add_code_source · Memex MCP: Risk & Policy

WHAT IT DOES

What add_code_source does on Memex

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

WHY IT NEEDS A POLICY

Why add_code_source needs a policy

The tool performs a Write operation: it adds a new code source, which creates a new data entry in the system's memory or configuration. This is reversible (sources can be removed or updated later). The severity is medium because misconfigured or malicious code sources could be added, potentially affecting downstream operations, but the action itself is not destructive, financial, or immediately executable.

From the tool's definition The tool name 'add_code_source' suggests adding or registering a code source. In the context of a centralized agentic memory and MCP gateway, this would create or register a new code source entry in the system, constituting a reversible data modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_code_source Rate-limited

add_code_source 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_code_source": {
      "limits": [
        {
          "counter": "add_code_source_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Memex, so you can run agents against it safely.

FAQ

Questions about add_code_source

What does the add_code_source tool do? +

add_code_source. It is categorised as a Write tool in the Memex 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_code_source? +

Register the Memex MCP server in PolicyLayer and add a rule for add_code_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 Memex. Nothing to install.

What risk level is add_code_source? +

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

Can I rate-limit add_code_source? +

Yes. Add a rate_limit block to the add_code_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.

How do I block add_code_source completely? +

Set action: deny in the PolicyLayer policy for add_code_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.

What MCP server provides add_code_source? +

add_code_source is provided by the Memex MCP server (queflyhq/memex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.