Start here for every task.
AI agents call get_active_task_contexts to retrieve information from Task Context MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval/query operation with no side effects. It fetches active task contexts to inform subsequent actions, analogous to a 'list' or 'get' operation. The severity is low because reading stored task metadata poses minimal risk unless the contexts contain sensitive information, but the operation itself is non-destructive and non-executable.
From the tool's definition Tool name 'get_active_task_contexts' and description 'Start here for every task' indicate a retrieval operation.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Start here for every task. It is categorised as a Read tool in the Task Context MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Task Context MCP Server MCP server in PolicyLayer and add a rule for get_active_task_contexts: 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 Task Context MCP Server. Nothing to install.
get_active_task_contexts 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_active_task_contexts 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_active_task_contexts. 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_active_task_contexts is provided by the Task Context MCP Server MCP server (l0kifs/task-context-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 →