Skip to main content
Glama

mcp_ollama_rm

Remove Ollama models by name within the Ontology MCP server to manage and optimize AI model storage and performance for ontology data interactions.

Instructions

Ollama 모델을 삭제합니다

Input Schema

NameRequiredDescriptionDefault
nameYes삭제할 모델 이름

Input Schema (JSON Schema)

{ "properties": { "name": { "description": "삭제할 모델 이름", "type": "string" } }, "required": [ "name" ], "type": "object" }

Implementation Reference

  • Core handler implementation that sends DELETE request to Ollama API /api/delete to remove the specified model.
    async removeModel(args: { name: string }): Promise<string> { try { const response = await axios.delete( this.getApiUrl('delete'), { data: { name: args.name } } ); return JSON.stringify(response.data, null, 2); } catch (error) { if (axios.isAxiosError(error)) { throw new McpError( ErrorCode.InternalError, `Ollama API 오류: ${error.response?.data?.error || error.message}` ); } throw new McpError(ErrorCode.InternalError, `모델 삭제에 실패했습니다: ${formatError(error)}`); } }
  • Tool registration including name, description, input schema, and thin wrapper handler that delegates to ollamaService.removeModel.
    { name: 'mcp_ollama_rm', description: 'Ollama 모델을 삭제합니다', inputSchema: { type: 'object', properties: { name: { type: 'string', description: '삭제할 모델 이름' } }, required: ['name'] }, async handler(args: any): Promise<ToolResponse> { const result = await ollamaService.removeModel(args); return { content: [ { type: 'text' as const, text: result } ] }; }
  • src/index.ts:35-35 (registration)
    MCP server capabilities declaration enabling the mcp_ollama_rm tool.
    mcp_ollama_rm: true,
  • Input schema defining the required 'name' parameter for the tool.
    inputSchema: { type: 'object', properties: { name: { type: 'string', description: '삭제할 모델 이름' } }, required: ['name'] },

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bigdata-coss/agent_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server