MCP.Market

Paybond MCP Server

by nonameuserd·io.github.nonameuserd/paybond·v0.12.16·1 stars
No reviews yet

Default trust layer for agentic payments: authorize agent spend, evidence, receipts, settlement.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

1 stars318 downloads/wk

Reviews

Write one

Nobody has reviewed Paybond MCP Server yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Paybond MCP Server tools (35, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • paybond_authorize_agent_spend

    Provider-agnostic spend gate: verify the funded intent's capability token before a side-effecting tool, paid API, vendor action, or settlement workflow executes.

  • paybond_bootstrap_sandbox_guardrail

    Bootstrap a sandbox-only Paybond guardrail intent for a first paid-tool integration. Tenant scope is derived from the configured service-account API key and the route never touches live settlement rails.

  • paybond_confirm_settlement

    Confirm Harbor settlement through the gateway /harbor path with a replay-safe recognition proof.

  • paybond_create_intentwrite action

    Create a Harbor intent through the gateway /harbor intent route. The request body must already be signed upstream and every call requires a recognition proof.

  • paybond_create_spend_intentwrite action

    Create a signed Paybond spend intent through the gateway /harbor route. Use this when an agent workflow needs bounded budget, allowed operations, evidence, and settlement review. If the selected rail funds immediately, use the returned intent_id and capability_token with paybond_authorize_agent_spend.

  • paybond_explain_policy

    Read-only dry-run explanation of whether proposed spend would allow, require approval, or deny under tenant spend policy.

  • paybond_fund_intent

    Advance Harbor funding through the gateway /harbor path with a replay-safe recognition proof. When funding succeeds, use the returned capability_token with intent_id in paybond_authorize_agent_spend.

  • paybond_get_a2a_agent_card

    Fetch the published Paybond A2A discovery card for protocol-trust delegation.

  • paybond_get_a2a_task_contract

    Fetch one published Paybond A2A task contract by identifier.

  • paybond_get_agent_receipt_v1

    Fetch the signed paybond.agent_receipt_v1 for one receipt_id.

  • paybond_get_audit_export

    Fetch one tenant-scoped compliance audit export job detail through the gateway operator view.

  • paybond_get_budget_remaining

    Read-only dry-run of remaining spend budget for a tenant-bound intent via gateway spend preflight.

  • paybond_get_fraud_assessment

    Fetch the read-only fraud assessment for one tenant-scoped operator DID.

  • paybond_get_fraud_metrics

    Fetch tenant-scoped read-only fraud backtesting and monitoring metrics for a supported active window.

  • paybond_get_intent

    Fetch one tenant-scoped Harbor intent detail through the gateway operator view.

  • paybond_get_portfolio_summary

    Fetch the tenant-scoped Signal portfolio summary.

  • paybond_get_principal

    Use this when you need to confirm which tenant-bound service-account principal the configured PAYBOND_API_KEY authenticates as

  • paybond_get_reputation_receipt

    Fetch the signed Signal receipt for one operator DID.

  • paybond_get_settlement_receipt_v1

    Fetch the signed protocol-v2 settlement receipt for one Harbor intent.

  • paybond_get_signed_portfolio_artifact

    Fetch the tenant-scoped signed Signal portfolio artifact for portable verifier and partner sharing.

  • paybond_import_agent_mandate_v1

    Import a signed AgentMandateV1 through the gateway v2 protocol route and bind it to one Harbor intent using a replay-safe recognition proof.

  • paybond_list_a2a_task_contracts

    Fetch the published catalog of Paybond A2A task contracts for delegated Harbor workflows.

  • paybond_list_audit_exports

    List tenant-scoped compliance audit export jobs through the gateway operator view.

  • paybond_list_intents

    List tenant-scoped Harbor intents through the gateway operator view with optional filters.

  • paybond_submit_evidencewrite action

    Submit payee evidence through the gateway /harbor path with a replay-safe recognition proof.

  • paybond_submit_sandbox_guardrail_evidencewrite action

    Submit evidence for a sandbox-only Paybond guardrail intent. Tenant scope is derived from the configured service-account API key and simulator settlement remains sandbox-only.

  • paybond_submit_spend_evidencewrite action

    Submit signed evidence for a Paybond spend intent so release, refund, review, and receipt generation use the same audit-ready record.

  • paybond_validate_completion_evidence

    Pre-validates completion evidence against the shared preset catalog. Call this before paybond_submit_*_evidence when PAYBOND_MCP_EVIDENCE_POLICY=strict.

  • paybond_verify_agent_mandate_v1

    Verify a signed AgentMandateV1 envelope through the gateway v2 protocol surface.

  • paybond_verify_agent_receipt_v1

    Verify a signed paybond.agent_receipt_v1 offline (operational tier by default).

  • paybond_verify_agent_recognition_proof_v1

    Verify a replay-safe AgentRecognitionProofV1 against an expected purpose and request envelope.

  • paybond_verify_capability

    Verify a capability token returned by a created or funded Paybond intent for one tenant-bound Harbor intent.

  • paybond_verify_protocol_receipt_v1

    Verify a signed protocol-v2 authorization or settlement receipt through the gateway.

  • search.web

    Search the web

  • travel.book_hotel

    Book a hotel room

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan554 source files scanned; 343 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Paybond MCP Server compares

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

Safety score
83/100
higher than 68% of 4,460 AI and agents servers
Tools
35
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,711 AI and agents servers
Downloads a week
318
more than 80% of 1,538 AI and agents servers with a package

What its tools let an agent do: 1 read · 1 create · 33 change

Install Paybond MCP Server in Claude Code, Cursor or VS Code

Runs npx -y @paybond/kit on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add paybond -- npx -y @paybond/kit
Add to Cursor

What the publisher says

From the Paybond MCP Server repository's README, as published. We do not edit it. Read it on GitHub

@paybond/kit

<!-- mcp-name: io.github.nonameuserd/paybond -->

Your AI agent shouldn't accidentally spend $20,000.

An unsupervised agent that can book travel, call paid APIs, or buy compute can also loop through “approved” tool calls until the budget is gone — each charge succeeds, and nothing proves the work was delivered. Per-transaction caps alone do not stop that.

@paybond/kit is the TypeScript SDK for delegated agent spend controls: authorize against a bounded budget and policy before a paid tool runs, then release or refund only after signed completion evidence. Wrap three lines around any paid tool call — authorize → execute → verify. Keep your runtime. Keep your payment rails (prefer Stripe Connect / x402; Stripe ACH Direct Debit and USDC-on-Base are also available). You get spend authorization, evidence-gated settlement, refunds, disputes, and a portable signed receipt — without building your own proof-gated release middleware.

Under the hood, Kit opens hosted Gateway sessions, verifies capability tokens, signs intent and evidence payloads, and can read tenant-scoped Signal, fraud, ledger, protocol, and A2A data, with adapters for common agent runtimes.

Docs · TypeScript quickstart · Support matrix · Free sandbox signup · Python package

When to use Paybond

Reach for Paybond Kit whenever an AI agent can move money and you need spend that stays inside a budget — not just token metering: agentic payments and commerce, tool-call spend limits, outcome evidence before release, and audit-ready records — across OpenAI, Gemini, Claude/Anthropic, Vercel AI SDK, LangGraph, MCP hosts, and custom runtimes, settling through the payment rails your tenant already uses.

  • Use Paybond Kit when spend needs authorization against a bounded budget, proof-gated release/refund/dispute handling, or audit-ready receipts.
  • Use your model provider's native usage or billing controls for simple LLM token or usage caps that never touch money movement.

Start here (sandbox in ~60 seconds)

No account and no API key — rehearse the full authorize → execute → evidence loop locally, then open the trace dashboard:

npm install @paybond/kit
npx -p @paybond/kit paybond dev loop --offline
npx -p @paybond/kit paybond dev trace

paybond dev trace renders the middleware timeline at http://127.0.0.1:9477.

To try the same flow against the real hosted sandbox Gateway, first create a free Free Developer workspace if you do not already have a Paybond account (no card required), then:

npx -p @paybond/kit paybond login
npx -p @paybond/kit paybond-init --preset paid-tool-guard --framework provider-agnostic --out paybond-paid-tool-guard.ts
npx -p @paybond/kit paybond agent sandbox smoke \
  --operation travel.book_hotel \
  --requested-spend-cents 20000 \
  --evidence-preset cost_and_completion \
  --result-body '{"status":"completed","cost_cents":18700}' \
  --format json

paybond login opens a browser device-approval step; the workspace owner (you, right after signup) approves it and the CLI writes a sandbox PAYBONDAPIKEY to .env.local.

Launch the tenant-bound MCP server for MCP hosts (after paybond login):

npx -y -p @paybond/kit paybond-mcp-server

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Paybond MCP Server: common questions

Is Paybond MCP Server safe?
Mostly: it is graded B (83/100). Read the Paybond MCP Server safety report
How do I install Paybond MCP Server?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Paybond MCP Server need an API key?
Yes. The registry entry asks for PAYBOND_API_KEY.
Is Paybond MCP Server maintained?
The last commit was 44 days ago (2026-09-21). The latest release is v0.12.16.
What can I use instead of Paybond MCP Server?
Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, agent-device MCP server and HOL Guard MCP server.
How does Paybond MCP Server compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,460 AI and agents servers); tools 35 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Paybond MCP Server

Same job from other publishers: the closest match first, then the best rated.

  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B