[BUG] MCP OAuth complete_authentication always fails with No OAuth flow is in progress

What this error means

"No OAuth flow is in progress for {provider}. Call mcp__{provider}__authenticate first" is a Claude Code failure pattern reported for developers trying to fix claude code mcp server oauth flow where pkce state is lost between authenticate and complete_authentication steps. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub bug report on claude-code repo: HTTP-type MCP servers with OAuth lose in-memory PKCE state before complete_authentication can consume it. Configured .mcp.json with oauth causes auth flow to fail silently. This blocks all MCP-based integrations (Asana, Datadog, Slack etc.) for enterprise users. Mapping to AI Coding Tools: Claude Code is a paid AI coding IDE, MCP auth is integral to its workflow.

Common causes

• GitHub bug report on claude-code repo: HTTP-type MCP servers with OAuth lose in-memory PKCE state before complete_authentication can consume it. Configured .mcp.json with oauth causes auth flow to fail silently. This blocks all MCP-based integrations (Asana, Datadog, Slack etc.) for enterprise users. Mapping to AI Coding Tools: Claude Code is a paid AI coding IDE, MCP auth is integral to its workflow.

Quick fixes

1. Confirm the exact error signature matches "No OAuth flow is in progress for {provider}. Call mcp__{provider}__authenticate first".
2. Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
3. Verify the account session, API key, provider settings, and environment where the failing tool is running.

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.

Sources checked

• https://github.com/anthropics/claude-code/issues/49043

Evidence note: GitHub bug report on claude-code repo: HTTP-type MCP servers with OAuth lose in-memory PKCE state before complete_authentication can consume it. Configured .mcp.json with oauth causes auth flow to fail silently. This blocks all MCP-based integrations (Asana, Datadog, Slack etc.) for enterprise users. Mapping to AI Coding Tools: Claude Code is a paid AI coding IDE, MCP auth is integral to its workflow.

Related errors

• AI Coding Tools

FAQ

What should I check first?

Start with the exact "No OAuth flow is in progress for {provider}. Call mcp__{provider}__authenticate first" text and the smallest action that reproduces it.

Can I ignore this error?

No. Treat it as a failed Claude Code workflow until the root cause is understood.

Is this guaranteed to have one fix?

No. The imported evidence supports the troubleshooting path above, but tool behavior can vary by account, plan, version, provider, and local configuration.

How do I know the fix worked?

Rerun the same command, editor action, or request. The fix is working when that action completes without "No OAuth flow is in progress for {provider}. Call mcp__{provider}__authenticate first".