Check who your agent is about to pay over x402: real service, relayer, treasury, or buyer.
AI & Agentsv1.0.0streamable-httpdata.crestsystems.ai
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 79ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo witnos@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 11 tools e.g. "check_counterparty"; 11/11 described, 11/11 fully-typed schemas, median description 340 chars |
| latency | 10 / 10 | initialize round-trip 79ms |
| provenance | 12 / 15 | description present; no repository URL; version 1.0.0; namespace ai.crestsystems matches endpoint/repo |
Score 97/100 · latency 79ms · 11 tools · auth: open
Claude Code:
claude mcp add --transport http counterparty-intelligence https://data.crestsystems.ai/mcp
Generic MCP client config:
{ "mcpServers": { "counterparty-intelligence": { "type": "http", "url": "https://data.crestsystems.ai/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/ai.crestsystems/counterparty-intelligence · referral link https://mcpqueen.com/go/ai.crestsystems/counterparty-intelligence (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/ai.crestsystems/counterparty-intelligence)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-12 14:19 | A | 97 | 79ms |