search_tasks_tool
AI agents call search_tasks_tool to retrieve information from Capsulecrm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve or query data without modifying or deleting anything. No side effects are indicated by the name or context. While the description is empty, the tool name and positioning among other Read-category siblings (find_tasks_tool, get_task_tool, list_milestones_tool) provide strong evidence this is a retrieval tool. Severity is low because misuse would only expose data, not modify or destroy it.
From the tool's definition Tool name 'search_tasks_tool' indicates a search operation. The server description mentions 'search' as a read operation. Sibling tools include 'find_tasks_tool' and 'get_task_tool' which are clearly Read operations.
Attacks that exploit this kind of access
search_tasks_tool. It is categorised as a Read tool in the Capsulecrm MCP Server, which means it retrieves data without modifying state.
Register the Capsulecrm MCP server in PolicyLayer and add a rule for search_tasks_tool: 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 Capsulecrm. Nothing to install.
search_tasks_tool 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 search_tasks_tool 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 search_tasks_tool. 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.
search_tasks_tool is provided by the Capsulecrm MCP server (monadsag/capsulecrm-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 →