Get the dependency graph for a codebase in JSON or DOT format
AI agents call get_dependency_graph to retrieve information from DependencyMCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns analytical data about codebase dependencies. It performs no modifications, deletions, code execution, or financial operations. The 'get_' prefix and description confirm it is a read-only query operation. Severity is low because the output is structural analysis information without side effects; misuse would result in information disclosure rather than system compromise or data loss.
From the tool's definition Tool description states it 'Get[s] the dependency graph for a codebase in JSON or DOT format' — a retrieval/query operation that analyzes and returns data about code structure without modifying or executing anything.
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 DependencyMCP Server, 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 dependency graph for a codebase in JSON or DOT format. It is categorised as a Read tool in the DependencyMCP Server MCP Server, which means it retrieves data without modifying state.
Register the DependencyMCP Server 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 DependencyMCP Server. 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 DependencyMCP Server MCP server (mkearl/dependency-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DependencyMCP Server, 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.
4 DependencyMCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.