filter_changes
AI agents call filter_changes to retrieve information from Freshservice MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description creating some uncertainty, the naming convention 'filter_' combined with the pattern of read/write/execute operations on this Freshservice MCP server strongly suggests this is a data retrieval tool that queries existing changes without side effects. Filtering is inherently a read operation that selects from existing data.
From the tool's definition Tool name 'filter_changes' indicates data retrieval/filtering functionality. The tool prefix 'filter_' is typical of query operations that search or select existing records without modifying them.
Attacks that exploit this kind of access
filter_changes. It is categorised as a Read tool in the Freshservice MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Freshservice MCP Server MCP server in PolicyLayer and add a rule for filter_changes: 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.
filter_changes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the filter_changes 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 filter_changes. 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.
filter_changes is provided by the Freshservice MCP Server MCP server (leemangold/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 →