MCP.Market

Is AgentPay — trust routing + spend caps for x402 agents MCP server safe?

Yes, with the usual care.

B79/100grade B

Safe to use. Minor gaps such as a missing repository or slower maintenance.

What to know before installing
  • highWrite-action tools reachable without authentication

How AgentPay — trust routing + spend caps for x402 agents compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
79/100
higher than 58% of 48,255 servers
Tools that change things
9%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%

What its tools let an agent do: 18 read · 1 create · 4 change

Release history: 4 versions in the registry since 2026-08-12, latest 2026-11-02, typically one every 30 days.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

1 high1 low
  • Code scan5 source files scanned25/25
  • Live reliabilityremote reachable in 2165ms17/20
  • Tool poisoning23 tool descriptions checked13/15
  • Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (2)

  • highWrite-action tools reachable without authenticationauth.open-write
  • lowUnusually long tool description (over 2,000 characters)poison.long-description
    tool pre_trade_check: …One-call pre-trade sanity check: 'I want to long $X of SYMBOL — is now sane?' Combines live orderbook slippage at YOUR size, cross-exchange funding (carry cost), open-interest crowding, and contract security (GoPlus) into a single ok/caution/avoid verdict with a per-factor breakdown. Major ERC-20 addresses (LINK, UNI, ARB, OP, AAVE, PEPE, SHIB) resolve automatically; native assets (BTC, ETH, SOL, ...) report security n/a; an unrecognized token without token_address reads 'unknown' and caps the verdict at caution — an unscreened contract can never read 'ok'. Replaces four API integrations and the judgment layer on top of them. Raw component data embedded so you can apply your own thresholds. Stacks tokens (STX, sBTC, USDCx, stSTX, ZEST, LEO, USDh, aeUSDC, stBTC) add the Bitflow DEX venue: price impact at YOUR size from a live route quote, the pools and bins the swap crosses, and their TVL; STX and sBTC keep their CEX perp legs, DEX-only tokens report funding/OI n/a and contract risk unscreened (no GoPlus coverage on Stacks). Use when: An agent (or human) is about to enter a position and wants one verdict covering liquidity, carry, crowding, and security — instead of four raw feeds plus its own synthesis. Not for: you need a single raw factor — funding_rates, open_interest, orderbook_depth or token_security are free; you are not about to size a position. This call settles $0.01 on-chain. Returns: verdict (ok/caution/avoid), factors{liquidity,carry,crowding,security} each with level + reason, components{orderbook_depth,funding_rates,open_interest}, symbol, side, size_usd Example response: {"symbol":"ETH","side":"long","size_usd":50000,"venue":"cex","verdict":"caution","factors":{"liquidity":{"level":"ok","slippage_pct":0.011,"bucket_usd":50000,"reason":"fills within 0.011% of best ask"},"carry":{"level":"caution","median_funding_pct":0.062,"annualized_pct":67.9,"reason":"longs paying elevated funding"},"crowding":{"level":"ok","long_short_ratio":1.4,"oi_change_24h_pct":3.2,"reason":"positioning unremarkable"},"security":{"level":"n/a","reason":"ETH is a native chain asset — no token contract to screen"}},"not_checked":["security"]} Price: $0.01 USDC per call (x402 over MCP: an unpaid call returns PaymentRequired; pay via _meta x402/payment)…
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

AgentPay — trust routing + spend caps for x402 agents reviews, tools and install