load_model
Load a 3D CAD model into the Eyeshot engine from a designated file path.
This record as markdown: /tools/a-001-byte-tesseract-26-eyeshot-mcp/load-model.md
What load_model does on Tesseract 26 Eyeshot
AI agents call load_model to retrieve information from Tesseract 26 Eyeshot without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why load_model is rated Low
This tool retrieves and imports an existing CAD model file into memory/an engine. While it may have downstream effects on the engine state, the tool itself performs a read operation—acquiring data from storage without modifying, deleting, or executing arbitrary code. The action is reversible (unload/clear the model) and has no destructive or financial impact.
From the tool's definition The tool 'load_model' reads and loads a 3D CAD model from a file path into the Eyeshot engine. The description indicates data retrieval ('Load...from a designated file path') with no modification, deletion, or code execution capability—it is a read operation…
Attacks that exploit this kind of access
The rule that runs load_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tesseract 26 Eyeshot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For load_model, this is the rule to start with:
load_model is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Tesseract 26 Eyeshot, apply this rule, and every load_model call is checked against it from then on.
Questions about load_model
Load a 3D CAD model into the Eyeshot engine from a designated file path. It is categorised as a Read tool in the Tesseract 26 Eyeshot MCP Server, which means it retrieves data without modifying state.
Register the Tesseract 26 Eyeshot MCP server in PolicyLayer and add a rule for load_model: 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 Tesseract 26 Eyeshot. Nothing to install.
load_model 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 load_model 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 load_model. 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.
load_model is provided by the Tesseract 26 Eyeshot MCP server (a-001-byte/tesseract-26-eyeshot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tesseract 26 Eyeshot, and thousands of servers like it.
This server
Across the catalogue