AI agents use update_function to create or update resources in Run402 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Run402 environment.
The tool creates or modifies data (function code) in a reversible manner without permanently deleting or destroying it. This aligns with the Write category. Severity is medium because modifying functions in an autonomous coding infrastructure could affect application behavior, but the action is reversible (can be updated again or rolled back).
From the tool's definition Tool name 'update_function' and description 'Update a function' indicate modification of code/function definitions. In a coding agent infrastructure context, this modifies existing functions reversibly.
Attacks that exploit this kind of access
Update a function. It is categorised as a Write tool in the Run402 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Run402 MCP server in PolicyLayer and add a rule for update_function: 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 Run402. Nothing to install.
update_function 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 update_function 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 update_function. 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.
update_function is provided by the Run402 MCP server (kychee-com/run402). 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 →