Create a new pipeline for sequential or DAG execution
AI agents use afc-create-pipeline to create or update resources in AFC Commander (Free Edition) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AFC Commander (Free Edition) environment.
This tool creates a new pipeline configuration object, which is a reversible write operation. Pipelines themselves are metadata/configuration that can be deleted or modified later.
From the tool's definition Tool name includes 'create' and description states 'Create a new pipeline for sequential or DAG execution', indicating data creation that defines a workflow.
Attacks that exploit this kind of access
Create a new pipeline for sequential or DAG execution. It is categorised as a Write tool in the AFC Commander (Free Edition) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AFC Commander (Free Edition) MCP server in PolicyLayer and add a rule for afc-create-pipeline: 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 AFC Commander (Free Edition). Nothing to install.
afc-create-pipeline is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the afc-create-pipeline 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 afc-create-pipeline. 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.
afc-create-pipeline is provided by the AFC Commander (Free Edition) MCP server (trace186/afc-commander-cli-registry-with-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 →