Postman Tool Generation MCP Server

Instructions

Implementation Reference

• src/index.ts:109-149 (handler)

  The handler function that executes the generate_ai_tool logic: validates input parameters, makes a POST request to Postman API endpoint '/postbot/generations/tool', and returns the generated tool code or error.

  private async handleGenerateTool(args: any): Promise<any> {
    if (!args?.collectionId || !args?.requestId || !args?.language || !args?.agentFramework) {
      throw new McpError(
        ErrorCode.InvalidParams,
        'Missing required parameters: collectionId, requestId, language, agentFramework'
      );
    }
  
    try {
      const response = await this.axiosInstance.post('/postbot/generations/tool', {
        collectionId: args.collectionId,
        requestId: args.requestId,
        config: {
          language: args.language,
          agentFramework: args.agentFramework,
        },
      });
  
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(response.data, null, 2),
          },
        ],
      };
    } catch (error) {
      if (axios.isAxiosError(error)) {
        return {
          content: [
            {
              type: 'text',
              text: `Error generating tool: ${error.response?.data?.error || error.message}`,
            },
          ],
          isError: true,
        };
      }
      throw error;
    }
  }

• src/index.ts:65-92 (registration)

  Registration of the generate_ai_tool in the ListTools response, including name, description, and input schema.

  {
    name: 'generate_ai_tool',
    description: 'Generate code for an AI agent tool using a Postman collection and request',
    inputSchema: {
      type: 'object',
      properties: {
        collectionId: {
          type: 'string',
          description: 'The Public API Network collection ID',
        },
        requestId: {
          type: 'string',
          description: 'The public request ID',
        },
        language: {
          type: 'string',
          enum: ['javascript', 'typescript'],
          description: 'Programming language to use',
        },
        agentFramework: {
          type: 'string',
          enum: ['openai', 'mistral', 'gemini', 'anthropic', 'langchain', 'autogen'],
          description: 'AI agent framework to use',
        },
      },
      required: ['collectionId', 'requestId', 'language', 'agentFramework'],
    },
  },

• src/index.ts:98-99 (registration)

  Dispatch in the CallToolRequest handler switch statement that routes to the generate_ai_tool handler.

  case 'generate_ai_tool':
    return this.handleGenerateTool(request.params.arguments);

• src/index.ts:68-91 (schema)

  Input schema definition for the generate_ai_tool tool parameters.

  inputSchema: {
    type: 'object',
    properties: {
      collectionId: {
        type: 'string',
        description: 'The Public API Network collection ID',
      },
      requestId: {
        type: 'string',
        description: 'The public request ID',
      },
      language: {
        type: 'string',
        enum: ['javascript', 'typescript'],
        description: 'Programming language to use',
      },
      agentFramework: {
        type: 'string',
        enum: ['openai', 'mistral', 'gemini', 'anthropic', 'langchain', 'autogen'],
        description: 'AI agent framework to use',
      },
    },
    required: ['collectionId', 'requestId', 'language', 'agentFramework'],
  },

• src/index.ts:12-19 (helper)

  TypeScript interface defining the structure for GenerateToolConfig, matching the tool's input and API request body.

  interface GenerateToolConfig {
    collectionId: string;
    requestId: string;
    config: {
      language: 'javascript' | 'typescript';
      agentFramework: 'openai' | 'mistral' | 'gemini' | 'anthropic' | 'langchain' | 'autogen';
    };
  }