AI agents call braille_encode to retrieve information from Sensory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a stateless text-to-Braille encoding transformation. It neither modifies external state, executes commands, deletes data, nor involves financial operations. It simply converts input text to a different representation (Braille Unicode), equivalent to a read/query operation.
From the tool's definition "Encode text to Braille Unicode characters" - this is a pure transformation/conversion operation that reads input text and returns Braille Unicode output with no side effects.
Attacks that exploit this kind of access
Encode text to Braille Unicode characters. It is categorised as a Read tool in the Sensory MCP Server, which means it retrieves data without modifying state.
Register the Sensory MCP server in PolicyLayer and add a rule for braille_encode: 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 Sensory. Nothing to install.
braille_encode 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 braille_encode 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 braille_encode. 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.
braille_encode is provided by the Sensory MCP server (jaspertvdm/mcp-server-sensory). 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 →