Skip to main content
Glama

kobold_max_context_length

Retrieve the maximum context length setting from KoboldAI's text generation server to manage input size for optimal performance.

Instructions

Get current max context length setting

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
apiUrlNohttp://localhost:5001

Implementation Reference

  • Handler logic that executes the tool: performs a GET request to the KoboldAI API endpoint '/api/v1/config/max_context_length' and returns the JSON response as text content.
    if (getEndpoints[name]) { const result = await makeRequest(`${apiUrl}${getEndpoints[name]}`); return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }], isError: false, };
  • Zod schema definition for tool input (optional apiUrl), referenced as MaxContextLengthSchema and converted to JSON schema in registration.
    const BaseConfigSchema = z.object({ apiUrl: z.string().default('http://localhost:5001'), }); // Core API schemas (api/v1) const MaxContextLengthSchema = BaseConfigSchema;
  • src/index.ts:167-171 (registration)
    Tool registration in the ListTools response, specifying name, description, and input schema.
    { name: "kobold_max_context_length", description: "Get current max context length setting", inputSchema: zodToJsonSchema(MaxContextLengthSchema), },
  • Dispatch table mapping tool name to the corresponding KoboldAI GET endpoint.
    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', };
  • Generic HTTP request helper function used by the tool handler to proxy requests to the KoboldAI server.
    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