Litport MCP server
OfficialClick 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., "@Litport MCP serverShow my proxy tokens and their usage."
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.
Litport MCP server
A Model Context Protocol server for the Litport account API: inspect proxy tokens, usage, pools, geo targeting, and build ready-to-use proxy connection URLs, directly from a coding agent or chat client.
The server is read-only. None of its tools can create, modify, delete, or disable a token, and
none of them can spend account balance — only web/app/views/users/ports.pug's dashboard export and
the Litport dashboard itself do that.
Install and configure
Create an API key at litport.net/users/settings, then add the
server to your MCP client's config with LITPORT_API_KEY in its env block.
Claude Code
claude mcp add litport -e LITPORT_API_KEY=lit_your_key_here -- npx -y @litportnet/litport-mcpOr in .mcp.json:
{
"mcpServers": {
"litport": {
"command": "npx",
"args": ["-y", "@litportnet/litport-mcp"],
"env": {
"LITPORT_API_KEY": "lit_your_key_here"
}
}
}
}Claude Desktop
Add the same block to claude_desktop_config.json under mcpServers:
{
"mcpServers": {
"litport": {
"command": "npx",
"args": ["-y", "@litportnet/litport-mcp"],
"env": {
"LITPORT_API_KEY": "lit_your_key_here"
}
}
}
}Cursor
Add the same block to .cursor/mcp.json, or use Cursor's Settings → MCP → Add new MCP Server with
command npx -y @litportnet/litport-mcp and LITPORT_API_KEY in the environment variables field.
Related MCP server: loxcorp
Credential exposure — two options
Proxy tokens carry a username/password pair. Putting every password from list_tokens into the
model's context by default is unnecessary exposure for a browse operation, so the server ships two
ways to reach a real password:
Option | Behavior |
Default ( |
|
|
|
Either way, nothing is ever permanently unreachable — the default just keeps bulk listings out of the model's context until a specific token is named.
Tools
Tool | Calls the API? | Description |
| yes | List proxy tokens, paginated by cursor; masks passwords by default. |
| yes | Get one token by id, including its real password. |
| yes | Get bandwidth usage for a token, optionally by domain and/or hourly charges. |
| yes | List PPG pools and the hubs they connect through. |
| yes | List available countries, regions, or cities for one or more pools. |
| yes | Get account balance and plan. |
| no (local) | Look up an |
| yes | Compose a ready-to-use proxy connection URL for a token, with pool/geo/session targeting. |
| yes (public) | Search the Litport documentation index for pages matching a query. |
| yes (public) | Fetch a Litport documentation page as markdown. |
All ten tools are annotated readOnlyHint: true, destructiveHint: false, idempotentHint: true.
build_proxy_url and the two token types
A pay-per-GB token is request-selected: build_proxy_url appends the pool, geo and session
segments to the username and picks the port matching the chosen protocol. A token with a saved pool
takes no pool argument and refuses a conflicting one; a token without a saved pool requires pool,
because the pool sets the price.
An unlimited token is assigned exactly one endpoint, so it takes no pool, geo or session arguments — passing them is refused by name rather than silently producing a username the proxy rejects. If its hub is no longer in service, the tool says so instead of returning a broken URL.
Parameters are validated against the published rules before anything is returned, so a malformed country slug or an out-of-range session lifetime is reported without spending a request.
Environment variables
Variable | Required | Description |
| yes | Your Litport account API key ( |
| no | Override the API base URL. Defaults to |
| no | Set to |
Development
npm install
npm test # node --test test/
npm run generate-contracts # regenerate src/contracts.generated.js from the web appsrc/contracts.generated.js is generated from the web application's canonical contract modules and
is never hand-edited.
License
MIT
Contracts
src/contracts.generated.js vendors the proxy error reference and pay-per-GB parameter rules from
the Litport web application, so explain_proxy_error and build_proxy_url answer without a network
call. It is generated, not hand-edited, and a parity check in the application fails if the two ever
disagree.
Related MCP Connectors
Read-only bank access for your AI agent. Connects Claude, ChatGPT, Cursor, Gemini, Codex.
Read-only smart-contract security intelligence for autonomous agents.
Read-only access to your CodeMouse accounts, repositories, and AI pull-request reviews.
- HAVNOAuthapp.havnre
Read-only AI access to HAVN properties, leads, tasks, files, media, and analytics.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables querying and verifying signed receipts of static inspections of public agent skills via read-only tools such as search_receipts, get_receipt, and get_verification_material.1-
- AlicenseNot gradedqualityCmaintenanceProvides live, read-only access to Robinhood Chain and Lox Corp data, enabling AI agents to query chain stats, token launches, agent details, and more.9 npmMIT
- FlicenseNot gradedqualityBmaintenanceProvides read-only inspection of Cloudflare account resources, including zones, DNS records, Workers, Pages projects, R2 buckets, and Tunnels, via a secure MCP endpoint.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search and analyze a Telegram account as a read-only knowledge source, allowing chat discovery, message search, history reading, contact inspection, and media download without exposing any mutating Telegram tools.13Apache 2.0