Search the local offline Victron register list (900+ registers with addresses, types, scale factors). Use this BEFORE making online requests — the local docs cover most questions about registers, unit IDs, data types, and device categories. For VRM cloud API search, use the victron-vrm-mcp siblin...
AI agents call victron_search_docs to retrieve information from Victron Tcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a local, offline database of Victron register documentation. It performs a read-only query operation against static reference data (900+ registers with metadata). There are no operations that create, modify, delete, or execute external actions. The stated purpose is to inform decisions before making online requests, not to perform those requests itself.
From the tool's definition Tool description states it 'Search[es] the local offline Victron register list' and 'cover[s] most questions about registers, unit IDs, data types, and device categories.' The word 'Search' and 'offline' combined with querying documentation/reference data…
Attacks that exploit this kind of access
Search the local offline Victron register list (900+ registers with addresses, types, scale factors). Use this BEFORE making online requests — the local docs cover most questions about registers, unit IDs, data types, and device categories. For VRM cloud API search, use the victron-vrm-mcp sibling package. It is categorised as a Read tool in the Victron Tcp MCP Server, which means it retrieves data without modifying state.
Register the Victron Tcp MCP server in PolicyLayer and add a rule for victron_search_docs: 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 Victron Tcp. Nothing to install.
victron_search_docs 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 victron_search_docs 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 victron_search_docs. 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.
victron_search_docs is provided by the Victron Tcp MCP server (lubosstrejcek/victron-tcp). 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 →