Impact analysis: traverse the call/import graph to find all symbols that depend on or are affected by a given symbol. Returns risk level (LOW / MEDIUM / HIGH).
AI agents call blast_radius to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the name 'blast_radius' which might suggest destructive impact, the tool is explicitly an 'impact analysis' function that reads and traverses static code relationships and returns risk assessment information. No side effects occur from invoking this tool—it only queries code structure and returns metadata. This is a read-only code intelligence operation.
From the tool's definition Tool description states it 'traverse[s] the call/import graph to find all symbols that depend on or are affected by a given symbol' and 'Returns risk level'.
Attacks that exploit this kind of access
Impact analysis: traverse the call/import graph to find all symbols that depend on or are affected by a given symbol. Returns risk level (LOW / MEDIUM / HIGH). It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for blast_radius: 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-intel MCP Server. Nothing to install.
blast_radius 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 blast_radius 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 blast_radius. 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.
blast_radius is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). 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 →