OpenAI API / OpenAI API

OpenAI Realtime API MCP tool calls not executing with Azure deployment

Fix OpenAI Realtime API MCP integration: tool calls never execute despite MCP server being connected and verified with inspector Includes evidence for OpenAI API troubleshooting demand.

Source-backed Last updated May 16, 2026 1 source Needs local verification

Category: OpenAI API
Error signature: Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned
Quick fix: Check the build output, project root, and deployment platform configuration before redeploying.
Updated: May 16, 2026
Verification status: Source-backed
Evidence: 1 public source URL

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for OpenAI API, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned is a OpenAI API failure pattern reported for developers trying to fix openai realtime api mcp integration: tool calls never execute despite mcp server being connected and verified with inspector. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue openai/openai-python#3128 (Apr 2026, bug-labeled): OpenAI Realtime SIP app connected to Twilio with MCP server (Langflow). MCP verified working with @modelcontextprotocol/inspector. Tool calls never fire — app only returns instruction text. Affects Azure OpenAI Realtime endpoint. Category mapping: OpenAI API (API feature failure).

Common causes

GitHub issue openai/openai-python#3128 (Apr 2026, bug-labeled): OpenAI Realtime SIP app connected to Twilio with MCP server (Langflow). MCP verified working with @modelcontextprotocol/inspector. Tool calls never fire — app only returns instruction text. Affects Azure OpenAI Realtime endpoint. Category mapping: OpenAI API (API feature failure).

Quick fixes

Confirm the exact error signature matches Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned.
Check the OpenAI API account, local tool state, and provider configuration involved in the failing workflow.
Check the build output, project root, and deployment platform configuration before redeploying.

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

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

Diagnostic flow for this page

Match Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned exactly before applying the quick fix.
Compare the failing environment with OpenAI API versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned mean in OpenAI API?

Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned indicates the workflow described by "OpenAI Realtime API MCP tool calls not executing with Azure deployment" failed in a OpenAI API context. Start by confirming the exact signature and the component that emitted it.

What should I check first for Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned?

Check whether this cause matches your environment: GitHub issue openai/openai-python#3128 (Apr 2026, bug-labeled): OpenAI Realtime SIP app connected to Twilio with MCP server (Langflow). MCP verified working with @modelcontextprotocol/inspector. Tool calls never fire — app only returns instruction text. Affects Azure OpenAI Realtime endpoint. Category mapping: OpenAI API (API feature failure).

Is the Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned guidance source-backed?

The "OpenAI Realtime API MCP tool calls not executing with Azure deployment" page is labeled source-backed. It has 1 public source URL from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned?

For "OpenAI Realtime API MCP tool calls not executing with Azure deployment", avoid applying "Check the build output, project root, and deployment platform configuration before redeploying." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned?

For "OpenAI Realtime API MCP tool calls not executing with Azure deployment", collect the failing OpenAI API command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.