drop-mcp

drop-mcp

A tiny remote MCP server with a single tool, drop, that saves a file from local content or a URL into a mounted directory, acting as a file dropper for watch-folder importers.

Category
Visit Server

README

drop-mcp

A tiny remote MCP server with a single tool, drop, that saves a file — from local content or a URL — into a directory it has mounted. It doesn't know or care what happens to the file afterward; that's the mounted directory owner's job (e.g. a watch-folder importer).

Tool

drop

Parameter Required Description
filename yes Destination filename, e.g. example.epub. No path separators.
content_base64 one of these two Base64-encoded file content.
source_url one of these two URL to fetch server-side.

Returns { status: "dropped", filename, bytes } on success.

Configuration

See .env.example. DROP_MCP_TOKEN is required — the server checks Authorization: Bearer <token> on every /mcp request. DROP_DIR is where the mounted target directory should be pointed to inside the container.

Run

Prebuilt image (recommended for deployment)

Every GitHub release publishes a container image to GHCR via .github/workflows/release.yml — no local build needed:

docker run -p 3000:3000 \
  -e DROP_MCP_TOKEN=... \
  -v /host/path/to/target/dir:/drop \
  ghcr.io/transmitt0r/drop-mcp:latest   # or a pinned version, e.g. :v0.1.0

Or in a docker-compose.yml:

services:
  drop-mcp:
    image: ghcr.io/transmitt0r/drop-mcp:v0.1.0
    restart: unless-stopped
    environment:
      DROP_MCP_TOKEN: "..."
      DROP_DIR: /drop
    volumes:
      - /host/path/to/target/dir:/drop
    ports:
      - "3000:3000"

From source

pnpm install
pnpm run build
DROP_MCP_TOKEN=... DROP_DIR=/drop pnpm start

Or build the image yourself:

docker build -t drop-mcp .
docker run -p 3000:3000 \
  -e DROP_MCP_TOKEN=... \
  -v /host/path/to/target/dir:/drop \
  drop-mcp

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured