AI agents call braille_punchcard 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 generates/renders an ASCII representation of a Braille punchcard pattern from input text. It is a transformation/encoding operation with no side effects — it produces output (a display pattern) but does not write to any system, execute code, or modify data. The mention of 'can be physically punched for audit trail' refers to a physical offline action by a human, not an automated system action.
From the tool's definition Generate ASCII punchcard pattern from text
Attacks that exploit this kind of access
Generate ASCII punchcard pattern from text - can be physically punched for audit trail!. 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_punchcard: 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_punchcard 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_punchcard 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_punchcard. 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_punchcard 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 →