Medium Risk

add_file

Add a file to the knowledge base. Supports text files, code files, and documents.

How to control add_file ↓

What add_file does on Code Graph Knowledge System

AI agents use add_file to create or update resources in Code Graph Knowledge System — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Graph Knowledge System environment.

Medium Risk

Why add_file needs a policy

The tool creates or modifies the knowledge base by ingesting new files, fitting the Write category. Severity is medium because an AI agent could add malicious or incorrect code/documentation to the knowledge graph, poisoning subsequent analyses and code recommendations, but the effect is bounded to the knowledge base rather than external systems.

From the tool's definition Tool name 'add_file' and description state it 'Add[s] a file to the knowledge base', which creates/modifies data in the Neo4j knowledge graph. This is a reversible write operation (files can be removed or replaced) rather than deletion.

Documented attack patterns abuse exactly the kind of access add_file gives an agent:

How to control add_file

PolicyLayer is an MCP gateway — it sits between your AI agents and Code Graph Knowledge System, and nothing reaches the server without passing your rules. This is the rule we recommend for add_file:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_file": {
      "limits": [
        {
          "counter": "add_file_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_file 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.

  1. Create a free account and register Code Graph Knowledge System — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about add_file

What does the add_file tool do? +

Add a file to the knowledge base. Supports text files, code files, and documents. It is categorised as a Write tool in the Code Graph Knowledge System MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_file? +

Register the Code Graph Knowledge System MCP server in PolicyLayer and add a rule for add_file: 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 Code Graph Knowledge System. Nothing to install.

What risk level is add_file? +

add_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_file? +

Yes. Add a rate_limit block to the add_file 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.

How do I block add_file completely? +

Set action: deny in the PolicyLayer policy for add_file. 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.

What MCP server provides add_file? +

add_file is provided by the Code Graph Knowledge System MCP server (royisme/codebase-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Code Graph Knowledge System tool call.

Start from Code Graph Knowledge System, 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.

30 Code Graph Knowledge System tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.