Returns ordered dependencies
AI agents call dependency_graph to retrieve information from Stackpress Context Provider without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns information about project dependencies. It has no capability to modify data, execute code, delete resources, or affect system state. The blast radius of misuse is minimal—an AI agent could only retrieve information already present in the system.
From the tool's definition Returns ordered dependencies — a retrieval operation with no side effects. The tool fetches and serves dependency information without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Returns ordered dependencies. It is categorised as a Read tool in the Stackpress Context Provider MCP Server, which means it retrieves data without modifying state.
Register the Stackpress Context Provider MCP server in PolicyLayer and add a rule for 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 Stackpress Context Provider. Nothing to install.
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 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 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.
dependency_graph is provided by the Stackpress Context Provider MCP server (stackpress/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 →