Skip to main content
Glama

get_tools

Retrieve a list of accessible tools, methods, and parameters from the VeyraX API to execute specific actions using tool_call. Includes access to relevant flows for streamlined operations.

Instructions

"Use this tool to retrieve a list of available tools from the Veyrax API. This will return dynamic tools that user has access to. You can use this tool to get the list of tools, method names and parameters, and then use tool_call tool to call the tool with the provided parameters. This method also returns all flows with name and id that user has access to (if any). "

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesQuery question that you want find answer for. Try to ALWAYS provide this field based on conversation with user. Could be your reasoning for calling tool.
toolYesGuess the tool name. Use explicit information based on the user's request or make an educated guess. It will be used for vector search for identifying the most relevant tools.

Implementation Reference

  • The GetToolsTool class that implements the core logic of the 'get_tools' tool, including input schema validation with Zod and the execute method that queries the Veyrax API endpoint '/get-tools'.
    export class GetToolsTool extends BaseTool { name = toolName; description = toolDescription; schema = z.object({ question: z.string() .describe("Query question that you want find answer for. Try to ALWAYS provide this field based on conversation with user. Could be your reasoning for calling tool."), tool: z.string() .describe("Guess the tool name. Use explicit information based on the user's request or make an educated guess. It will be used for vector search for identifying the most relevant tools.") }); async execute({ question, tool }: z.infer<typeof this.schema>) { try { let url = '/get-tools'; const params = new URLSearchParams(); if (question) params.append('question', question); if (tool) params.append('tool', tool); if (params.toString()) { url += `?${params.toString()}`; } const { data } = await veyraxClient.get(url); return { content: [ { type: "text" as const, text: JSON.stringify(data, null, 2), }, ], }; } catch (error) { throw error; } } }
  • src/index.ts:13-13 (registration)
    Registration of the GetToolsTool instance with the MCP server.
    new GetToolsTool().register(server);
  • TypeScript interface defining the structure of the response from the get_tools tool.
    export interface GetToolsResponse { tools: { [toolName: string]: Tool; }; }
  • Zod schema for input parameters of the get_tools tool (question and tool fields).
    schema = z.object({ question: z.string() .describe("Query question that you want find answer for. Try to ALWAYS provide this field based on conversation with user. Could be your reasoning for calling tool."), tool: z.string() .describe("Guess the tool name. Use explicit information based on the user's request or make an educated guess. It will be used for vector search for identifying the most relevant tools.") });
  • src/index.ts:4-4 (registration)
    Import statement for the GetToolsTool class.
    import { GetToolsTool } from "./tools/get-tools";

Other Tools

Related Tools

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/VeyraX/veyrax-mcp'

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