Get MCP server status, including stdio mode detection Use when native Claude Code MCP status is wrong because you need Ruflo-side server detail — tool counts per namespace, transport stats, MCP handshake errors. For just
AI agents call mcp_status to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic and status information about MCP server state without performing any mutations, triggering external operations, or side effects. It is a pure information-gathering tool for troubleshooting and monitoring purposes, fitting the Read category. Blast radius is minimal since status queries cannot damage systems.
From the tool's definition Tool name is 'mcp_status' and description states 'Get MCP server status' with read-only intent: 'tool counts per namespace, transport stats, MCP handshake errors.' The verb 'Get' and focus on monitoring/observability indicate data retrieval with no…
Attacks that exploit this kind of access
Get MCP server status, including stdio mode detection Use when native Claude Code MCP status is wrong because you need Ruflo-side server detail — tool counts per namespace, transport stats, MCP handshake errors. For just. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for mcp_status: 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 Claude Flow. Nothing to install.
mcp_status 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 mcp_status 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 mcp_status. 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.
mcp_status is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.