semantic_model.extend
Idempotently add target-specific component types to an existing semantic twin.
This record as markdown: /tools/visionmcp/semantic-model.extend.md
What semantic_model.extend does on Visionmcp
AI agents use semantic_model.extend to create or update resources in Visionmcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Visionmcp environment.
Why semantic_model.extend is rated Medium
This tool creates or modifies data in a reversible manner by extending a semantic model with new component types. It is not destructive (nothing is deleted), does not execute arbitrary code, and does not involve financial operations.
From the tool's definition The tool description states it will 'add target-specific component types to an existing semantic twin.' The verb 'add' and the action of modifying an existing model structure indicates data modification.
Attacks that exploit this kind of access
The rule that runs semantic_model.extend safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For semantic_model.extend, this is the rule to start with:
semantic_model.extend 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every semantic_model.extend call is checked against it from then on.
Questions about semantic_model.extend
Idempotently add target-specific component types to an existing semantic twin. It is categorised as a Write tool in the Visionmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vision MCP server in PolicyLayer and add a rule for semantic_model.extend: 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 Visionmcp. Nothing to install.
semantic_model.extend is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the semantic_model.extend 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 semantic_model.extend. 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.
semantic_model.extend is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue