io.boundra/boundra

up checked 2026-11-11T14:37:42.264Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Boundra — Payment Approval Gateway for AI Agents

Publisher-provided description

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

Summary by lookupd

Lets an agent evaluate, approve, reserve, and settle payments against user-signed spend policies, with audit trails and spend reports.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http boundra https://api.boundra.io/mcp

Claude Code, pypi package (stdio)

claude mcp add boundra -- uvx boundra-mcp

Codex, remote (streamable-http)

codex mcp add boundra --url https://api.boundra.io/mcp

Codex, pypi package (stdio)

codex mcp add boundra -- uvx boundra-mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "boundra": {
      "url": "https://api.boundra.io/mcp"
    }
  }
}

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "boundra": {
      "command": "uvx",
      "args": [
        "boundra-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (14 tools)

Publisher-provided text

• 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
• 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 refer
• 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.
• get_evaluation Inspect the reservation/settlement state of an evaluation
• 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 publ
• get_policy View the active signed payment policy for an owner (and optionally an agent scope)
• get_spend_report View today's spend summary for an owner
• get_audit_trail View recent payment-approval audit records for an owner
• 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
• 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 st
• get_policy_versions View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)
• list_policy_requests List pending agent policy-change requests
• list_templates List policy templates (personal assistant / travel / dev API / procurement)
• render_template Render a natural-language rule from a template + parameters (then compile, sign & publish)

Details

• Version: 0.2.0
• Transports: streamable-http, stdio
• Uptime (7 days): 100%
• Median latency: 1200 ms
• First indexed: 2026-11-01T09:02:55.439Z
• Last seen in registry: 2026-11-10T07:17:21.501Z
• Repository: https://github.com/gobeyondfj-cmd/boundra
• Website: https://boundra.io

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.boundra/boundra.svg)](https://lookupd.com/servers/io.boundra/boundra)

• 62092 servers
• Last crawl: 2026-11-11T17:17:22.074Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp