Skip to main content
Glama
A-Niranjan

MCP Filesystem Server

by A-Niranjan

curl_request

Execute HTTP requests to external APIs by specifying URL, method, headers, and data for integrating with web services.

Instructions

Execute a curl request to an external HTTP API. Allows specifying URL, method, headers, and data. Useful for integrating with external services via HTTP.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesFull URL to send the request to
methodNoHTTP methodGET
headersNoHTTP headers to include in the request
dataNoData to send in the request body
timeoutNoRequest timeout in seconds
followRedirectsNoWhether to follow redirects
insecureNoWhether to skip SSL certificate verification (use with caution)

Implementation Reference

  • The main handler function that constructs a curl command from the input arguments and executes it via the bash_execute tool.
    export async function handleCurlRequest(args: CurlRequestArgs, config: Config) {
      try {
        const { url, method, headers, data, timeout, followRedirects, insecure } = args
    
        // Build curl command with appropriate options
        let command = `curl -X ${method} `
    
        // Add headers
        Object.entries(headers).forEach(([key, value]) => {
          command += `-H "${key}: ${value}" `
        })
    
        // Add data if present
        if (data) {
          command += `-d '${data}' `
        }
    
        // Add additional options
        command += `-s ` // Silent mode but show error messages
        command += `--connect-timeout ${timeout} `
    
        if (followRedirects) {
          command += `-L `
        }
    
        if (insecure) {
          command += `-k `
        }
    
        // Add URL (should be last)
        command += `"${url}"`
    
        // Log the command (without sensitive headers like Authorization)
        const logCommand = command.replace(
          /-H "Authorization: [^"]*"/,
          '-H "Authorization: [REDACTED]"'
        )
        await logger.debug(`Executing curl request: ${logCommand}`)
    
        // Execute the command using bash_execute
        const result = await handleBashExecute({ command, timeout: timeout * 1000 }, config)
    
        return result
      } catch (error) {
        await logger.error('Error executing curl request', { error })
        throw error
      }
    }
  • Zod schema defining the input parameters for the curl_request tool, including URL, method, headers, data, and options.
    export const CurlRequestArgsSchema = z.object({
      url: z.string().describe('Full URL to send the request to'),
      method: z
        .enum(['GET', 'POST', 'PUT', 'DELETE', 'PATCH', 'HEAD', 'OPTIONS'])
        .default('GET')
        .describe('HTTP method'),
      headers: z
        .record(z.string(), z.string())
        .optional()
        .default({})
        .describe('HTTP headers to include in the request'),
      data: z.string().optional().describe('Data to send in the request body'),
      timeout: z.number().positive().optional().default(30).describe('Request timeout in seconds'),
      followRedirects: z.boolean().optional().default(true).describe('Whether to follow redirects'),
      insecure: z
        .boolean()
        .optional()
        .default(false)
        .describe('Whether to skip SSL certificate verification (use with caution)'),
    })
  • src/index.ts:372-378 (registration)
    Tool registration in the list_tools response, defining the name, description, and input schema for curl_request.
      name: 'curl_request',
      description:
        'Execute a curl request to an external HTTP API. ' +
        'Allows specifying URL, method, headers, and data. ' +
        'Useful for integrating with external services via HTTP.',
      inputSchema: zodToJsonSchema(CurlRequestArgsSchema) as ToolInput,
    },
  • src/index.ts:765-774 (registration)
    Dispatch case in the CallToolRequest handler that validates input with the schema and invokes the handleCurlRequest function.
    case 'curl_request': {
      const parsed = CurlRequestArgsSchema.safeParse(a)
      if (!parsed.success) {
        throw new FileSystemError(`Invalid arguments for ${name}`, 'INVALID_ARGS', undefined, {
          errors: parsed.error.format(),
        })
      }
    
      return await handleCurlRequest(parsed.data, config)
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the tool 'executes a curl request,' it doesn't disclose important behavioral traits like authentication requirements, rate limits, error handling, what happens with failed requests, or the format of returned data. The description is too high-level for a tool that performs external HTTP operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two sentences that are front-loaded with the core purpose. The first sentence states what the tool does and what it allows, while the second provides usage context. There's minimal waste, though the second sentence could be slightly more specific.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that executes external HTTP requests with 7 parameters and no output schema, the description is insufficient. It doesn't explain what the tool returns, error conditions, security implications (especially for the 'insecure' parameter), or how results are formatted. Given the complexity of HTTP operations and lack of annotations/output schema, more completeness is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 7 parameters thoroughly. The description adds minimal value beyond the schema by mentioning URL, method, headers, and data in general terms, but doesn't provide additional semantic context about how these parameters interact or special considerations for their use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('execute a curl request') and resources ('external HTTP API'), and distinguishes it from sibling tools by focusing on HTTP API integration rather than file operations or shell commands. It explicitly mentions what the tool allows (specifying URL, method, headers, and data).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('useful for integrating with external services via HTTP'), which distinguishes it from sibling tools like bash_execute or file operations. However, it doesn't explicitly state when NOT to use it or name specific alternatives for similar HTTP tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other 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/A-Niranjan/mcp-filesystem'

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