care_gap_closure_plan
AI agents use care_gap_closure_plan to create or update resources in HomeCare Cohort MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HomeCare Cohort MCP environment.
The tool creates clinical care plans (a form of structured data) that will be stored and acted upon in patient management systems. While the description is empty, the context—a homecare clinical decision support system—indicates this generates reversible care documentation rather than executing direct medical interventions.
From the tool's definition Tool name 'care_gap_closure_plan' indicates generation of care plans; sibling tools include patient/cohort data retrieval, suggesting this generates actionable clinical documents that modify patient care workflows.
Attacks that exploit this kind of access
care_gap_closure_plan. It is categorised as a Write tool in the HomeCare Cohort MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HomeCare Cohort MCP server in PolicyLayer and add a rule for care_gap_closure_plan: 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 HomeCare Cohort MCP. Nothing to install.
care_gap_closure_plan 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 care_gap_closure_plan 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 care_gap_closure_plan. 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.
care_gap_closure_plan is provided by the HomeCare Cohort MCP server (nasir0md/homecare-cohort-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 →