Skip to main content
Glama

kobold_perf_info

Retrieve performance metrics from the Kobold MCP Server to monitor and optimize integration with KoboldAI and MCP-compatible applications.

Instructions

Get performance information

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
apiUrlNohttp://localhost:5001

Implementation Reference

  • src/index.ts:193-197 (registration)
    Registration of the 'kobold_perf_info' tool in the ListTools response, including name, description, and inputSchema based on PerfInfoSchema.
    { name: "kobold_perf_info", description: "Get performance information", inputSchema: zodToJsonSchema(PerfInfoSchema), },
  • Definition of PerfInfoSchema, which is used for input validation of the kobold_perf_info tool (aliases BaseConfigSchema).
    const PerfInfoSchema = BaseConfigSchema;
  • BaseConfigSchema defining the common 'apiUrl' parameter used by PerfInfoSchema.
    const BaseConfigSchema = z.object({ apiUrl: z.string().default('http://localhost:5001'), });
  • Handler logic within CallToolRequestSchema that dispatches GET requests for kobold_perf_info to the KoboldAI API endpoint '/api/extra/perf' using makeRequest and returns the JSON response.
    const getEndpoints: Record<string, string> = { kobold_max_context_length: '/api/v1/config/max_context_length', kobold_max_length: '/api/v1/config/max_length', kobold_generate_check: '/api/extra/generate/check', kobold_model_info: '/api/v1/model', kobold_version: '/api/v1/info/version', kobold_perf_info: '/api/extra/perf', kobold_sd_models: '/sdapi/v1/sd-models', kobold_sd_samplers: '/sdapi/v1/samplers', }; if (getEndpoints[name]) { const result = await makeRequest(`${apiUrl}${getEndpoints[name]}`); return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }], isError: false, };
  • Helper function makeRequest used by the tool handler to perform HTTP requests to the KoboldAI backend API.
    async function makeRequest(url: string, method = 'GET', body: Record<string, unknown> | null = null) { const options: RequestInit = { method, headers: body ? { 'Content-Type': 'application/json' } : undefined, }; if (body && method !== 'GET') { options.body = JSON.stringify(body); } const response = await fetch(url, options); if (!response.ok) { throw new Error(`KoboldAI API error: ${response.statusText}`); } return response.json(); }

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/PhialsBasement/KoboldCPP-MCP-Server'

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