Read a texture back as an image so you can inspect what it currently looks like. Returns the PNG inline.
AI agents call get_texture to retrieve information from BlockbenchMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves texture data for inspection purposes without modifying, executing, or deleting anything. It is a straightforward read operation with minimal risk—the texture is already stored in Blockbench and the tool simply renders and returns it. Even if misused by an AI agent, no destructive or unwanted changes occur.
From the tool's definition Tool description explicitly states 'Read a texture back as an image so you can inspect what it currently looks like' and 'Returns the PNG inline'. The verb 'Read' and the inspection-only purpose indicate this is purely retrieval with no side effects.
Attacks that exploit this kind of access
Read a texture back as an image so you can inspect what it currently looks like. Returns the PNG inline. It is categorised as a Read tool in the BlockbenchMCP MCP Server, which means it retrieves data without modifying state.
Register the Blockbench MCP server in PolicyLayer and add a rule for get_texture: 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 BlockbenchMCP. Nothing to install.
get_texture 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 get_texture 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 get_texture. 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.
get_texture is provided by the Blockbench MCP server (sosadly/blockbench-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 →