localhostmcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@localhostmcp make a GET request to localhost:3000/api/users"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Localhost MCP
localhostmcp is an MCP server that allows LLMs to send HTTP requests to your local development server.
Installation
You can try out piston-mcp locally without cloning it.
Install uv
To try out piston-mcp you'll need to install uv:
# On MacOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# On Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Install MCP Client
You will also need to download an MCP client to connect to piston-mcp, such as Claude Desktop.
Update MCP Client Configuration
Update the MCP client's configuration with the following configuration to connect to piston-mcp:
{
"mcpServers": {
"localhostmcp": {
"command": "uv",
"args": [
"tool",
"run",
"--from",
"git+https://github.com/alvii147/localhostmcp.git@main",
"localhostmcp"
]
}
}
}Related MCP server: HTTP MCP Server
Usage
Once you've followed the steps above, your MCP client should be able to send requests to localhost for you:

Acknowledgements
Available Tools
1 toolrequestA
Sends an HTTP request to localhost at given port, with given HTTP method, request body, and headers.
Parameters
port : int Port to send request to (e.g. port=8000 hits http://localhost:8000).
path : str Path to send request to (e.g. path=/foo/bar hits http://localhost:{port}/foo/bar).
method : str, HTTP method for request (e.g. GET, POST).
data : str, optional HTTP request body. Note: content type header is not set automatically, and must be set through "headers".
headers : dict, optional HTTP headers (e.g. {"Content-Type": "application/json"}).
Returns
int Response status code.
str Response data.
Inputs: port (required), path (required), method (required), data, +1 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools.
With a single tool, naming is trivially consistent.
One tool for making HTTP requests to localhost is slightly thin but appropriate for a focused utility.
Covers core HTTP request parameters (method, path, data, headers) but limited to localhost and lacks automatic content-type handling.
Maintenance
Related MCP Connectors
Debug webhooks from your AI agent: inspect and replay captured webhooks on localhost.
Capture, inspect, send and assert on webhooks and inbound email from your coding agent.
Call third-party APIs from agents without leaking secrets. SSRF blocked, per-key quotas.
13 privacy-first network, auth & web tools for AI agents — no API key, 60 req/min free.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to take screenshots of localhost development servers for visual verification of UI changes, reducing manual debugging cycles.24 npmMIT
- AlicenseAqualityDmaintenanceEnables AI agents to send HTTP requests to any endpoint with full control over methods, headers, query parameters, and request bodies.127 npmMIT
- AlicenseAqualityDmaintenanceConnects AI tools to local dev servers, enabling them to view pages, call APIs, read/edit files, and run commands with safety guardrails.13MIT
- AlicenseNot gradedqualityBmaintenanceEnables direct local development operations such as shell commands, interactive terminals, file patches, images, and execution history through MCP tools, accessible via HTTP/stdio or a ChatGPT tunnel.8Apache 2.0