# Boundra — Payment Approval Gateway for AI Agents

> Allow, ask, or veto — a policy decision point your agent consults before signing any payment

- name: io.boundra/boundra
- version: 0.1.2
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.boundra%2Fboundra
- tools: https://api.protogrid.dev/v1/servers/io.boundra%2Fboundra/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "boundra": {
      "type": "http",
      "url": "https://api.boundra.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% +updated-16d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_policy_requests (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_evaluation (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_audit_trail (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,681 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know boundra-mcp@0.1.1

- tools: 14, about 1,681 tokens to load them all
- tool set hash: e0a243bad824cbe299986b4749018ef9
- tools last changed: 2026-11-02T19:08:22.640Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.boundra/boundra.svg)](https://protogrid.dev/servers/io.boundra/boundra)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-02 `get_evaluation` added
  - Inspect the reservation/settlement state of an evaluation
- 2026-11-02 `release_evaluation` added
  - Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.
- 2026-11-02 `settle_evaluation` added
  - 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.
- 2026-11-02 `evaluate_payment` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.boundra%2Fboundra/changes

## Dependencies

- pypi boundra-mcp@0.1.1: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://api.boundra.io/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- pypi boundra-mcp@0.1.1

## Tools (14)

- `evaluate_payment`: 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.
- `get_audit_trail`: View recent payment-approval audit records for an owner
- `get_evaluation`: Inspect the reservation/settlement state of an evaluation
- `get_policy`: View the active signed payment policy for an owner (and optionally an agent scope)
- `get_policy_versions`: View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)
- `get_spend_report`: View today's spend summary for an owner
- `list_policy_requests`: List pending agent policy-change requests
- `list_templates`: List policy templates (personal assistant / travel / dev API / procurement)
- `release_evaluation`: Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.
- `render_template`: Render a natural-language rule from a template + parameters (then compile, sign & publish)
- `request_policy_change`: [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_policy`: [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_policy`: [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.
- `settle_evaluation`: 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.