Return compact decision-relevant state for a specific task.
AI agents call get_task_context to retrieve information from Decision State MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns state information (goals, constraints, facts, decisions) for a specific task without creating, modifying, or deleting any data. It has no side effects beyond querying. This is a straightforward Read operation with minimal blast radius if misused — an agent could only access stored decision context, not alter it.
From the tool's definition Tool name is 'get_task_context' and description states 'Return compact decision-relevant state' — uses the verb 'return' indicating retrieval without modification.
Attacks that exploit this kind of access
Return compact decision-relevant state for a specific task. It is categorised as a Read tool in the Decision State MCP MCP Server, which means it retrieves data without modifying state.
Register the Decision State MCP server in PolicyLayer and add a rule for get_task_context: 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 Decision State MCP. Nothing to install.
get_task_context 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_task_context 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_task_context. 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_task_context is provided by the Decision State MCP server (koolercat/mcp-state). 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 →