Read and validate project-local graph metadata sidecar. Actions: get|validate
AI agents call graph_metadata to retrieve information from Project Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and validates metadata about the project graph structure. The 'get' action retrieves data, and 'validate' checks integrity without modifying anything. No data creation, modification, deletion, or external execution occurs. The narrow scope of reading/validating metadata with no reversible or irreversible changes classifies this as a Read operation with low severity impact.
From the tool's definition Tool name 'graph_metadata' and description explicitly states 'Read and validate project-local graph metadata sidecar. Actions: get|validate' - both 'get' and 'validate' are read-only operations with no side effects.
Attacks that exploit this kind of access
Read and validate project-local graph metadata sidecar. Actions: get|validate. It is categorised as a Read tool in the Project Graph MCP Server, which means it retrieves data without modifying state.
Register the Project Graph MCP server in PolicyLayer and add a rule for graph_metadata: 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 Project Graph. Nothing to install.
graph_metadata 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 graph_metadata 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 graph_metadata. 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.
graph_metadata is provided by the Project Graph MCP server (rnd-pro/project-graph-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 →