Skip to main content
Glama
hoangdn3

OpenRouter MCP Multimodal Server

by hoangdn3

validate_model

Verify if a model ID is compatible with OpenRouter's multimodal AI ecosystem before use.

Instructions

Check if a model ID is valid

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYesThe model ID to validate

Implementation Reference

  • The core handler function that implements the validate_model tool logic: checks if the model cache is valid, verifies if the specified model exists using modelCache.hasModel, and returns JSON {valid: boolean} or an error response.
    export async function handleValidateModel(
      request: { params: { arguments: ValidateModelToolRequest } },
      modelCache: ModelCache
    ) {
      const args = request.params.arguments;
      
      try {
        if (!modelCache.isCacheValid()) {
          return {
            content: [
              {
                type: 'text',
                text: 'Model cache is empty or expired. Please call search_models first to populate the cache.',
              },
            ],
            isError: true,
          };
        }
        
        const isValid = modelCache.hasModel(args.model);
        
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify({ valid: isValid }),
            },
          ],
        };
      } catch (error) {
        if (error instanceof Error) {
          return {
            content: [
              {
                type: 'text',
                text: `Error validating model: ${error.message}`,
              },
            ],
            isError: true,
          };
        }
        throw error;
      }
    }
  • Tool registration in the ListToolsRequest handler, defining the tool name, description, and input schema for MCP clients.
    {
      name: 'validate_model',
      description: 'Check if a model ID is valid',
      inputSchema: {
        type: 'object',
        properties: {
          model: {
            type: 'string',
            description: 'The model ID to validate',
          },
        },
        required: ['model'],
      },
    },
  • Dispatch logic in the CallToolRequest switch statement that invokes the validate_model handler with the request arguments and modelCache instance.
    case 'validate_model':
      return handleValidateModel({
        params: {
          arguments: request.params.arguments as unknown as ValidateModelToolRequest
        }
      }, this.modelCache);
  • TypeScript type definition for the tool's input parameters, matching the JSON schema in registration.
    export interface ValidateModelToolRequest {
      model: string;
    }
  • JSON Schema for input validation in the MCP tool specification.
    inputSchema: {
      type: 'object',
      properties: {
        model: {
          type: 'string',
          description: 'The model ID to validate',
        },
      },
      required: ['model'],
    },

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/hoangdn3/mcp-ocr-fallback'

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