Scan a directory for source files and populate the graph
AI agents use scan_dir to create or update resources in CodeRAG — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CodeRAG environment.
This tool reads files from a directory but its primary effect is writing/creating data in the Neo4J knowledge graph by populating it with nodes and edges representing the scanned code. The side effect is data creation in the graph database, making it a Write operation. Severity is medium since it could overwrite or pollute existing graph data if misused.
From the tool's definition 'Scan a directory for source files and populate the graph'
Documented attack patterns abuse exactly the kind of access scan_dir gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeRAG, and nothing reaches the server without passing your rules. This is the rule we recommend for scan_dir:
{
"version": "1",
"default": "deny",
"tools": {
"scan_dir": {
"limits": [
{
"counter": "scan_dir_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}scan_dir stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Scan a directory for source files and populate the graph. It is categorised as a Write tool in the CodeRAG MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CodeRAG MCP server in PolicyLayer and add a rule for scan_dir: 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 CodeRAG. Nothing to install.
scan_dir is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scan_dir 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 scan_dir. 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.
scan_dir is provided by the CodeRAG MCP server (jonnoc/coderag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeRAG, 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.
38 CodeRAG tools catalogued and risk-classified — across an index of 43,000+ MCP servers.