Get tasks that AI can potentially execute. Returns PENDING or IN_PROGRESS tasks sorted by priority. Use this to find tasks to work on. Args: tags: Filter by tags (e.g., ['coding', 'ai-executable']) limit: Maximum number of tasks to return Returns: List of executable tasks with details
AI agents call get_executable_tasks to retrieve information from Taskdog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries task state and returns matching results based on filter criteria (tags, limit). It has no side effects on task data itself—it does not create, modify, delete, or execute tasks. The purpose is discovery/retrieval to inform downstream decisions. Even though the tasks themselves might be AI-executable, this tool only reads and presents information about them.
From the tool's definition Tool retrieves and filters PENDING or IN_PROGRESS tasks sorted by priority. Description uses 'Get', 'Returns', and 'Filter' — all read-only operations with no modification, deletion, or execution of underlying data.
Documented attack patterns abuse exactly the kind of access get_executable_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Taskdog, and nothing reaches the server without passing your rules. This is the rule we recommend for get_executable_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"get_executable_tasks": {}
}
}get_executable_tasks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get tasks that AI can potentially execute. Returns PENDING or IN_PROGRESS tasks sorted by priority. Use this to find tasks to work on. Args: tags: Filter by tags (e.g., ['coding', 'ai-executable']) limit: Maximum number of tasks to return Returns: List of executable tasks with details. It is categorised as a Read tool in the Taskdog MCP Server, which means it retrieves data without modifying state.
Register the Taskdog MCP server in PolicyLayer and add a rule for get_executable_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 Taskdog. Nothing to install.
get_executable_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 get_executable_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 get_executable_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.
get_executable_tasks is provided by the Taskdog MCP server (kohei-wada/taskdog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Taskdog, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Taskdog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.