DeskLink
Can load a Git MCP server such as @modelcontextprotocol/server-git through mcp.json, exposing repository tools and Git operations via DeskLink’s unified MCP endpoint.
Supports ngrok as an optional tunnel provider to expose the local MCP endpoint publicly, configured through the tunnel settings and NGROK_AUTHTOKEN.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
DeskLink (JavaScript / TypeScript)
Turn your local computer into a remotely accessible MCP endpoint for cloud AI agents.
DeskLink is a thin authenticated bridge. It loads local MCP servers (especially STDIO servers defined in a standard mcp.json), discovers their tools, and exposes all of them through a single Streamable HTTP URL (optionally tunnelled with ngrok).
Package name on npm: desklink
CLI commands: desklink and devlink (alias)
Feature parity with the Python package.
What it does
Loads MCP servers from a standard
mcp.json(or injects the official@modelcontextprotocol/server-filesystemif none are defined).Starts a local Streamable HTTP server (default
http://127.0.0.1:8765/mcp).Proxies every discovered tool under a namespaced name (
servername__toolname).Protects the endpoint with a device bearer token and/or OAuth 2.1 (Authorization Code + PKCE).
Optionally opens an ngrok tunnel so the same endpoint is reachable from the public internet.
Provides a web dashboard + consent screen for OAuth apps.
You keep full control: tools stay on your machine, approvals can prompt you, and tokens never leave your machine unless you choose.
Related MCP server: Levitate
Quick start
npm install -g desklink
# Optional but recommended for public tunnels
export NGROK_AUTHTOKEN=your_ngrok_token
desklink startOn first run DeskLink will:
Create
~/.desklink/token(device bearer token)Start the official filesystem MCP server scoped to your home directory (unless you provide an
mcp.json)Print the local and public MCP URLs plus the auth token
Useful flags
desklink start \
--mcp-config ./mcp.json \
--config ./desklink.config.json \
--dir ~/Documents --dir ~/projects \
--port 8765 \
--tunnel ngrok # or "none" for local-only
--token my-static-token # optional override
-v # verbose loggingConfiguration
DeskLink looks for two files (first match wins):
File | Search order |
DeskLink settings |
|
MCP servers |
|
Example mcp.json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/Documents", "/Users/you/projects"]
},
"my-custom-server": {
"command": "node",
"args": ["./my-mcp-server.js"],
"env": { "API_KEY": "..." }
}
}
}Any STDIO MCP server works. Tools appear as filesystem__read_file, my-custom-server__do_something, etc.
Example desklink.config.json
{
"logging": { "level": "info" },
"tracing": {
"enabled": true,
"level": "basic",
"redact_sensitive": true
},
"auth": {
"enabled": true
},
"approvals": {
"default": "auto",
"tools": {
"filesystem__write_file": "prompt",
"filesystem__create_directory": "prompt"
}
},
"server": {
"host": "127.0.0.1",
"port": 8765,
"mcp_path": "/mcp"
},
"tunnel": {
"provider": "ngrok"
}
}Approvals
"auto"– run immediately"prompt"– ask in the terminal before the tool executes
Tracing levels
none/basic/full(full logs args + truncated results; sensitive keys are redacted by default)
Authentication
1. Device bearer token (always available)
Stored at ~/.desklink/token. Sent as:
Authorization: Bearer <token>2. OAuth 2.1 (recommended for cloud agents)
DeskLink acts as a full OAuth 2.1 authorization server so agents never see your device token.
Create an app (CLI)
desklink create oauth-app claude
desklink create oauth-app chatgpt
desklink create oauth-app manus
desklink create oauth-app cursor
desklink create oauth-app custom --name "My Agent" --publicPresets come with sensible default scopes. Confidential clients get a Client Secret; public clients rely on PKCE.
Endpoints (when desklink start is running)
Purpose | URL |
Metadata |
|
Authorize |
|
Token |
|
Revoke |
|
Dynamic registration |
|
Dashboard |
|
MCP |
|
When using a tunnel the same paths work on the public URL.
Manage apps
desklink oauth list
desklink oauth revoke <client_id>Or open /dashboard in a browser – create apps, view Client IDs, revoke access, and see recent activity.
Scopes
Scope | Meaning |
| Call tools |
| Read resources |
| Read files |
| Write / create |
| Full control |
All OAuth state lives as JSON under ~/.desklink/oauth/ (no database).
Customer usage flow
Install & start DeskLink on the machine whose tools/files you want to expose.
(Optional) Create an OAuth app for the agent you will connect.
Give the agent the public MCP URL + either the device token or the OAuth Client ID (and secret if confidential).
The agent discovers tools via normal MCP
tools/listand calls them. DeskLink proxies the call to the local STDIO server, applies your approval policy, and returns the result.Stop with
Ctrl+C. The tunnel and local servers shut down cleanly.
Extensibility
Any STDIO MCP server – just add it to
mcp.json. No code changes required.Approvals & tracing – configure per-tool policies and log levels without touching the bridge.
Tunnel providers – currently
ngrokandnone. The interface is abstract; additional providers can be added later.Auth – static bearer + full OAuth 2.1 (PKCE, refresh tokens, dynamic registration, consent screen). Device identity stays separate from OAuth application credentials.
Programmatic use – import
desklinkand driveDeskLinkServer/McpBridgefrom your own Node process.
import { loadConfig, ensureDefaultFilesystem, DeskLinkServer } from "desklink";
const cfg = ensureDefaultFilesystem(loadConfig());
const server = new DeskLinkServer(cfg);
await server.startHttpServer();
await server.startTunnel();Development
git clone https://github.com/sam-14uel/desklink-js.git
cd desklink-js
npm install
npm run build
npm run dev -- start --tunnel noneRequires Node.js ≥ 18.
License
MIT © Samuel Obinna Chimdi
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Secure and manage MCP servers through the Speakeasy AI Control Plane from your agent.
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExposes any stdio-based MCP server to the internet via HTTP/SSE transport, enabling remote agents to access MCP tools over a network.MIT
- AlicenseNot gradedqualityBmaintenanceLifts local stdio MCP servers into remote Streamable HTTP endpoints for cloud-hosted AI clients, with bearer-token auth and tool policy filtering.12 npmMIT
- AlicenseNot gradedqualityCmaintenanceExposes local stdio MCP servers to chat AIs through temporary public URLs, providing both a Streamable HTTP gateway and a REST+OpenAPI bridge for integration with ChatGPT and other clients.MIT
- AlicenseNot gradedqualityBmaintenanceEnables running local MCP servers on machines behind NAT and accessing their tools from anywhere through a single Streamable HTTP endpoint, without opening any inbound ports.MIT