Your MCP server returns HTTP 200 and still doesn't work A developer documented shipping a three-tool MCP server for a 16-record parts catalogue and found that HTTP 200 responses masked total tool failure: the handler's structuredContent returned part_numbers as a slash-separated string and specifications as an array of rows, violating the declared outputSchema, so clients rejected every result with "MCP error -32602: data/part_numbers must be array" before the model ever saw data. The fix was explicit projection at the MCP layer rather than loosening or rewriting the shared schema, and the developer also notes that a Streamable HTTP server without an SSE stream must answer GET with 405, since a 200 leaves clients waiting indefinitely for data frames. A field note from shipping a three-tool MCP server that real assistants actually use. I spent a day turning a dead MCP endpoint into a working one. The endpoint had been live for a day, passed every curl check I threw at it, and returned well-formed JSON-RPC for initialize and tools/list . At the HTTP layer it looked healthy. At the client layer every single tool was broken. This is the gap that MCP tooling makes easy to fall into, and the checklist I'd hand to anyone shipping an MCP server to customers rather than to themselves. A read-only reference catalogue: 16 records covering 22 OEM part numbers, exposed through three tools. | Tool | What it does | |---|---| | search parts | Free-text lookup over part numbers, titles, specifications | | get part | One full record by OEM part number | | list parts | Enumerate records, paged | Stateless Streamable HTTP, one edge function, no database, no auth. The simplest MCP server you can build — which is exactly why it's a good test case: nothing here is hidden by infrastructure. structuredContent didn't match outputSchema , and every tool died My outputSchema promised: "part numbers": { "type": "array", "items": { "type": "string" } }, "specifications": { "type": "object" } The handler returned: "part numbers": "00-000000-00013 / 00-000000-00014", "specifications": { "name": "Capillary length", "value": "24 in" } Both are reasonable shapes. They just aren't the same shape, and a real client validates the second against the first before it hands the result to the model. So the model never saw the data — it saw: MCP error -32602: data/part numbers must be array Three tools, three failures, HTTP 200 the whole time. If I had only tested with curl , I would have shipped this and found out from a customer. The fix is not "loosen the schema". It's to decide which layer owns which truth and project explicitly: js const PART NUMBER SPLIT = /\s /,;| \s /; function partNumberList v { return Array.isArray v ? v : String v .split PART NUMBER SPLIT .filter Boolean ; } function projectRecord r { return { ...r, part numbers: partNumberList r.part numbers , specifications: specRows r.specifications }; } The same record is served three ways: a static JSON file, a page with JSON-LD, and the MCP tool. I had "fixed" the mismatch by changing the schema everywhere — which broke the other two consumers, because they had been correct all along. The rule that survived: Each layer declares its own truth. The published artefact keeps the single slash-separated string it has always had; the MCP projection flattens it to an array and says so in its own outputSchema . Never let a projection rewrite the source of record, and never let one schema describe two shapes. If two consumers need different shapes, that's two schemas. Anything else is a bug waiting for the second consumer. GET /mcp returned 200, so clients waited forever The spec is explicit: a Streamable HTTP server that does not offer an SSE stream must answer GET with 405 . Returning 200 tells the client "a stream is starting", and the transport then sits waiting for data: frames that will never arrive. From the outside it looks like a hang, not an error. bash $ curl -i https://fryerparts.pages.dev/mcp HTTP/2 405 allow: POST, OPTIONS Keep the self-description — server name, tool list, /.well-known/mcp.json pointer — in the 405 body so humans doing curl still learn what the endpoint is. 405 is a refusal of the method , not of the reader . With the tools finally working, I asked a real assistant a buyer-style question: "Our fryer keeps tripping the hi-limit thermostat — which part number, and is it the same as 00-000000-00013?" It got the distinction right. It also wrote: "for the 1HF series 1HF50C/D, 1HF85C/D the hi-limit is 00-000000-00002." Those two sub-models appear nowhere in the record. The record said only "1HF". The model filled in the rest from its own priors — and a buyer reading that would order against a model number I never claimed. Server-level instructions did not prevent it. What helped was putting the boundary in the data , on every record, so it travels with the answer: function fitmentNote r { return Fitment: cross-referenced from the OEM manual for only the models listed ${named} — not certified. + Do not add sub-models, series members or equivalents that this record does not list; + safety devices must not be substituted on dimensional fit alone. ; } Re-running the same question, the answer changed to "confirm by model plate" instead of inventing two model numbers. Not a guarantee — models can still embellish — but the disclaimer is now inside the payload the agent quotes from, not in a preamble it may skip. Generalisation: if a wrong answer is expensive in your domain fitment, dosage, price, compatibility , the constraint belongs in the record, not in the prompt. Every record's canonical URL came out as https://