AI agents use update_node 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 modifies data within the CodeRAG knowledge graph but does not delete data (Destructive), execute code (Execute), create financial transactions (Financial), or trigger external operations. It is a Write operation that updates metadata about code nodes.
From the tool's definition Tool name 'update_node' and description 'Update an existing code node' indicate modification of existing data in the Neo4J knowledge graph. The action is reversible (can be updated again or reverted), and operates on graph nodes representing code structure.
Documented attack patterns abuse exactly the kind of access update_node 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 update_node:
{
"version": "1",
"default": "deny",
"tools": {
"update_node": {
"limits": [
{
"counter": "update_node_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_node 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.
Update an existing code node. 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 update_node: 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.
update_node 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 update_node 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 update_node. 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.
update_node 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.