connect_source · Lucid MCP: Risk & Policy

WHAT IT DOES

What connect_source does on Lucid

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

WHY IT NEEDS A POLICY

Why connect_source needs a policy

This is a Write action because it creates a new data source connection and persists configuration/metadata about that source. While read-only in terms of not querying data, it modifies the server's internal state of available sources.

From the tool's definition The tool 'connect_source' modifies system state by establishing and storing a new data source connection. The description indicates it 'Connect[s] a data source' and 'Automatically collects schema and basic profiling,' which involves creating a new…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

connect_source Rate-limited

connect_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": {
    "connect_source": {
      "limits": [
        {
          "counter": "connect_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 Lucid, so you can run agents against it safely.

FAQ

Questions about connect_source

What does the connect_source tool do? +

Connect a data source (Excel, CSV, MySQL, or PostgreSQL). Automatically collects schema and basic profiling. It is categorised as a Write tool in the Lucid MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on connect_source? +

Register the Lucid MCP server in PolicyLayer and add a rule for connect_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 Lucid. Nothing to install.

What risk level is connect_source? +

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

Can I rate-limit connect_source? +

Yes. Add a rate_limit block to the connect_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 connect_source completely? +

Set action: deny in the PolicyLayer policy for connect_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 connect_source? +

connect_source is provided by the Lucid MCP server (wiseriaai/lucid-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.