Sends data to the stdin of a running background task.
AI agents invoke send-to-task-stdin to trigger actions in MCP Background Task Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Sending data to stdin of a running process can influence or control its execution behavior, effectively acting as an Execute operation. Depending on the task receiving input, this could trigger arbitrary commands or alter running processes significantly, making the blast radius high.
From the tool's definition Sends data to the stdin of a running background task
Attacks that exploit this kind of access
Sends data to the stdin of a running background task. It is categorised as a Execute tool in the MCP Background Task Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Background Task Server MCP server in PolicyLayer and add a rule for send-to-task-stdin: 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.
send-to-task-stdin is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send-to-task-stdin 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 send-to-task-stdin. 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.
send-to-task-stdin 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 →