About HTTPX MCP Server
HTTPX MCP Server exposes REST API requests through Python's httpx library. It is for AI workflows that need to call endpoints using common HTTP methods and optional authentication or headers.
Key features
- 01Send GET, POST, PUT, PATCH, and DELETE requests
- 02Pass request payloads
- 03Set optional tokens and headers
- 04Return status code and response body
Use cases
- 01Fetch data from a REST endpoint
- 02Submit or update API records
- 03Delete a resource through an API
MCP support
Exposes HTTP request tools to MCP clients, covering GET, POST, PUT, PATCH, and DELETE operations. Responses include the URL, status code, and body.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEHTTPX MCP Server
📋 Overview
The HTTPX MCP Server is an implementation of the Model Context Protocol (MCP) that performs REST API operations using the Python httpx library. It provides various methods for making HTTP requests, including GET, POST, PUT, PATCH, and DELETE.
🚀 Quick Start
Using uv:
git clone https://github.com/avishekjana-89/mcp-httpx.git
cd mcp-httpx
uv pip install .
Using Docker:
git clone https://github.com/avishekjana-89/mcp-httpx.git
cd mcp-httpx
docker build -t mcp/httpx .
🛠️ Available Tools
The server provides the following core tools for interacting with web APIs:
get_request
- Description: Executes a
GETrequest for the specified URL. - Arguments:
url: A structured URL with scheme, host, and path (e.g.,https://example.com/path?query=value).token: Optional token for authentication.headers: Optional HTTP headers as key-value pairs (e.g.,{"Content-Type": "application/json"}).
- Returns: A dictionary containing the URL, status code, and the response body.
post_request
- Description: Executes a
POSTrequest for the specified URL with a given payload. - Arguments:
url: A structured URL (e.g.,https://example.com/path).data: The payload to send with the request (e.g.,{"key": "value"}).token: Optional token for authentication.headers: Optional HTTP headers as key-value pairs (e.g.,{"Content-Type": "application/json"}).
- Returns: A dictionary containing the URL, status code, and the response body.
put_request
- Description: Executes a
PUTrequest for the specified URL with a given payload. - Arguments:
url: A structured URL (e.g.,https://example.com/path).data: The payload to send with the request (e.g.,{"key": "value"}).token: Optional token for authentication.headers: Optional HTTP headers as key-value pairs.
- Returns: A dictionary containing the URL, status code, and the response body.
patch_request
- Description: Executes a
PATCHrequest for the specified URL with a given payload. - Arguments:
url: A structured URL (e.g.,https://example.com/path).data: The payload to send with the request (e.g.,{"key": "value"}).token: Optional token for authentication.headers: Optional HTTP headers as key-value pairs.
- Returns: A dictionary containing the URL, status code, and the response body.
delete_request
- Description: Executes a
DELETErequest for the specified URL. - Arguments:
url: A structured URL (e.g.,https://example.com/path).token: Optional token for authentication.headers: Optional HTTP headers as key-value pairs.
- Returns: A dictionary containing the URL, status code, and the response body.
Usage with Claude Desktop
Using uv
To run the MCP server using uv, add the following configuration to your claude_desktop_config.json:
{
"mcpServers":{
"mcp-httpx":{
"command":"uv",
"args":[
"--directory",
"path_of_the_repo/mcp-httpx/src/mcp-httpx",
"run",
"server.py"
]
}
}
}
Using Docker
To run the MCP server via Docker, add the following configuration to your claude_desktop_config.json:
{
"mcpServers":{
"mcp-httpx":{
"command":"docker",
"args":[
"run",
"-i",
"--rm",
"--name",
"mcp-httpx",
"mcp/httpx"
]
}
}
}
License
This MCP server is licensed under the MIT License. You are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.