AI agents call codegraph_affected to retrieve information from Context 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 analysis tool that traverses a codebase knowledge graph to identify dependencies and affected nodes. It queries existing graph structure to provide information about code relationships, similar to other codegraph_* tools (query, nodes, filter) which are read operations. There is no indication of data mutation, code execution, or side effects.
From the tool's definition Tool performs 'BFS traversal' to 'find every node that would be affected' — a graph query operation that retrieves and analyzes existing data without modifying, deleting, or executing external operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
BFS traversal: given a node name, find every node that would be affected. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for codegraph_affected: 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 Context. Nothing to install.
codegraph_affected 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 codegraph_affected 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 codegraph_affected. 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.
codegraph_affected is provided by the Context MCP server (vibhasdutta/context-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 →