AI agents call get_code_snippet to retrieve information from CodeGraphMCPServer 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 data with no side effects. It reads and returns source code snippets for analysis purposes. While the server offers execute_shell_command (Execute) and other tools with higher severity, this specific tool is purely read-based. Confidence is high because the name and description clearly indicate data retrieval, though it exists on a server with code execution capabilities.
From the tool's definition Tool name 'get_code_snippet' and description 'Get source code for an entity' indicate retrieval of existing source code without modification or execution.
Documented attack patterns abuse exactly the kind of access get_code_snippet gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraphMCPServer, and nothing reaches the server without passing your rules. This is the rule we recommend for get_code_snippet:
{
"version": "1",
"default": "deny",
"tools": {
"get_code_snippet": {}
}
}get_code_snippet 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.
Get source code for an entity. It is categorised as a Read tool in the CodeGraphMCPServer MCP Server, which means it retrieves data without modifying state.
Register the CodeGraphMCPServer MCP server in PolicyLayer and add a rule for get_code_snippet: 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 CodeGraphMCPServer. Nothing to install.
get_code_snippet 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 get_code_snippet 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 get_code_snippet. 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.
get_code_snippet is provided by the CodeGraphMCPServer MCP server (nahisaho/codegraphmcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraphMCPServer, 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.
14 CodeGraphMCPServer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.