AI agents use deployment_manifest_gen to create or update resources in Sfgraph — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sfgraph environment.
This tool generates deployment manifest files including destructiveChanges.xml, which defines components to be deleted in a Salesforce deployment. While the tool itself only generates/writes XML files (not executes the deployment), the destructiveChanges.xml artifact it produces is specifically designed to irreversibly delete org components when deployed.
From the tool's definition Generate package.xml + destructiveChanges.xml from cross-org diff
Attacks that exploit this kind of access
Generate package.xml + destructiveChanges.xml from cross-org diff. It is categorised as a Write tool in the Sfgraph MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sfgraph MCP server in PolicyLayer and add a rule for deployment_manifest_gen: 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 Sfgraph. Nothing to install.
deployment_manifest_gen 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 deployment_manifest_gen 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 deployment_manifest_gen. 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.
deployment_manifest_gen is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →