AI agents call braille_decode 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.
This tool retrieves and translates encoded data (Braille) into plaintext. It is a query/transformation operation with no ability to modify, delete, or execute code. The operation is read-only and reversible by nature (decoding is the inverse of encoding). No destructive, financial, or code execution capability exists.
From the tool's definition Tool name: 'braille_decode'; description: 'Decode Braille back to text' — performs decoding/translation of Braille input to readable text output with no data modification or external side effects.
Attacks that exploit this kind of access
Decode Braille back to text. 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_decode: 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_decode 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_decode 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_decode. 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_decode 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 →