close_proposal · Dolibarr MCP Server MCP: Risk & Policy

WHAT IT DOES

What close_proposal does on Dolibarr MCP Server

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

WHY IT NEEDS A POLICY

Why close_proposal needs a policy

This tool modifies proposal data by updating its status field, which is a write operation. While it changes an important business state, it is reversible (proposals can be reopened or status corrected), so it falls under Write rather than Destructive.

From the tool's definition Tool description states 'Close proposal: status 2=signed/won, 3=refused/lost' — this modifies the status field of a proposal record, changing it from an open state to a terminal state (signed/won or refused/lost).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

close_proposal Rate-limited

close_proposal 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": {
    "close_proposal": {
      "limits": [
        {
          "counter": "close_proposal_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 Dolibarr MCP Server, so you can run agents against it safely.

FAQ

Questions about close_proposal

What does the close_proposal tool do? +

Close proposal: status 2=signed/won, 3=refused/lost. It is categorised as a Write tool in the Dolibarr MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on close_proposal? +

Register the Dolibarr MCP Server MCP server in PolicyLayer and add a rule for close_proposal: 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 Dolibarr MCP Server. Nothing to install.

What risk level is close_proposal? +

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

Can I rate-limit close_proposal? +

Yes. Add a rate_limit block to the close_proposal 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 close_proposal completely? +

Set action: deny in the PolicyLayer policy for close_proposal. 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 close_proposal? +

close_proposal is provided by the Dolibarr MCP Server MCP server (marioser/dolibarr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.