Boundra — Payment Approval Gateway for AI Agents

io.boundra/boundraVersion 0.2.0

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

Status

Responds4553 msNov 14, 2026, 14:33 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:33 UTC
Latency: 4553 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://api.boundra.io/mcpResponds4553 msNov 14, 2026, 14:33 UTC

No sign-in

Claude Code

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

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: boundra
Remote MCP server URL: https://api.boundra.io/mcp

Cursor

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

VS Code

code --add-mcp '{"name":"boundra","type":"http","url":"https://api.boundra.io/mcp"}'

Streamable HTTP

pypi: boundra-mcp 0.2.0

Package only

PyPI (uvx)

claude mcp add boundra -- uvx boundra-mcp==0.2.0

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

14 tools

Tools of Boundra — Payment Approval Gateway for AI Agents
	Description		Read-only	Idempotent	Open world
`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.	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.	No	No	No	No
`get_audit_trail`View recent payment-approval audit records for an owner	View recent payment-approval audit records for an owner	No	Yes	Yes	No
`get_evaluation`Inspect the reservation/settlement state of an evaluation	Inspect the reservation/settlement state of an evaluation	No	Yes	Yes	No
`get_policy`View the active signed payment policy for an owner (and optionally an agent scope)	View the active signed payment policy for an owner (and optionally an agent scope)	No	Yes	Yes	No
`get_policy_versions`View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)	View a user's policy version history (version chain + hashes, verifiable against on-chain commitments)	No	Yes	Yes	No
`get_spend_report`View today's spend summary for an owner	View today's spend summary for an owner	No	Yes	Yes	No
`list_policy_requests`List pending agent policy-change requests	List pending agent policy-change requests	No	Yes	Yes	No
`list_templates`List policy templates (personal assistant / travel / dev API / procurement)	List policy templates (personal assistant / travel / dev API / procurement)	No	Yes	Yes	No
`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.	Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.	No	No	Yes	No
`render_template`Render a natural-language rule from a template + parameters (then compile, sign & publish)	Render a natural-language rule from a template + parameters (then compile, sign & publish)	No	Yes	Yes	No
`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.	[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.	No	No	No	No
`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.	[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.	Yes	No	Yes	No
`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.	[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.	No	No	No	No
`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.	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.	No	No	Yes	No

Details

Registry status: Active
Published: Nov 10, 2026
Updated: Nov 10, 2026
Website: https://boundra.io/⁠ (opens in a new tab)
Repository: https://github.com/gobeyondfj-cmd/boundra⁠ (opens in a new tab)
Categories (suggested): Finance and paymentsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing