Blast-radius analysis: transitive closure of code.references up to depth N. Hard cap of 500 symbols with pagination cursor. code.impact(X, depth=∞) is algorithmically identical to BFS closure of code.references(X).
AI agents call code.impact to retrieve information from Lore Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
code.impact is a read-only analysis tool that queries and computes derived information (transitive dependency closure) from existing code metadata without creating, modifying, deleting, or executing anything. The 'blast radius' computation is an analytical operation that produces reports about code impact, analogous to a search or graph query.
From the tool's definition Tool performs 'blast-radius analysis' and 'transitive closure' computation over existing code.references data with 'hard cap of 500 symbols' and pagination.
Attacks that exploit this kind of access
Blast-radius analysis: transitive closure of code.references up to depth N. Hard cap of 500 symbols with pagination cursor. code.impact(X, depth=∞) is algorithmically identical to BFS closure of code.references(X). It is categorised as a Read tool in the Lore Context MCP Server, which means it retrieves data without modifying state.
Register the Lore Context MCP server in PolicyLayer and add a rule for code.impact: 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 Lore Context. Nothing to install.
code.impact 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 code.impact 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 code.impact. 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.
code.impact is provided by the Lore Context MCP server (Lore-Context/lore-context). 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 →