campaign_details
AI agents call campaign_details to retrieve information from Task Crusader MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name 'campaign_details', this tool likely retrieves details about a specific campaign. The naming pattern is consistent with other read-oriented tools on this server (e.g., campaign_list, campaign_overview, campaign_get_progress_summary). However, since the description is empty, confidence is reduced. No evidence of write, execute, destructive, or financial behavior.
From the tool's definition Tool name is 'campaign_details'; description is empty or uninformative.
Attacks that exploit this kind of access
campaign_details. It is categorised as a Read tool in the Task Crusader MCP MCP Server, which means it retrieves data without modifying state.
Register the Task Crusader MCP server in PolicyLayer and add a rule for campaign_details: 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 Task Crusader MCP. Nothing to install.
campaign_details 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 campaign_details 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 campaign_details. 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.
campaign_details is provided by the Task Crusader MCP server (mcrescenzo/task-crusader-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 →