Get dependencies or dependents of a node
AI agents call gid_query_deps to retrieve information from GID MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves dependency relationships within a software architecture graph. The verb 'Get' and the absence of any mention of modification, deletion, or execution of external operations confirms this is a Read operation. The data retrieved is informational for analysis purposes only. Severity is low because misuse would only surface existing architectural information without side effects.
From the tool's definition Tool name 'gid_query_deps' and description 'Get dependencies or dependents of a node' indicate retrieval of graph-based dependency information with no modification.
Attacks that exploit this kind of access
Get dependencies or dependents of a node. It is categorised as a Read tool in the GID MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GID MCP Server MCP server in PolicyLayer and add a rule for gid_query_deps: 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 GID MCP Server. Nothing to install.
gid_query_deps 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 gid_query_deps 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 gid_query_deps. 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.
gid_query_deps is provided by the GID MCP Server MCP server (potatouniverse/graph-indexed-development-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 →