add_goal_task
Add a task to a goal. Task types: - research — gather information - draft — write content - code — write or modify code - execute — run a workflow - recipe — invoke a specific recipe (use title to name the recipe alias) - loop — repeat an action - notify — send a notification - toolkit — invoke a...
This record as markdown: /tools/flowdot-llc-mcp-server/add-goal-task.md
What add_goal_task does on FlowDot MCP Server
AI agents use add_goal_task to create or update resources in FlowDot MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FlowDot MCP Server environment.
Why add_goal_task is rated Medium
This tool creates new data (tasks) within a goal structure, making it a Write operation. Severity is medium because while tasks are reversible (can be abandoned via sibling tool abandon_goal), malicious task injection could trigger unwanted workflows, code execution, or notifications depending on task type.
From the tool's definition Tool description states "Add a task to a goal" which creates new task records. The task types listed (research, draft, code, execute, recipe, loop, notify, toolkit) demonstrate the tool modifies goal state by appending executable tasks that will be processed…
Attacks that exploit this kind of access
The rule that runs add_goal_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FlowDot MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For add_goal_task, this is the rule to start with:
add_goal_task stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FlowDot MCP Server, apply this rule, and every add_goal_task call is checked against it from then on.
Questions about add_goal_task
Add a task to a goal. Task types: - research — gather information - draft — write content - code — write or modify code - execute — run a workflow - recipe — invoke a specific recipe (use title to name the recipe alias) - loop — repeat an action - notify — send a notification - toolkit — invoke an MCP toolkit tool Tasks are executed by the FlowDot daemon/CLI when the goal runs. It is categorised as a Write tool in the FlowDot MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FlowDot MCP Server MCP server in PolicyLayer and add a rule for add_goal_task: 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 FlowDot MCP Server. Nothing to install.
add_goal_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_goal_task 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 add_goal_task. 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.
add_goal_task is provided by the FlowDot MCP Server MCP server (flowdot-llc/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FlowDot MCP Server, and thousands of servers like it.
This server
Across the catalogue