What this error means

Claude Code Figma connector loaded by VSCode extension despite being disabled in web + Desktop + /mcp UI is a Claude Code failure pattern reported for developers trying to fix claude code vscode extension loading disabled mcp connectors like figma. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Three official UI toggles (web, Desktop, /mcp) do not propagate disabled state. Extension still attempts handshake with disabled connector. Fails with -32600. Only manual JSON edit silences it. Max plan subscriber affected.

Common causes

  • Figma connector still loads and attempts JSON-RPC handshake even after being disabled in claude.ai web, Claude Desktop, and extension /mcp UI. Handshake fails with '-32600 Invalid content from server' causing the [object Object] toast. Only manual edit to disabledMcpServers in ~/.claude.json works.
  • Three official UI toggles (web, Desktop, /mcp) do not propagate disabled state. Extension still attempts handshake with disabled connector. Fails with -32600. Only manual JSON edit silences it. Max plan subscriber affected.

Quick fixes

  1. Confirm the exact error signature matches Claude Code Figma connector loaded by VSCode extension despite being disabled in web + Desktop + /mcp UI.
  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.