Hi OpenAI team, we are seeing a read-only ChatGPT App MCP tool call being blocked by OpenAI safety checks before it reaches our MCP server. The tool output is: This tool call was blocked by OpenAI’s safety checks. Please double check what you are sending. The trace shows: { "externalCallTimeM…

I have also seen this fail since sometime yesterday. Absolutely benign calls are getting blocked. For example, I send this to my personal MCP server for GItea to retrieve a file: { "repo": "mcp-diagnostic-harness", "path": "pyproject.toml", "ref": "main" } This is the reply I get: “This too…

I get the same issue, which started 2 days go. I’ve tried extensive testing in the past 2 days, tried with the browser and the desktop. It is not an issue with platform - I’ve tried with a .Net api and a node.js api. Tools that do not require parameters execute successfully. But Tools that acce…

i am seeing this as well, and I’ve got both claude code and GPT working on this - what we’re finding is that files getting the block error, when retried, pass and don’t return the error

I’m seeing intermittent MCP tool-call failures in ChatGPT where benign filesystem-style connector calls are blocked by OpenAI before they reach my MCP server. The error shown in ChatGPT is: This tool call was blocked by OpenAI's safety checks. Please double check what you are sending. When this…

I was receiving the same issue yesterday, however my requests seem to be going through now (touch wood). Whilst not ideal, I found it helps listing all your tools as non-destructive.

Same here. on an app that is in production for a few months now, a simple read operation is not working. The model can discover them, but can’t call some of the tools At the moment, though, the runtime is still only surfacing the tool schemas rather than allowing me to execute those Glinded tool ca…

Same here! App in production for some months. Getting a lot of user complaints currently! This is a large scale regression (at least for us). @OpenAI_Support Please investigate ASAP.

Same here, this seems unnecessary given we ourselves have given the permission to run certain tools without filters. Please at the very least keep this safety filtering optional as it otherwise hampers our existing workflows.

ChatGPT App MCP tool calls blocked by OpenAI safety checks before reaching MCP server

ChatGPT Apps SDK

casey-chow July 10, 2026, 12:59pm 16

Hey all, we’re aware of the issues and are working to tune things.

Write actions blocked on custom MCP server – Business plan workspace, Developer Mode unavailable at workspace level

Topic		Replies	Views
Write actions blocked on custom MCP server – Business plan workspace, Developer Mode unavailable at workspace level ChatGPT Apps SDK bug , mcp	8	931	July 10, 2026
Reporting false-positive safety blocks on benign custom MCP actions Bugs plugins , mcp	1	45	October 14, 2026
MCP Connector "Resource not found" - tools/call never reaches server ChatGPT Apps SDK bug	32	2427	July 19, 2026
Previously working ChatGPT integrations are suddenly being blocked by OpenAI's safety checks. What's going on? ChatGPT chatgpt , plugin-development , bug , api , feature-request	4	318	October 13, 2026
Safety blocks with Remote Desktop Commander, including read-only SSH checks ChatGPT chatgpt , bug	0	30	October 14, 2026

ChatGPT App MCP tool calls blocked by OpenAI safety checks before reaching MCP server

Related topics