justdrop-mcp
Click on "Install 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., "@justdrop-mcpdrop dist/report.pdf to my phone"
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.
justdrop-mcp
Give your AI agent a way to hand you files — live, end-to-end encrypted, nothing stored.
justdrop-mcp is an MCP (Model Context Protocol) server for JustDrop. Your agent creates a room, you scan a QR or open a link on any device, and the files move — encrypted before they leave the machine, decrypted only on yours, gone when the room closes. No account on either end. The receiving device needs nothing installed: just a browser.
You: "drop dist/report.pdf to my phone"
Agent: Room code: brave-otter-4821
Link: https://justdrop.ai/app#join=brave-otter-4821
[QR code]
You: *scan, tap, done — the room self-destructs*It works the other way too: "grab the screenshot from my phone" gives you a QR; whatever you drop from the phone lands decrypted in your working directory, and the agent keeps working with it.
Install
Requires Node.js 20+.
claude mcp add justdrop -- npx -y justdrop-mcpOr in .mcp.json / any MCP client config:
{
"mcpServers": {
"justdrop": {
"command": "npx",
"args": ["-y", "justdrop-mcp"],
"env": {
"JUSTDROP_ROOT": "C:/path/to/allowed/folder"
}
}
}
}Related MCP server: vnsh-mcp
Tools
Tool | What it does |
| Send files/folders. Returns room code + link + QR immediately; the transfer runs automatically when the recipient opens the link. Pass |
| Receive files into a directory. Creates a room (code + link + QR) and saves anything dropped into it, decrypted, automatically. Pass |
| Live progress: peer presence, per-file state, saved paths. |
| Destroys a room this session created (files + metadata deleted), or leaves a joined room. |
Configuration
Env var | Default | Meaning |
|
| Backend to talk to (point at |
| server's working directory | The only directory the server may read from / save into. |
|
| Room lifetime when a tool doesn't specify one (1–1440). |
Safety model
An MCP server that reads local files is a prompt-injection target, so the guardrails are structural, not polite suggestions:
Root jail — every path (sent or saved) must resolve inside
JUSTDROP_ROOT. Anything else is refused.Credential refusal — dotfiles (
.env,.npmrc, …), SSH/TLS keys, keystores, cloud credential files, and shell histories are never sent, even when named explicitly. There is no override flag.Explicit manifests — every
dropresult lists exactly which files were queued, so the user sees what's leaving.Server-side blocklist parity — extensions JustDrop rejects (
.exe,.bat, …) are refused up front with a hint to zip instead.Ephemeral by default — rooms carry an expiry (default 60 min) and self-destruct after delivery.
How the transfer works
dropcreates a room and registers an RSA-2048 public key; the tool returns the code/link/QR immediately.When the recipient opens the link, their browser registers its own key. Rooms are one-to-one by design — treat the room code like the secret it is.
Each file gets a fresh AES-256-GCM key, encrypted for both parties' RSA keys. The encrypted blob is relayed through short-lived signed URLs — the relay never sees plaintext or keys.
Delivery is observed live; the room (and everything in it) is destroyed afterwards.
Files are encrypted in one shot in memory (format parity with the web app), so very large files need commensurate RAM. The hard cap is 2GB per file.
Local development
npm install
npm run verify # builds, boots ../justdrop-simple dev server, runs both test suites
# or piecewise, against a server you started yourself:
npm run build
node test/e2e.mjs http://localhost:3000 # core roundtrip (both directions + SSE)
node test/mcp-smoke.mjs http://localhost:3000 # full MCP stdio protocol exerciseLicense
MIT
Available Tools
1 toolstatusCheck a transferA
Shows the live status of a JustDrop transfer started with drop or receive: peer presence, per-file progress, saved paths, and errors. Call with no room_code to list all transfers in this session.
| Name | Required | Description | Default |
|---|---|---|---|
| room_code | No | Room code returned by drop/receive |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes the data shown but does not explicitly state it is read-only, nor does it disclose any behavioral traits like rate limits or authentication. The implication is non-destructive, but could be more explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences; no redundant words. Front-loaded with the main action and details, then calling modes. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool (one optional param, no output schema), the description covers the key aspects: what status information is included and how to call. It does not detail the output format, but lists contents, which is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter schema has 100% coverage describing room_code. The description adds context that omitting room_code lists all transfers, which adds value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it shows live status of a JustDrop transfer and lists included details (peer presence, per-file progress, saved paths, errors). It also distinguishes two calling modes, making the purpose precise and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description explains when to use the tool (after drop or receive) and how to call it with or without room_code. Since there are no sibling tools, no explicit when-not-to is needed, but it could include a note about prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Only one tool exists, so there is no ambiguity between tools.
With a single tool, naming consistency is trivially perfect.
A single tool for a file transfer server is too few; essential operations like initiating a drop or receive are missing.
The server only provides a status tool, lacking the core drop and receive tools needed to perform file transfers.
Maintenance
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
Free no-signup file transfer, handoff & scratchpad memory for AI agents. Share files by url.
Upload any file, get a tracked shareable link. DocSend for AI agents.
File uploads for AI agents. Upload, list, and manage files. No signup required.
Connect AnyFile to AI clients to manage files, share links, file requests, and analytics.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceIntegrates with the AgentCraft framework to enable secure communication and data exchange between AI agents, supporting both premade and custom enterprise AI agents.3
- AlicenseNot gradedqualityAmaintenanceEnables sharing and reading encrypted files (text, images, logs) for AI workflows, with automatic 24-hour expiration and host-blind security.1,132155MIT

YAFL MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely transfer files between machines via encrypted, expiring share links, with tools for upload, download, status checks, and link management.MIT- AlicenseNot gradedqualityBmaintenanceSecure file exchange MCP server enabling AI agents to upload, share, fetch, and revoke files with SHA-256 verification, malware scanning, expiry, access restrictions, and human approval workflows.12MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Managed-Digital-LLC/justdrop-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server