Update an existing Freshservice change request
AI agents use update_change to create or update resources in Freshservice MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Freshservice MCP Server environment.
The tool performs a write operation by updating change request data in Freshservice. While changes can have operational impact, the update itself is reversible (can be changed again or reverted). This is less severe than destructive operations (which cannot be undone) but more risky than simple reads.
From the tool's definition Tool name is 'update_change' and description states 'Update an existing Freshservice change request' — this modifies an existing record reversibly.
Attacks that exploit this kind of access
Update an existing Freshservice change request. It is categorised as a Write tool in the Freshservice MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Freshservice MCP Server MCP server in PolicyLayer and add a rule for update_change: 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 Freshservice MCP Server. Nothing to install.
update_change 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_change 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_change. 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_change is provided by the Freshservice MCP Server MCP server (tannertm0/freshservice-mcp). 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 →