show_model
Retrieve detailed information for a specific model including modelfile, parameters, template, capabilities, architecture, and quantization level.
Instructions
Show detailed information for a specific model: modelfile excerpt, parameters, template, capabilities, architecture details, quantization level.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Model name (e.g. "llama3.1:8b" or "forge:b6c1"). |
Implementation Reference
- server.js:160-176 (handler)The async function showModel that executes the tool logic. It validates the 'name' argument via requireString, sends a POST request to Ollama's /api/show endpoint, and returns a structured result with modelfile excerpt, parameters, template, capabilities, details, model_info_keys, and modified_at.
async function showModel(args) { const bad = requireString(args, 'name'); if (bad) return errorResult(bad); const r = await httpRequest('POST', '/api/show', { name: args.name }); if (r.error) return errorResult(r.error); const d = r.data || {}; return textResult({ name: args.name, modelfile_excerpt: typeof d.modelfile === 'string' ? d.modelfile.slice(0, 500) : null, parameters: d.parameters || null, template: d.template || null, capabilities: d.capabilities || [], details: d.details || null, model_info_keys: d.model_info ? Object.keys(d.model_info).slice(0, 30) : [], modified_at: d.modified_at || null, }); } - server.js:294-305 (schema)The input schema definition for the show_model tool, including the 'name' property (string, required) and a description explaining it shows modelfile excerpt, parameters, template, capabilities, architecture details, and quantization level.
{ name: 'show_model', description: 'Show detailed information for a specific model: modelfile excerpt, parameters, template, capabilities, architecture details, quantization level.', annotations: { title: 'Show model details', readOnlyHint: true, destructiveHint: false, openWorldHint: false }, inputSchema: { type: 'object', properties: { name: { type: 'string', description: 'Model name (e.g. "llama3.1:8b" or "forge:b6c1").' }, }, required: ['name'], additionalProperties: false, }, - server.js:385-394 (registration)The HANDLERS mapping that registers the show_model tool name to the showModel handler function, enabling dispatch when a tools/call request arrives with name 'show_model'.
const HANDLERS = { ollama_status: ollamaStatus, list_models: listModels, list_running: listRunning, show_model: showModel, generate: generate, chat: chat, pull_model: pullModel, delete_model: deleteModel, }; - server.js:274-306 (registration)The TOOLS array that defines the show_model tool metadata (name, description, annotations, inputSchema) for the tools/list response. The show_model entry is at lines 294-306.
// ─── Tool registry ──────────────────────────────────────────────────────── const TOOLS = [ { name: 'ollama_status', description: 'Health check: whether the Ollama server is reachable and its version. Use this as a precondition before other tools if you\'re unsure whether Ollama is running.', annotations: { title: 'Ollama server status', readOnlyHint: true, destructiveHint: false, openWorldHint: false }, inputSchema: { type: 'object', properties: {}, additionalProperties: false }, }, { name: 'list_models', description: 'List locally-installed models: name, size in bytes, digest, modified timestamp, family (e.g. llama), parameter size (e.g. 8.0B), and quantization level (e.g. Q4_K_M).', annotations: { title: 'List installed models', readOnlyHint: true, destructiveHint: false, openWorldHint: false }, inputSchema: { type: 'object', properties: {}, additionalProperties: false }, }, { name: 'list_running', description: 'List models currently loaded into VRAM with their size, VRAM footprint, and expiry timestamp. Empty list means Ollama is idle.', annotations: { title: 'List running models', readOnlyHint: true, destructiveHint: false, openWorldHint: false }, inputSchema: { type: 'object', properties: {}, additionalProperties: false }, }, { name: 'show_model', description: 'Show detailed information for a specific model: modelfile excerpt, parameters, template, capabilities, architecture details, quantization level.', annotations: { title: 'Show model details', readOnlyHint: true, destructiveHint: false, openWorldHint: false }, inputSchema: { type: 'object', properties: { name: { type: 'string', description: 'Model name (e.g. "llama3.1:8b" or "forge:b6c1").' }, }, required: ['name'], additionalProperties: false, }, },