Skip to main content
Glama
yryuu

MCP API Requester

by yryuu

MCP API Requester

A Model Context Protocol (MCP) server that enables LLMs to make arbitrary HTTP API requests (GET, POST, PUT, DELETE, etc.) with custom headers and bodies. Works with Claude Desktop and other MCP-compatible AI tools.

Features

  • 🌐 HTTP Operations: Make any HTTP request (GET, POST, PUT, DELETE, PATCH, etc.)

  • 🔧 Custom Configuration: Full control over headers, query parameters, and request body

  • 📄 JSON Support: Native handling of JSON request and response bodies

  • 🛠 Robust Error Handling: Returns 4xx/5xx responses as structured data instead of failing, allowing the LLM to inspect errors

  • 🔒 Safe Execution: Useful for testing APIs, webhooks, and interacting with external services

Related MCP server: Web Request MCP Server

Installation

No installation needed! Just configure Claude Desktop to use npx:

{
  "mcpServers": {
    "api-requester": {
      "command": "npx",
      "args": [
        "-y",
        "github:yryuu/mcp-api-requester"
      ]
    }
  }
}

Local Installation

git clone <repository-url>
cd mcp-api-requester
npm install
npm run build

Configuration

Claude Desktop

Edit your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the server configuration:

{
  "mcpServers": {
    "api-requester": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-api-requester/dist/index.js"]
    }
  }
}

Available Tools

make_request

Make an arbitrary HTTP request.

Parameters:

  • url (string): The full URL to make the request to.

  • method (string): HTTP method (GET, POST, PUT, DELETE, PATCH, etc.). Defaults to GET.

  • headers (object, optional): Key-value pairs of HTTP headers.

  • params (object, optional): Key-value pairs of URL query parameters.

  • cookies (object, optional): Key-value pairs of cookies to be included in the request.

  • body (object/string, optional): The request body. Content-Type header should match this body.

Example (GET):

Make a GET request to https://api.example.com/users?id=123

Example (POST):

POST to https://api.example.com/data with content-type application/json and body {"key": "value"}

Example (Cookies):

Make a GET request to https://api.example.com/profile with cookies {"session": "abc", "theme": "dark"}

Development

Setup

cd mcp-api-requester
npm install

Build

npm run build

Testing

Run the included manual test script:

npm test

Note: uses tsx to run the TypeScript test file directly.

Debugging

Use the MCP Inspector to test the server:

npx @modelcontextprotocol/inspector node dist/index.js

Security

  • Warning: This tool enables the LLM to make requests to any URL you provide or it discovers.

  • Ensure you only use this in a trusted environment.

  • Be cautious when asking the LLM to interact with sensitive APIs or internal services.

License

MIT

Author

yryuu

Available Tools

1 tool
make_requestA

Make an arbitrary HTTP request (GET, POST, PUT, DELETE, etc.) with custom headers and body. Returns the status, headers, and body of the response.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe full URL to make the request to.
bodyNoThe request body. Can be a JSON object or string. Content-Type header should match this body.
methodNoHTTP method (GET, POST, PUT, DELETE, PATCH, etc.). Defaults to GET.
paramsNoKey-value pairs of URL query parameters.
cookiesNoKey-value pairs of cookies to include in the request. Will be formatted into the Cookie header.
headersNoKey-value pairs of HTTP headers.

TDQS

A3.6/5.0
Behavior2/5

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

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions return values but omits critical side-effect warnings, such as the tool actually sending requests that can modify or delete resources (e.g., DELETE, POST). No security, authentication, or network-related caveats are provided.

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

Conciseness5/5

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

The description is two sentences, front-loaded with the core purpose, and includes return values. Every word contributes without redundancy or fluff.

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

Completeness4/5

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

For a generic HTTP tool with no output schema, the description adequately covers return values. It does not go into error handling or timeouts, but the core behavior is sufficiently described given the schema's parameter details.

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 coverage is 100%, so the schema already describes all six parameters. The description adds minimal extra meaning beyond referencing 'custom headers and body', which the schema already hides. This matches the baseline 3 for high schema coverage.

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 makes arbitrary HTTP requests with methods, headers, and body, and returns status/headers/body. It is specific and unambiguous, even without sibling tools to differentiate from.

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

Usage Guidelines3/5

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

The description implies usage for making HTTP requests but provides no explicit guidance on when to use it vs alternatives or when not to use it. Since there are no sibling tools, the lack of direct comparison is understandable, but it still offers no contextual cues beyond the basic purpose.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedmake_request

TDQS

A4/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion or overlapping purposes. The single tool's purpose is clearly defined as making arbitrary HTTP requests.

Naming Consistency5/5

With a single tool named 'make_request', the naming follows a clear verb_noun pattern. There are no other tools to create inconsistency.

Tool Count4/5

The server has just one tool, which is slightly below the typical 3-15 range, but for a focused HTTP request utility this is reasonable. The tool is general-purpose and well-suited to the server's stated purpose.

Completeness5/5

The single tool covers the full scope of making HTTP requests: all methods, custom headers, body, and returns status, headers, and body. There are no obvious gaps in the server's intended functionality.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that enables AI assistants to make HTTP requests (GET, POST, PUT, DELETE) to external APIs through standardized MCP tools.
    4
    2
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    A TypeScript-based MCP server that enables AI assistants to execute HTTP requests with full control over methods, headers, and body content. It facilitates seamless interaction with web APIs and endpoints through a versatile tool that handles automatic JSON formatting and response truncation.
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Universal HTTP client tool for LLM agents. Enables Claude and other MCP-compatible agents to perform GET, POST, PUT, DELETE, and other HTTP requests to any URL, including localhost and internal network addresses.
    2
    -

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/yryuu/mcp-api-requester'

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