Search code references by query under source_root (explicit) or source_root from dump_id.
AI agents call search_code_references to retrieve information from DumpAnalysisMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries code reference data without side effects. It performs a search operation constrained to a source root directory, matching the Read category pattern (search, list, get, fetch). The severity is low as search operations have minimal blast radius even if misused—worst case returns unexpected data.
From the tool's definition Tool name 'search_code_references' and description 'Search code references by query' indicate a query/search operation. The description specifies reading from source_root with no modification, deletion, or execution mentioned.
Documented attack patterns abuse exactly the kind of access search_code_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DumpAnalysisMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_code_references:
{
"version": "1",
"default": "deny",
"tools": {
"search_code_references": {}
}
}search_code_references 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.
Search code references by query under source_root (explicit) or source_root from dump_id. It is categorised as a Read tool in the DumpAnalysisMCP MCP Server, which means it retrieves data without modifying state.
Register the DumpAnalysis MCP server in PolicyLayer and add a rule for search_code_references: 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 DumpAnalysisMCP. Nothing to install.
search_code_references 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 search_code_references 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 search_code_references. 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.
search_code_references is provided by the DumpAnalysis MCP server (kindtis/dumpanalysismcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DumpAnalysisMCP, 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.
12 DumpAnalysisMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.