// SCAN REPORT

Ucp

5 tools. 4 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

4 can modify or destroy data

1 read-only

5 tools total

Community server · catalogue entry verified 12/06/2026

How to control Ucp ↓

TOOL MAP

What Ucp exposes to your agents

Read (1) Write / Execute (1) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ucp tools

Financial · Critical ucp_checkout_complete The tool name 'ucp_checkout_complete' strongly implies finalizing a purchase/payment transaction. Financial · Critical ucp_checkout_create The tool name strongly suggests initiating a checkout process in a shopping/payment context. Financial · High ucp_checkout_update Given the server context (shopping, payments, checkout) and sibling tools (checkout_create, checkout_complete), ucp_checkout_update almost certainly modifies an in-progress checkout, which is a financial operation. Write · High ucp_checkout_set_fulfillment This tool modifies fulfillment settings within an active checkout session.

4 of Ucp's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ucp

PolicyLayer is an MCP gateway — it sits between your AI agents and Ucp, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "ucp_checkout_complete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "ucp_checkout_set_fulfillment": {
    "limits": [
      {
        "counter": "ucp_checkout_set_fulfillment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ucp_discover": {
    "limits": [
      {
        "counter": "ucp_discover_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ucp — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON UCP →

Free to start. No card required.

FULL CATALOGUE

All 5 Ucp tools

FINANCIAL 3 tools

Financial ucp_checkout_complete ucp_checkout_complete Financial ucp_checkout_create ucp_checkout_create Financial ucp_checkout_update ucp_checkout_update

WRITE 1 tools

Write ucp_checkout_set_fulfillment ucp_checkout_set_fulfillment

READ 1 tools

Read ucp_discover ucp_discover

FAQ

Questions about Ucp

Can an AI agent move money through the Ucp MCP server? +

Yes. The Ucp server exposes 3 financial tools including ucp_checkout_complete, ucp_checkout_create, ucp_checkout_update. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Ucp? +

The Ucp server has 1 write tools including ucp_checkout_set_fulfillment. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ucp.

How many tools does the Ucp MCP server expose? +

5 tools across 1 categories: Write. 1 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Ucp? +

Register the Ucp MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ucp tool call.

Deterministic rules across all 5 Ucp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UCP →

Free to start. No card required.

5 Ucp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.