Boundra — Payment Approval Gateway for AI Agents MCP server
online · 100% uptimeio.boundra/boundra·v0.1.2Allow, ask, or veto — a policy decision point your agent consults before signing any payment
0 stars283 downloads/wk
Reviews
Write oneNobody has reviewed Boundra — Payment Approval Gateway for AI Agents yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Boundra — Payment Approval Gateway for AI Agents tools (11)
write = sends, deletes, buys or postsevaluate_paymentFreeEvaluate a payment intent. MUST be called before executing any payment. ALLOW = you may pay; DENY = you must abandon; ASK = a challenge is returned — relay the reason to the user, then retry with approval_token once the user signs. An optional mandate parameter carries a user-issued single-task authorization.
get_audit_trailFreeView recent payment-approval audit records for an owner
get_policyFreeView the active signed payment policy for an owner (and optionally an agent scope)
get_policy_versionsFreeView a user's policy version history (version chain + hashes, verifiable against on-chain commitments)
get_spend_reportFreeView today's spend summary for an owner
list_policy_requestsFreeList pending agent policy-change requests
list_templatesFreeList policy templates (personal assistant / travel / dev API / procurement)
render_templateFreeRender a natural-language rule from a template + parameters (then compile, sign & publish)
request_policy_changeFree[For agents] Ask the user for a policy/budget change (e.g. 'raise daily budget from 50 to 80'). The request is queued for user approval; the user signs and publishes a new policy version. Agents can NEVER change policy directly.
revoke_policyFree[USER ONLY] Revoke a policy chain (takes effect immediately; subsequent payments default to DENY). Must carry the user's wallet signature over the revocation statement.
set_policyFree[USER ONLY] Submit a new policy version. Must carry the user's wallet EIP-191 signature over the policy document; accepted only after signature + version-chain checks pass. Agents MUST NOT call this tool.
Public scan report
scanner v0.1.10 · 2026-10-25 · same rubric, same numbers if you re-run it
- Code scan10 source files scanned25/25
- Live reliabilityremote reachable in 854ms20/20
- Tool poisoning11 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityendpoint served from the registry-verified namespace domain8/10
How Boundra — Payment Approval Gateway for AI Agents compares
Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 93/100
- higher than 96% of 1,765 Finance servers
- Tools
- 11
- the typical Finance server has 8
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote Finance server answers 100%
- Response time
- 5,436 ms
- faster than 0% of 1,135 Finance servers
- Downloads a week
- 283
- more than 84% of 413 Finance servers with a package
What its tools let an agent do: 8 read · 1 change · 1 delete · 1 run or deploy
Install Boundra — Payment Approval Gateway for AI Agents in Claude Code, Cursor or VS Code
claude mcp add --transport http boundra https://api.boundra.io/mcp
What the publisher says
From the Boundra — Payment Approval Gateway for AI Agents repository's README, as published. We do not edit it. Read it on GitHub
Boundra · Payment approval gateway for AI agents
<!-- mcp-name: io.boundra/boundra -->
Boundra (boundra.io) — Boundaries for agent payments.
The boundary layer for agent payments: before any money moves, answer
"should this payment happen at all?"
Our thesis: the opportunity in agent payments is not "how to pay" (protocols solved that) but "whether to pay."
One natural-language rule → compiled into a policy → every payment the agent attempts is genuinely evaluated → allow / ask a human / veto, with a full audit trail.
Two run modes:
and wallets, zero dependencies, zero network
- Offline simulation (demo.py): stdlib only, self-contained mock merchant
Base Sepolia testnet
- Real protocol (demo/demo_real.py): standard MCP server + real x402 SDK +
Data flow
Policies and keys stay with the user; the gateway is read-only; only hash commitments go on-chain. Revocation is free — forever, no exceptions.
Integrating Boundra into your agent? See
docs/INTEGRATION.md — hosted API, x402 SDK hook,
and MCP paths with tested code.
See it run in 60 seconds
# 1. Hit the hosted evaluation API — a real, public x402 merchant
curl -X POST https://api.boundra.io/evaluate/basic \
-H 'Content-Type: application/json' \
-d '{"intent":{"amount":0.01,"recipient":"api.weather.com","purpose":"weather data"}}'
# → {"decision":"ALLOW",...} · semantic layer: 100 free calls per agent,
# then $0.003 via x402 — settled for real on Base mainnet (USDC)
# 2. Local end-to-end simulation — a data-procurement agent's day
.venv/bin/python demo/simulate_agent.py
# signed policy publish → ALLOW / DENY (limit) / ASK → user-signed approval token
# → prompt-injection blocked → audit trail, plus a dogfood call to api.boundra.io
# 3. One-line MCP install + 2-minute policy wizard
uvx --from git+https://github.com/gobeyondfj-cmd/boundra boundra-mcp # stdio server
uvx --from git+https://github.com/gobeyondfj-cmd/boundra boundra-init # wallet → template → sign → anchor
uvx --from git+https://github.com/gobeyondfj-cmd/boundra boundra-approve # sign an ASK challengeThe complete flow, step by step
Zero to a signed, enforced policy in ~10 minutes. No accounts, no dashboards — your wallet key is your identity.
0 · Try the hosted API (30 seconds, nothing to install)
curl -X POST https://api.boundra.io/evaluate/basic \
-H 'Content-Type: application/json' \
-d '{"intent":{"amount":0.01,"recipient":"api.weather.com","purpose":"weather data"}}'1 · Bind your identity — the wallet is the account
uvx --from git+https://github.com/gobeyondfj-cmd/boundra boundra-initCreates or imports a Base wallet. No signup, no email — the private key never leaves your device, and your address is your identity everywhere in the system.
2 · Set your policy
The wizard offers templates (personal assistant / travel / dev API / procurement) or lets you write your own rule in plain English, then compiles it and shows you exactly what will be enforced — before anything is signed.
3 · Sign & publish
You sign the policy document with your wallet key (EIP-191). It is published as a versioned document and a hash commitment is anchored on-chain. From this moment the gateway is read-only for every agent — changing the policy without your key is impossible.
4 · Mount the MCP server into your agent
Hosted (zero install, multi-tenant, default-deny until you publish a signed policy):
{ "mcpServers": { "boundra": { "url": "https://api.boundra.io/mcp" } } }Or self-hosted:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Boundra — Payment Approval Gateway for AI Agents: common questions
- Is Boundra — Payment Approval Gateway for AI Agents MCP server safe?
- Yes, by our scan: it is graded A (93/100). Read the Boundra — Payment Approval Gateway for AI Agents safety report
- How do I install Boundra — Payment Approval Gateway for AI Agents?
- It runs remotely at api.boundra.io. 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 Boundra — Payment Approval Gateway for AI Agents need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Boundra — Payment Approval Gateway for AI Agents maintained?
- The last commit was 9 days ago (2026-10-24). The latest release is v0.1.2.
- Is Boundra — Payment Approval Gateway for AI Agents up?
- 100% of our last 26 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Boundra — Payment Approval Gateway for AI Agents?
- Servers from other publishers that do the same job: X402 List MCP server, Conekta MCP server and PayRam MCP server. Compare all Boundra — Payment Approval Gateway for AI Agents alternatives.
- How does Boundra — Payment Approval Gateway for AI Agents compare with other Finance MCP servers?
- safety score 93/100 (higher than 96% of 1,765 Finance servers); tools 11 (the typical Finance server has 8); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Boundra — Payment Approval Gateway for AI Agents
Same job from other publishers: the closest match first, then the best rated.
- X402 ListFind and vet x402 payment APIs before your agent pays one: uptime, price, on-chain volume.not reviewedEstablishedA
- not reviewedEstablishedB
PayRamInstall, configure, operate and integrate self-hosted PayRam crypto payment gateways.not reviewedGrowingB- Pulsefeed X402Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.not reviewedGrowingA
- Yolfi Payments MCPLet AI agents add Yolfi crypto checkout, paylinks, webhooks, and status checks.not reviewedEstablishedA