Boundra — Payment Approval Gateway for AI Agents
Server Details
Allow, ask, or veto — a policy decision point your agent consults before signing any payment
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- gobeyondfj-cmd/boundra
- GitHub Stars
- 1
- Server Listing
- Boundra
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
Each tool has a distinct resource+action target, and the audience tags ([USER ONLY], [For agents]) plus the evaluate→settle/release lifecycle make roles clear. The only mild overlap is between get_policy, get_policy_versions, and get_evaluation/get_audit_trail, which all surface policy or evaluation state and could occasionally be misselected.
All 14 tools follow a strict snake_case verb_noun pattern (evaluate_payment, get_policy, set_policy, release_evaluation, settle_evaluation). Verbs are used consistently by intent (get_* for reads, list_* for collections, set/revoke/request for mutations), with no style mixing.
14 tools sits comfortably in the well-scoped range and each one maps to a concrete operation in the payment-approval domain. No tool appears redundant; the split between agent-facing and user-facing policy tools is intentional rather than bloat.
The surface covers the full evaluation lifecycle (evaluate → get → settle/release), policy management (get/set/revoke/versions/requests), templates, audit, and spend reporting. Minor gaps remain, such as no explicit cancellation/expiry path for a pending ASK challenge and no tool to enumerate past evaluations beyond the audit trail.
Available Tools
14 toolsevaluate_paymentAInspect
Evaluate 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.
Inputs: amount (required), purpose (required), recipient (required), asset, +11 more. Returns: result
get_audit_trailBRead-onlyIdempotentInspect
View recent payment-approval audit records for an owner
Inputs: owner (required), limit. Returns: result
get_evaluationCRead-onlyIdempotentInspect
Inspect the reservation/settlement state of an evaluation
Inputs: evaluation_id (required). Returns: result
get_policyARead-onlyIdempotentInspect
View the active signed payment policy for an owner (and optionally an agent scope)
Inputs: owner (required), agent_id. Returns: result
get_policy_versionsARead-onlyIdempotentInspect
View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)
Inputs: owner (required). Returns: result
get_spend_reportBRead-onlyIdempotentInspect
View today's spend summary for an owner
Inputs: owner (required). Returns: result
list_policy_requestsARead-onlyIdempotentInspect
List pending agent policy-change requests
Inputs: no named parameters. Returns: result
list_templatesARead-onlyIdempotentInspect
List policy templates (personal assistant / travel / dev API / procurement)
Inputs: no named parameters. Returns: result
release_evaluationAIdempotentInspect
Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.
Inputs: evaluation_id (required), reservation_token (required). Returns: result
render_templateCRead-onlyIdempotentInspect
Render a natural-language rule from a template + parameters (then compile, sign & publish)
Inputs: whitelist (required), template_id (required), daily, per_tx, +1 more. Returns: result
request_policy_changeAInspect
[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.
Inputs: reason (required), request (required), agent_id (required). Returns: result
revoke_policyADestructiveIdempotentInspect
[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.
Inputs: owner (required), scope (required), signature (required), created_at (required), +2 more. Returns: result
set_policyAInspect
[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.
Inputs: owner (required), scope (required), nl_rule (required), version (required), +4 more. Returns: result
settle_evaluationAIdempotentInspect
Confirm that an ALLOWed payment settled. Requires the evaluation_id and the reservation_token returned by evaluate_payment, plus the real transaction/hash reference. Idempotent for the same evaluation; never call this before settlement.
Inputs: evaluation_id (required), settlement_ref (required), reservation_token (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Public demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.
The decision layer for AI agents: act, escalate or refuse, and every decision comes back signed.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to verify proposed payments against their assigned task, budgets, permitted categories, and counterparties, returning an ALLOW or DENY decision with a tamper-evident audit trail.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to propose wallet payments while a local, human-authored policy decides whether each transaction is approved, requires human confirmation, or is refused, and records every decision in a signed, append-only ledger.-
- AlicenseNot gradedqualityDmaintenanceAgentPay is the authorization layer between an AI agent and real spending. You define the rules — spending caps, allowed merchants, time windows — and every purchase attempt the agent makes is checked against them in real time. Approved transactions go through. Anything outside the mandate is blocked and logged. No more babysitting every agent action. No more runaway charges.MIT
- FlicenseNot gradedqualityDmaintenanceEnables human-in-the-loop authorization for AI agent transactions, allowing real-time approval or denial of purchases based on configurable spending limits, vendor blocklists, daily caps, and category restrictions.1-
Glama MCP Gateway
Add one secure layer between your agents and this server.