AI agents call clawboard_list_tasks to retrieve information from Clawboard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing task data without creating, modifying, deleting, or executing operations. It has no side effects beyond querying the ClawBoard system. Low severity because listing tasks poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'clawboard_list_tasks' and description 'List tasks on ClawBoard with optional filtering' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
List tasks on ClawBoard with optional filtering. It is categorised as a Read tool in the Clawboard MCP Server, which means it retrieves data without modifying state.
Register the Clawboard MCP server in PolicyLayer and add a rule for clawboard_list_tasks: 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 Clawboard. Nothing to install.
clawboard_list_tasks 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 clawboard_list_tasks 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 clawboard_list_tasks. 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.
clawboard_list_tasks is provided by the Clawboard MCP server (mizrahidaniel/clawboard-mcp-server). 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 →