// SCAN REPORT

Mcp Upbank

13 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 12 Jun 2026

3 can modify or destroy data

10 read-only

13 tools total

Community server · catalogue entry verified 12/06/2026

How to control Mcp Upbank ↓

TOOL MAP

What Mcp Upbank exposes to your agents

Read (10) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Upbank tools

Destructive · Medium deleteTransactionsTransactionIdRelationshipsTags This tool removes tags from transactions, which is a destructive operation as it irreversibly deletes tag associations. Write · Medium patchTransactionsTransactionIdRelationshipsCategory This tool creates or modifies transaction category relationships, which is reversible data modification. Write · Low postTransactionsTransactionIdRelationshipsTags This tool creates or modifies transaction tags, which is a reversible write operation.

3 of Mcp Upbank's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Upbank

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

Deny destructive operations

{
  "deleteTransactionsTransactionIdRelationshipsTags": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "patchTransactionsTransactionIdRelationshipsCategory": {
    "limits": [
      {
        "counter": "patchtransactionstransactionidrelationshipscategory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "getAccounts": {
    "limits": [
      {
        "counter": "getaccounts_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 Mcp Upbank — 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 MCP UPBANK →

Free to start. No card required.

FULL CATALOGUE

All 13 Mcp Upbank tools

DESTRUCTIVE 1 tools

Destructive deleteTransactionsTransactionIdRelationshipsTags Remove tags from transaction

WRITE 2 tools

Write patchTransactionsTransactionIdRelationshipsCategory Categorize transaction Write postTransactionsTransactionIdRelationshipsTags Add tags to transaction

READ 10 tools

Read getAccounts List accounts Read getAccountsAccountIdTransactions List transactions by account Read getAccountsId Retrieve account Read getAttachments List attachments Read getAttachmentsId Retrieve attachment Read getCategories List categories Read getCategoriesId Retrieve category Read getTags List tags Read getTransactions List transactions Read getTransactionsId Retrieve transaction

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Upbank

Can an AI agent delete data through the Mcp Upbank MCP server? +

Yes. The Mcp Upbank server exposes 1 destructive tools including deleteTransactionsTransactionIdRelationshipsTags. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Upbank? +

The Mcp Upbank server has 2 write tools including patchTransactionsTransactionIdRelationshipsCategory, postTransactionsTransactionIdRelationshipsTags. 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 Mcp Upbank.

How many tools does the Mcp Upbank MCP server expose? +

13 tools across 3 categories: Destructive, Read, Write. 10 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Mcp Upbank? +

Register the Mcp Upbank 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 Mcp Upbank tool call.

Deterministic rules across all 13 Mcp Upbank tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP UPBANK →

Free to start. No card required.

13 Mcp Upbank tools catalogued and risk-classified — across an index of 43,000+ MCP servers.