Read source code from a file with optional line range. Returns numbered lines.
AI agents call get_source to retrieve information from CodeGraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays source code content without altering it. It matches the Read category definition: retrieves data with no side effects. The operation is a simple file read bounded by optional line ranges, posing minimal risk even if accessed by an AI agent with limited capability to cause harm through code inspection alone.
From the tool's definition Tool description explicitly states "Read source code from a file" with "Returns numbered lines" — a query operation with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access get_source gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraph, and nothing reaches the server without passing your rules. This is the rule we recommend for get_source:
{
"version": "1",
"default": "deny",
"tools": {
"get_source": {}
}
}get_source 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.
Read source code from a file with optional line range. Returns numbered lines. It is categorised as a Read tool in the CodeGraph MCP Server, which means it retrieves data without modifying state.
Register the CodeGraph MCP server in PolicyLayer and add a rule for get_source: 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 CodeGraph. Nothing to install.
get_source 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_source 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_source. 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_source is provided by the CodeGraph MCP server (phoenixrr2113/codebase-graph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraph, 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.
18 CodeGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.