protogrid
Sign inAdd to your agent

Search / io.boundra/boundra

Boundra — Payment Approval Gateway for AI Agents

R0· no sign-in

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

v0.1.2 · active · repository · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality83good
Trust96of 100
Uptime, 30 days100%
Latency p50338 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "boundra": {
      "type": "http",
      "url": "https://api.boundra.io/mcp"
    }
  }
}
claude mcp add --transport http boundra https://api.boundra.io/mcp
[mcp_servers.boundra]
url = "https://api.boundra.io/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "boundra": {
      "type": "remote",
      "url": "https://api.boundra.io/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "boundra": {
      "type": "http",
      "url": "https://api.boundra.io/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=boundra&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmJvdW5kcmEuaW8vbWNwIn0%3D"
}
{
  "servers": {
    "boundra": {
      "type": "http",
      "url": "https://api.boundra.io/mcp"
    }
  }
}
{
  "mcpServers": {
    "boundra": {
      "httpUrl": "https://api.boundra.io/mcp"
    }
  }
}
extensions:
  "boundra":
    enabled: true
    name: "boundra"
    type: streamable_http
    uri: "https://api.boundra.io/mcp"
    timeout: 300

Quality 83 / 100good

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno 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_costabout 1,681 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changes4 tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

14 tools, about 1,681 tokens to load them all · tool set e0a243bad824 · tools last changed 2026-11-02 · checked 2026-11-07 19:10 UTC

Tool changes

  • get_evaluationadded

    Inspect the reservation/settlement state of an evaluation

  • release_evaluationadded

    Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.

  • settle_evaluationadded

    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.

  • evaluate_paymentchangedinput schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 96 / 100

provenance85
liveness100
freshness100
hygiene100

+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. How it is computed.

Dependencies

[email protected] PyPIthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://api.boundra.io/mcp streamable-httpnoneyes100%338 ms2026-07-282026-11-07
packageregistryversionruntimesecrets
boundra-mcppypi0.1.1–

Tools (14)

evaluate_paymentEvaluate 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_trailView recent payment-approval audit records for an owner
get_evaluationInspect the reservation/settlement state of an evaluation
get_policyView the active signed payment policy for an owner (and optionally an agent scope)
get_policy_versionsView a user's policy version history (version chain + hashes, verifiable against on-chain commitments)
get_spend_reportView today's spend summary for an owner
list_policy_requestsList pending agent policy-change requests
list_templatesList policy templates (personal assistant / travel / dev API / procurement)
release_evaluationRelease a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.
render_templateRender 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_evaluationConfirm 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.

Schemas: list_tools.

Also listed as

1 other active names share this repository: io.github.gobeyondfj-cmd/boundra

Similar MCP servers

  • amlR0quality 81
    com.oceanalt/aml

    Pre-payment checks for AI agents: sanctions and AML screening of payees, payment pages and requests.

  • drift — mandate enforcement for AI agentsR0quality 88
    io.github.mrpkk/drift

    Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.

  • SatGate – Economic Firewall for AI AgentsR2quality 92
    io.github.SatGate-io/satgate

    Budget, payment and audit controls for AI agent API calls and MCP tool calls.

  • ASPERN: counterparty checks for agentsR0quality 69
    org.aspern/aspern

    What the chain records about an address before you pay it, and whether a payment fits it.

  • nidhipati — proof of spend for AI agentsR0quality 85
    io.github.mrpkk/nidhipati

    Proof-of-spend and reserve checks for AI agents: receipts, spend audit, NAV, reconciliation.

  • x402-data-gatewayR0quality 67
    io.github.epistemedeus/x402-data-gateway

    Agent tools for discovery, payment safety, data extraction, and DeFi.

Official server.json
{
  "name": "io.boundra/boundra",
  "title": "Boundra — Payment Approval Gateway for AI Agents",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.boundra.io/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.2",
  "packages": [
    {
      "version": "0.1.1",
      "transport": {
        "type": "stdio"
      },
      "identifier": "boundra-mcp",
      "registryType": "pypi"
    }
  ],
  "repository": {
    "url": "https://github.com/gobeyondfj-cmd/boundra",
    "source": "github"
  },
  "websiteUrl": "https://boundra.io",
  "description": "Allow, ask, or veto — a policy decision point your agent consults before signing any payment"
}