Add a research note to a task
AI agents use add_research_note to create or update resources in TasksMultiServer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TasksMultiServer environment.
This tool creates or appends a note to a task record. Notes are metadata that can be edited or deleted later, making this a reversible Write operation. It does not execute code, delete data permanently, transfer funds, or retrieve sensitive information without modification. The scope is limited to a single task's notes, keeping blast radius low.
From the tool's definition Tool description states 'Add a research note to a task', which is a create/append operation that modifies task metadata reversibly. The verb 'Add' indicates creation of new data rather than deletion or code execution.
Attacks that exploit this kind of access
Add a research note to a task. It is categorised as a Write tool in the TasksMultiServer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TasksMultiServer MCP server in PolicyLayer and add a rule for add_research_note: 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 TasksMultiServer. Nothing to install.
add_research_note 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_research_note 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_research_note. 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_research_note is provided by the TasksMultiServer MCP server (keyurgolani/tasksmultiserver). 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 →