Analyze all symbols that directly call or import a given symbol. Shows what would break if the symbol changes.
AI agents call impact_analysis to retrieve information from GraphHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
impact_analysis retrieves and presents dependency and call graph information from an already-constructed knowledge graph. It performs static analysis by examining relationships between symbols but does not execute code, modify the codebase, delete data, or trigger external operations. The output informs decision-making but has no side effects. This is a classic Read operation (analyze/query).
From the tool's definition Tool description: 'Analyze all symbols that directly call or import a given symbol. Shows what would break if the symbol changes.' — purely analytical/query operation with no modification of code or data.
Documented attack patterns abuse exactly the kind of access impact_analysis gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GraphHub, and nothing reaches the server without passing your rules. This is the rule we recommend for impact_analysis:
{
"version": "1",
"default": "deny",
"tools": {
"impact_analysis": {}
}
}impact_analysis is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Analyze all symbols that directly call or import a given symbol. Shows what would break if the symbol changes. It is categorised as a Read tool in the GraphHub MCP Server, which means it retrieves data without modifying state.
Register the GraphHub MCP server in PolicyLayer and add a rule for impact_analysis: 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 GraphHub. Nothing to install.
impact_analysis 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 impact_analysis 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 impact_analysis. 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.
impact_analysis is provided by the GraphHub MCP server (slnquangtran/graph-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GraphHub, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 GraphHub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.