mcp_ollama_status
Check the status of Ollama servers connected to the Ontology MCP, enabling real-time monitoring of AI models for ontology data querying and manipulation.
Instructions
Ollama 서버 상태 확인
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| random_string | Yes | Dummy parameter for no-parameter tools |
Input Schema (JSON Schema)
{
"properties": {
"random_string": {
"description": "Dummy parameter for no-parameter tools",
"type": "string"
}
},
"required": [
"random_string"
],
"type": "object"
}
Implementation Reference
- src/tools/index.ts:453-484 (handler)Complete tool definition for 'mcp_ollama_status' including input schema, description, and handler function. The handler delegates to ollamaService.getStatus() and formats the response.{ name: 'mcp_ollama_status', description: 'Ollama 서버 상태 확인', inputSchema: { type: 'object', properties: { random_string: { type: 'string', description: 'Dummy parameter for no-parameter tools' } }, required: ['random_string'] }, async handler(args: any): Promise<ToolResponse> { try { const result = await ollamaService.getStatus(); return { content: [{ type: 'text', text: result }] }; } catch (error) { return { content: [{ type: 'text', text: `Status 확인 오류: ${error instanceof Error ? error.message : String(error)}` }] }; } } },
- Core implementation of Ollama status check in OllamaService.getStatus(). Executes 'ollama list' command and queries /api/tags endpoint to determine server status and list models./** * Ollama 상태 확인 */ async getStatus(): Promise<string> { try { // 로컬 Ollama 목록 커맨드 실행 const { stdout, stderr } = await execAsync('ollama list'); if (stderr) { throw new Error(stderr); } // 설치된 모델 가져오기 const response = await axios.get(this.getApiUrl('tags')); return JSON.stringify({ status: 'online', localModels: stdout.trim(), apiModels: response.data }, null, 2); } catch (error) { return JSON.stringify({ status: 'offline', error: formatError(error) }, null, 2); } }
- src/index.ts:26-54 (registration)MCP Server capabilities registration enabling the 'mcp_ollama_status' tool (line 37).mcp_sparql_execute_query: true, mcp_sparql_update: true, mcp_sparql_list_repositories: true, mcp_sparql_list_graphs: true, mcp_sparql_get_resource_info: true, mcp_ollama_run: true, mcp_ollama_show: true, mcp_ollama_pull: true, mcp_ollama_list: true, mcp_ollama_rm: true, mcp_ollama_chat_completion: true, mcp_ollama_status: true, mcp_http_request: true, mcp_openai_chat: true, mcp_openai_image: true, mcp_openai_tts: true, mcp_openai_transcribe: true, mcp_openai_embedding: true, mcp_gemini_generate_text: true, mcp_gemini_chat_completion: true, mcp_gemini_list_models: true, mcp_gemini_generate_images: false, mcp_gemini_generate_image: false, mcp_gemini_generate_videos: false, mcp_gemini_generate_multimodal_content: false, mcp_imagen_generate: false, mcp_gemini_create_image: false, mcp_gemini_edit_image: false },