taskwarrior_tags
AI agents call taskwarrior_tags to retrieve information from Taskwarrior MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests it retrieves tag information from Taskwarrior. Sibling tools include read-oriented tools (taskwarrior_list, taskwarrior_get, taskwarrior_bulk_get), and 'tags' fits the pattern of a read/list operation. However, the empty description lowers confidence — it could also modify tags. Given the naming convention and context, Read is the most likely category with low severity.
From the tool's definition Tool name is 'taskwarrior_tags'; description is empty. Based on naming convention and sibling tools (list, get, bulk_get), 'tags' most likely retrieves or lists tags.
Attacks that exploit this kind of access
taskwarrior_tags. It is categorised as a Read tool in the Taskwarrior MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Taskwarrior MCP Server MCP server in PolicyLayer and add a rule for taskwarrior_tags: 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 Taskwarrior MCP Server. Nothing to install.
taskwarrior_tags 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 taskwarrior_tags 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 taskwarrior_tags. 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.
taskwarrior_tags is provided by the Taskwarrior MCP Server MCP server (tylyan/taskwarrior-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 →