What this error means

/mcp isn't available over Remote Control; in-session tool list frozen at boot-time snapshot after MCP server restart is a Claude Code failure pattern reported for developers trying to find solution to refresh/reconnect mcp tools in an active claude code remote control session without killing the entire session. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub Issue #60538 in anthropics/claude-code, opened May 19 2026 (yesterday). Details how the /mcp slash command is disabled under Remote Control and there is no CLI escape hatch to refresh the MCP tool catalog mid-session. Requires claude mcp remove+add which doesn't update live session cache. Directly impacts developers iterating on MCP server tool definitions. Category mapped to AI Coding Tools per approved mapping (Claude Code → AI Coding Tools).

Common causes

  • GitHub Issue #60538 in anthropics/claude-code, opened May 19 2026 (yesterday). Details how the /mcp slash command is disabled under Remote Control and there is no CLI escape hatch to refresh the MCP tool catalog mid-session. Requires claude mcp remove+add which doesn't update live session cache. Directly impacts developers iterating on MCP server tool definitions. Category mapped to AI Coding Tools per approved mapping (Claude Code → AI Coding Tools).

Quick fixes

  1. Confirm the exact error signature matches /mcp isn't available over Remote Control; in-session tool list frozen at boot-time snapshot after MCP server restart.
  2. Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

  • Verify the command, editor, extension, or API client that produced the error.
  • Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
  • Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

  • Keep provider/tool configuration documented.
  • Record non-secret diagnostics such as tool version, provider name, model name, and command path.
  • Add a lightweight check before CI or production workflows depend on the tool.