# LLM Gateway MCP server > Chat with any LLM, generate images, browse models and check usage and costs across providers through LLM Gateway. - Listing: https://mcp.tc/i/llm-gateway - Connect: use the server's own URL `https://api.llmgateway.io/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml) - Vendor: theopenco - Homepage: - Docs: - Repository: ## About Connects an MCP client to LLM Gateway, an open-source gateway that routes requests to multiple LLM providers. You can generate text or images, browse available models, and inspect usage and costs, including your most-used models, providers and coding apps. It runs as a hosted Streamable HTTP endpoint at https://api.llmgateway.io/mcp. Access needs an LLM Gateway API key sent as a Bearer token in the Authorization header, or OAuth 2.0 sign-in for clients that prefer it. Keys are created in the LLM Gateway dashboard. ## What it can do - Chat with models from multiple LLM providers - Generate images - Browse available models - Check usage and inference costs - Rank providers, models, coding apps or API keys by requests, cost or tokens ## Example prompts - "Show my LLM Gateway usage and costs for this month" - "Rank my models by inference cost" - "Generate an image of a lighthouse at dusk" - "Which coding apps use the most tokens on my account?" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http llm-gateway https://api.llmgateway.io/mcp ``` 2. Start Claude Code, type `/mcp`, pick **llm-gateway** and choose **Authenticate**. A browser window opens for the theopenco sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**. 2. Name it **LLM Gateway** and paste this URL: ```url https://api.llmgateway.io/mcp ``` 3. Click **Add**, then **Connect**, and sign in when theopenco asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://api.llmgateway.io/mcp` and click **Add**. 3. Click **Connect** and sign in when theopenco asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**. 2. Enter a name for the server. 3. Under **Connection**, paste `https://api.llmgateway.io/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to theopenco to sign in. 4. Check **I understand and want to continue**, then select **Create as a plugin**. Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can). ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "llm-gateway": { "url": "https://api.llmgateway.io/mcp" } } } ``` Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"llm-gateway","type":"http","url":"https://api.llmgateway.io/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "llm-gateway": { "type": "http", "url": "https://api.llmgateway.io/mcp" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "llm-gateway": { "serverUrl": "https://api.llmgateway.io/mcp" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add llm-gateway --url https://api.llmgateway.io/mcp codex mcp login llm-gateway ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.llm-gateway] url = "https://api.llmgateway.io/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http llm-gateway https://api.llmgateway.io/mcp ``` Then, inside Gemini CLI, run `/mcp auth llm-gateway` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "llm-gateway": { "type": "http", "url": "https://api.llmgateway.io/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.llmgateway.io/mcp`. ## Details - Server version: 1.0.0 - Last checked: 2026-10-31 (reachable, asks for credentials) - Listed: 2026-10-28 - Updated: 2026-10-28 --- Source: https://mcp.tc/i/llm-gateway (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report