AI agents use mono_set_limits to create or update resources in Monospay — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Monospay environment.
This tool creates or modifies spending control settings, which is a reversible configuration change (Write category). However, severity is high because improper spending limits could restrict legitimate transactions or be used to lock out users, and the tool operates with API key authority in a financial payment context (monospay-mcp).
From the tool's definition Tool description states 'Set spending controls' and 'uses API key'. The tool modifies spending limit configurations without moving funds. Named 'mono_set_limits', indicating write/configuration change.
Attacks that exploit this kind of access
Set spending controls. Does not move funds — uses API key. It is categorised as a Write tool in the Monospay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Monospay MCP server in PolicyLayer and add a rule for mono_set_limits: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Monospay. Nothing to install.
mono_set_limits is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mono_set_limits rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mono_set_limits. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mono_set_limits is provided by the Monospay MCP server (monospay/monospay). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →