AI agents call project_dependencies to retrieve information from Ensemble without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about code dependencies—a read-only operation with no side effects. It does not execute code, modify files, delete data, or trigger external operations. The verb 'Get' and the action of returning a dependency graph are consistent with the Read category. Low severity because misuse would only expose static code structure information, not cause harm.
From the tool's definition Tool name 'project_dependencies' and description 'Get import/dependency graph for a specific file' indicate a retrieval operation that queries and returns dependency information without modifying or executing any code.
Attacks that exploit this kind of access
Get import/dependency graph for a specific file. It is categorised as a Read tool in the Ensemble MCP Server, which means it retrieves data without modifying state.
Register the Ensemble MCP server in PolicyLayer and add a rule for project_dependencies: 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 Ensemble. Nothing to install.
project_dependencies 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 project_dependencies 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 project_dependencies. 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.
project_dependencies is provided by the Ensemble MCP server (lynkbyte/ensemble). 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 →