Code-mode MCP server for the Unraid 7.2+ GraphQL API. Two tools (search + execute) with QuickJS WASM sandbox plus an optional Cloudflare Workers entry. Single-user (env) and multi-user (per-request HTTP headers) modes.
Two tools with minimal descriptions and no visible input schemas in the provided source. Both tools accept only a 'code' parameter (string), but lack structured output documentation. Descriptions are present but generic and lack actionable guidance for LLM selection. No parameter constraints, error recovery hints, or output schema documentation visible. Tool names are verb-based (search, execute) but descriptions do not clearly distinguish when to use each or what data structures are returned. No evidence of pagination, result limits, or error categorization.
Run Unraid GraphQL operations by writing JavaScript that uses the `unraid.local` namespace. Although the sandbox is JavaScript, the calls below appear synchronous — `await` is supported and recommended. Each call returns once the host-side HTTP request settles. Surfaces: - `unraid.local.graphql({ query, variables, operationName })` — POST any GraphQL document directly to `/graphql`. Returns the unwrapped `data` field. - `unraid.local.query.<fieldName>({ args, fields })` — typed query call. `args` map to GraphQL variables; `fields` is either a GraphQL selection-set string (no wrapping braces) or a shorthand array of leaf field names. `fields` is required for non-scalar return types. - `unraid.local.mutation.<fieldName>({ args, fields })` — typed mutation call, same rules. - `unraid.local.request({ method, path, body, headers })` — raw HTTP escape hatch for endpoints outside GraphQL. Returns `{ status, body, headers }`. - `unraid.local.spec` — `{ title, version, sourceUrl, queryCount, mutationCount }` for diagnostics. Operations are async — use `await`. The final expression is the tool result.
Search the Unraid GraphQL schema by writing JavaScript. The sandbox is read-only — no network. Use this tool to **discover** what to call before invoking `execute`. ## Globals - `index` — `{ namespace, title, version, sourceUrl, operations[], types }`. Each operation is the compact form: `{ kind: 'query'|'mutation', namespace: 'local', name, description, args, returnType, returnTypeFields, deprecated }`. - `unraid.local` — same shape as `index` for parity with the execute tool. May be `null` if no spec is loaded. - `searchOperations(query, limit?)` — text-ranked search across name, description, args, and return type. - `getOperation(name)` — full operation info including arg types and return-type field hints. - `findOperationsByName(substring)` — list operations whose name contains the substring (case-insensitive). - `getType(typeName)` — full named-type info (fields for OBJECT/INTERFACE/INPUT_OBJECT, members for UNION, enumValues for ENUM). - `console.log()` — captured into the tool output.
No input schema validation visible. Both tools accept only 'code' (string) with minimal constraint documentation. No length limits, format validation, or error messages for invalid code.
Output schemas not documented. Descriptions mention return values (e.g., 'final expression is returned') but do not specify field names, types, or structure. LLMs cannot plan downstream operations without knowing response shape.
Descriptions lack actionable guidance. Both tools describe what they do but omit WHEN to use each, prerequisites, or error recovery paths. 'Search the Unraid GraphQL schema' does not explain when to call search vs execute or what to do if code fails.
No error handling guidance. Descriptions do not explain what errors are possible, whether they are retryable, or what the LLM should do next. A sandbox timeout or syntax error leaves the agent without recovery direction.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | <=2025-11-25 | v2 |
Parameter 'code' lacks constraints and examples. No mention of max length, timeout, or what constitutes valid code. LLMs may pass arbitrarily large or malformed code without guidance.