemini's..
Developer ToolsAI / LLM tooling
Median latency 566 ms · Last checked
AI agents that watch DeFi positions: read a wallet report, draft agents for the owner to sign.
Finance & CryptoPayments & trading
Median latency 567 ms · Last checked
schoolscope.coVerified
California school data for AI agents — scores, comparisons, feeder paths, TK ages, applications.
Median latency 568 ms · Last checked
signalharness.aiVerified
330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use.
Finance & CryptoPayments & trading
Median latency 568 ms · Last checked
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
Marketing & SalesAI / LLM tooling
Median latency 569 ms · Last checked
entradoxVerified
Meter, cap, and block AI agent spend before the provider is charged.
Median latency 569 ms · Last checked
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP
Median latency 571 ms · Last checked
geroncoVerified
Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.
Median latency 571 ms · Last checked
Automated measurements. Not a rating. Unmeasured checks are not failures. How to read the evidence