> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/dapta-mcp/troubleshooting.md). # Troubleshooting Common Dapta MCP problems and how to fix them: workspace questions, sign-in issues, key errors, usage limits, removed web search tools and expired previews. Most issues come down to the workspace, the login or the API key. This table covers the common cases. | Symptom | Likely cause | Fix | | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ | | Claude asks which workspace to use | You signed in and your account has several workspaces | Answer with the workspace name (not an id). Say "switch to \" to change later | | "workspace is required" in a tool answer | A signed-in conversation that has not named its workspace yet | Tell Claude the workspace. It repeats the call | | Login page loops, or the connector shows an error in claude.ai | Stale connector session | Remove the Dapta connector and add it again with `https://mcp.dapta.ai/mcp` | | You signed in but no workspace is listed | Signing in reaches only the workspaces where you are an owner or admin | Ask your workspace owner to make you an admin, or to give you an API key for that workspace | | ChatGPT opens the browser a second time after you install the app | Installing the app links your account once more | Expected. Click **Open ChatGPT** again | | Cursor warns that the sign-in redirects to `localhost` | Cursor receives the sign-in on your own computer | Expected. Click **Allow access**, then **Open Cursor** | | 401 "Invalid or revoked API key" | Wrong or revoked key | Check the key in **MCP Access**. Create a new one if needed | | 401 that sends the client to a login although you use a key | The key was sent as `Authorization: ` without `Bearer`, or in an unknown header | Use the `x-api-key` header, `Authorization: Bearer `, or the connector URL with the key | | **Create API key** is missing or fails | Only the workspace owner can create keys | Sign in with your Dapta account instead, or ask the workspace owner for a key | | "Key limit reached (10 active keys)" | The workspace already has 10 active keys | Revoke a key you no longer use in **MCP Access**, then create the new one | | "Rate limit exceeded (60/min)" | More than 60 tool calls in one minute from the same key or login | Wait a minute and ask again | | "heavy-tool budget exceeded (100/hour)" | Heavy analytics, such as call heatmaps, variable analysis or flow run statistics, are limited to 100 calls per hour per workspace | Wait and retry later, or narrow the question to one agent or a shorter date range | | Claude says a web search tool is unknown | Web search tools were removed from the server | Use your client's own web search. Otherwise Claude asks you for the company details | | A write says the preview expired | Previews are single-use and short-lived | Ask Claude to preview again and confirm | | Old instructions mention a plugin or a skills bundle | Both are retired | Nothing to download. Connect with a login or a key as described in [Setup & Connection](/dapta-mcp/setup.md) | *** ## Still stuck? Write to and include the client you use, how you connected (login or API key), and the exact message you see. Never send your API key. *** ## Related {% content-ref url="/pages/y0N0ytQ0C9FIgnF9BZoY" %} [Verify your connection](/dapta-mcp/setup/verify.md) {% endcontent-ref %} {% content-ref url="/pages/zhvtvDJJrqsIADXWzT7U" %} [Mint your API key](/dapta-mcp/setup/mint-your-api-key.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.dapta.ai/dapta-mcp/troubleshooting.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.