Search proposals by reference number (e.g.,
AI agents call search_proposals to retrieve information from Dolibarr MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries proposal data based on search criteria (reference number). It performs no mutations, deletions, code execution, or financial transactions. It is a standard read operation typical of ERP/CRM search functionality. The low severity reflects minimal blast radius if misused—an agent could only retrieve proposal information that already exists.
From the tool's definition Tool name is 'search_proposals' and description indicates it 'Search proposals by reference number', which is a query/retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Search proposals by reference number (e.g.,. It is categorised as a Read tool in the Dolibarr MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dolibarr MCP Server MCP server in PolicyLayer and add a rule for search_proposals: 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.
search_proposals is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_proposals 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 search_proposals. 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.
search_proposals 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →