Get the import/export dependency graph. Without filters, returns a summary dashboard. With a file or module filter, returns scoped edges (capped at 50). Use
AI agents call get_dependency_graph to retrieve information from Codecortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries pre-digested codebase knowledge without side effects. It does not create, modify, delete, or execute anything. The tool retrieves structural information about code dependencies, which is safe to expose to AI agents. Severity is low because even if misused, dependency graph queries cannot harm the codebase or system.
From the tool's definition Tool retrieves and queries dependency graph data. Key verbs: 'Get', 'returns'. No modification, deletion, or execution capability mentioned. Returns summary dashboard or scoped edges—purely informational queries.
Documented attack patterns abuse exactly the kind of access get_dependency_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codecortex, and nothing reaches the server without passing your rules. This is the rule we recommend for get_dependency_graph:
{
"version": "1",
"default": "deny",
"tools": {
"get_dependency_graph": {}
}
}get_dependency_graph is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the import/export dependency graph. Without filters, returns a summary dashboard. With a file or module filter, returns scoped edges (capped at 50). Use. It is categorised as a Read tool in the Codecortex MCP Server, which means it retrieves data without modifying state.
Register the Codecortex MCP server in PolicyLayer and add a rule for get_dependency_graph: 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 Codecortex. Nothing to install.
get_dependency_graph 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 get_dependency_graph 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 get_dependency_graph. 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.
get_dependency_graph is provided by the Codecortex MCP server (rushikeshmore/codecortex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codecortex, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Codecortex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.