Generates Dependency & Sensitivity Graph (Repo Intelligence)
AI agents call codeguard_graph to retrieve information from Code Guard Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and visualizes repository dependencies and sensitivity classifications without creating side effects, modifying data, executing code, or deleting resources. It is a read-only intelligence/audit function consistent with a compliance and code-scanning engine. Low severity because misuse would at worst expose internal repository structure information rather than cause damage.
From the tool's definition Tool name 'codeguard_graph' and description 'Generates Dependency & Sensitivity Graph (Repo Intelligence)' indicate data retrieval and analysis operations.
Attacks that exploit this kind of access
Generates Dependency & Sensitivity Graph (Repo Intelligence). It is categorised as a Read tool in the Code Guard Ai MCP Server, which means it retrieves data without modifying state.
Register the Code Guard Ai MCP server in PolicyLayer and add a rule for codeguard_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 Code Guard Ai. Nothing to install.
codeguard_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 codeguard_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 codeguard_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.
codeguard_graph is provided by the Code Guard Ai MCP server (negraodenio/code-guard-ai). 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 →