Get human-readable change summaries for a watch
AI agents call get_change_summary to retrieve information from Mcp Watched without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents information about changes that have already been detected and stored. It performs a read-only query operation with no side effects, state modifications, or external actions triggered. The data it accesses (change summaries) is informational only. Severity is low because reading change summaries poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get_change_summary' and description 'Get human-readable change summaries for a watch' indicate a retrieval operation that returns summaries of previously detected changes without modifying any data.
Attacks that exploit this kind of access
Get human-readable change summaries for a watch. It is categorised as a Read tool in the Mcp Watched MCP Server, which means it retrieves data without modifying state.
Register the Mcp Watched MCP server in PolicyLayer and add a rule for get_change_summary: 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 Mcp Watched. Nothing to install.
get_change_summary 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 get_change_summary 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 get_change_summary. 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.
get_change_summary is provided by the Mcp Watched MCP server (ng-pr0ject/mcp-watched). 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 →