Return a read-only local LM Studio health summary, including API and model counts.

Run a high-level, non-mutating diagnostic suite against local LM Studio.

Read and validate LM Studio's MCP JSON without changing it; secret-like values are redacted.

List locally downloaded models and discoverable metadata. Read-only.

List model instances currently loaded in memory. Read-only.

Return all discoverable local metadata and distinguish static capability from runtime configuration.

Run one tiny deterministic inference against an explicitly selected local endpoint. Never falls back to cloud.

Classify native chat, OpenAI chat completions, and Responses API as passed, unsupported, or failed.

Run a real deterministic local tool-call round trip with argument validation, fixture execution, result delivery, and continuation verification.

Verify a real streamed Chat Completions tool-call round trip, including fragmented delta reassembly, strict argument validation, fixture execution, streamed continuation, progress, and cancellation.

Test JSON Schema enforcement independently from JSON mode and prompt-only JSON, then validate output with Ajv.

Separate DECLARED metadata, passively DETECTED support, and live VERIFIED capability evidence recorded in this MCP process.

Read-only audit of loopback binding, LAN exposure, CORS, authentication, sensitive logging, and remote destinations.

Return a deterministic-schema, secret-free capability snapshot plus canonical JSON and its SHA-256 digest. This tool does not write files or rerun capability tests.

Run at most five small streaming requests and report only measurements actually available.

Capture a bounded lms log stream, redact secrets, and always terminate the child process.

MUTATING and disabled by default. Validates a downloaded model and context before invoking lms load; never downloads.

MUTATING and disabled by default. Requires one explicit loaded identifier and never unloads all models.