build_task
AI agents invoke build_task to trigger actions in PsyFlow-MCP. 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.
Given the server context (PsyFlow task templates with tools like download_task, list_tasks, localize, list_voices), 'build_task' most likely compiles or generates/transforms a task template, which implies executing a build/transform process. Without a description, confidence is low, but 'build' typically implies executing a pipeline rather than a simple read or write.
From the tool's definition Tool name is 'build_task'; description is empty and uninformative.
Attacks that exploit this kind of access
build_task. It is categorised as a Execute tool in the PsyFlow-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PsyFlow- MCP server in PolicyLayer and add a rule for build_task: 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 PsyFlow-MCP. Nothing to install.
build_task 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 build_task 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 build_task. 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.
build_task is provided by the PsyFlow- MCP server (taskbeacon/taskbeacon-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 →