Retrieves the stderr of a running background task.
AI agents call get-task-stderr to retrieve information from MCP Background Task Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only accesses and returns data (stderr stream) from an already-running task. It does not modify, delete, execute, or control the task itself—it merely observes its output. The blast radius of misuse is minimal, as an attacker learns only what errors a background task has already emitted. No state is altered.
From the tool's definition The tool 'get-task-stderr' retrieves stderr output from a running background task. The verb 'Retrieves' and the function of reading error stream output indicate a read-only operation with no side effects.
Attacks that exploit this kind of access
Retrieves the stderr of a running background task. It is categorised as a Read tool in the MCP Background Task Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Background Task Server MCP server in PolicyLayer and add a rule for get-task-stderr: 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 MCP Background Task Server. Nothing to install.
get-task-stderr 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-stderr 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-stderr. 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-stderr is provided by the MCP Background Task Server MCP server (nanoseil/mcp-bgtask). 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 →