Discover Claude Code installation on the system
AI agents call find_claude_binary to retrieve information from Shannon MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the system to locate where Claude Code is installed. It performs information retrieval only—no code execution, data modification, deletion, or side effects occur. The operation is read-only and has minimal security impact if misused by an agent.
From the tool's definition Tool name 'find_claude_binary' and description 'Discover Claude Code installation on the system' indicate a search/discovery operation that retrieves information about existing installations without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Discover Claude Code installation on the system. It is categorised as a Read tool in the Shannon MCP MCP Server, which means it retrieves data without modifying state.
Register the Shannon MCP server in PolicyLayer and add a rule for find_claude_binary: 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 Shannon MCP. Nothing to install.
find_claude_binary 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 find_claude_binary 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 find_claude_binary. 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.
find_claude_binary is provided by the Shannon MCP server (krzemienski/shannon-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 →