Get recent change history (snapshots) for a watch.
AI agents call get_changes 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 queries historical change data for a monitored watch without creating, modifying, deleting, or executing any operations. It has no side effects beyond querying existing data, placing it squarely in the Read category with low severity risk.
From the tool's definition Tool name 'get_changes' and description 'Get recent change history (snapshots) for a watch' indicate data retrieval with no modification or deletion. The verb 'Get' and action of retrieving historical snapshots are read-only operations.
Attacks that exploit this kind of access
Get recent change history (snapshots) 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_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 Mcp Watched. Nothing to install.
get_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 get_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 get_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.
get_changes 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 →