Paycrow MCP server

• escrow_createwrite actionFree

  Create a USDC escrow with built-in dispute resolution. Funds are locked on-chain until delivery is confirmed (release) or a problem is flagged (dispute). If disputed, an arbiter reviews and rules — the only escrow service with real dispute resolution on Base.

• escrow_disputeFree

  Flag a problem with delivery — PayCrow's key differentiator. Locks escrowed funds and triggers arbiter review. Unlike other escrow services that say 'no disputes, no chargebacks', PayCrow has real on-chain dispute resolution. Use when service was not delivered or quality was unacceptable.

• escrow_releaseFree

  Confirm delivery and release escrowed USDC to the seller. Only call this when you've verified the service/product was delivered correctly.

• escrow_statusFree

  Check the current state of an escrow (funded, released, disputed, expired, etc.)

• rate_serviceFree

  Rate a completed escrow. After escrow_release, rate the seller's service quality (1-5 stars). This builds the reputation data that makes PayCrow's trust scores meaningful over time. Both sides can rate: buyer rates seller's service quality, seller rates buyer's conduct. Ratings are on-chain and permanent — they feed directly into trust scoring.

• safe_paywrite actionFree

  The smart way to pay an agent. Checks their trust score first, then auto-configures escrow protection based on risk. Flow: Check trust → Set protection level → Create escrow → Call API → Verify → Auto-release or auto-dispute. Protection levels (automatic): - High trust agent → 15min timelock, proceed normally - Moderate trust → 60min timelock, payment capped at $25 - Low trust → 4hr timelock, payment capped at $5 - Unknown/caution → BLOCKED — will not send funds This is the recommended tool for paying any agent. If you need manual control, use x402_protected_call instead.

• trust_gateFree

  Should you pay this agent? Check before sending money. Returns a go/no-go decision with recommended escrow protection parameters. Unlike other trust services, PayCrow ties trust directly to escrow protection: - High trust → shorter timelock, proceed with confidence - Low trust → longer timelock, smaller amounts recommended - Caution → don't proceed, or use maximum protection This is the tool to call BEFORE escrow_create or safe_pay.

• trust_onchain_quickFree

  Quick on-chain reputation check using only the PayCrow Reputation contract. Free, no API keys needed. Use trust_score_query for the full composite score.

• trust_score_queryFree

  Full trust score breakdown for an agent address. Aggregates 4 on-chain sources: PayCrow escrow history, ERC-8004 agent identity, Moltbook social karma, and Base chain activity. Returns 0-100 score with per-source details. For a quick go/no-go decision, use trust_gate instead.

• x402_protected_callFree

  Make an HTTP API call with manual escrow protection. Full control over verification and timelock parameters. For most payments, use safe_pay instead — it auto-configures protection based on seller trust. Use x402_protected_call when you need: - Custom JSON Schema verification (not just "valid JSON + 2xx") - Hash-lock verification (exact response match) - Specific timelock durations - To override safe_pay's trust-based amount limits

• Code scan9 source files scanned25/25
• Live reliabilityremote reachable in 98ms20/20
• Tool poisoning10 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
• Maintenancelast push 197 days ago4/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

75/100

higher than 45% of 4,460 AI and agents servers

Tools

10

the typical AI and agents server has 6

Tools that change things

20%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote AI and agents server answers 100%

Response time

299 ms

faster than 47% of 2,331 AI and agents servers

GitHub stars

1

more than 50% of 2,711 AI and agents servers

Paycrow: common questions

Is Paycrow MCP server safe?

Mostly: it is graded B (75/100). Read the Paycrow safety report

How do I install Paycrow?

It runs remotely at paycrow-app.fly.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Paycrow need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Paycrow maintained?

The last commit was 235 days ago (2026-03-14). The latest release is v1.0.0.

Is Paycrow up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Paycrow?

Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, IWE (iwe.md) MCP server and DCC-MCP Core MCP server.

How does Paycrow compare with other AI and agents MCP servers?

safety score 75/100 (higher than 45% of 4,460 AI and agents servers); tools 10 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.