# Vaaya MCP server > Pay for third-party APIs and buy tokenized shares from a prepaid balance, with a spend ceiling stated on every agent call. - Listing: https://mcp.tc/i/vaaya - Connect: use the server's own URL `https://vaaya.ai/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: [Finance & Payments](https://mcp.tc/c/finance-payments) - Vendor: vaaya-ai - Homepage: - Repository: - Package: npm `@vaaya/mcp` ## About Vaaya gives an AI agent one prepaid balance for paid APIs such as web search, scraping, contact data, compute sandboxes, media generation, browser sessions, email inboxes and memory. The agent asks for a priced plan, then runs a call with a maximum cost. Calls above that cost are refused, and failed calls are not billed. It can also buy supported tokenized stocks on Base. It runs as a hosted Streamable HTTP endpoint at https://vaaya.ai/mcp with OAuth sign-in, or locally through the npm package @vaaya/mcp, which proxies the hosted server. A Vaaya account and prepaid funds are needed for paid calls. No vendor API keys are placed in the agent environment. ## What it can do - Get a priced plan for a task before spending - Run paid API calls with a per-call maximum cost - Use search, scraping, research and browser services from one balance - Run code in per-second-billed compute sandboxes - Generate images, video, speech and music - Buy supported tokenized stocks and check order status - Check portfolio buying power and prepaid balance ## Example prompts - "Consult Vaaya for a plan to scrape this site, then run it with a 5 cent limit." - "List the tokenized stocks I can buy with my Vaaya balance." - "Buy $10 of Apple tokenized stock and tell me when the order is confirmed." - "Run a deep research report on competitor pricing using Vaaya." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http vaaya https://vaaya.ai/mcp ``` 2. Start Claude Code, type `/mcp`, pick **vaaya** and choose **Authenticate**. A browser window opens for the vaaya-ai sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Vaaya** and paste this URL: ```url https://vaaya.ai/mcp ``` 3. Click **Add**, then **Connect**, and sign in when vaaya-ai 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://vaaya.ai/mcp` and click **Add**. 3. Click **Connect** and sign in when vaaya-ai 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, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://vaaya.ai/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to vaaya-ai to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### 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": { "vaaya": { "url": "https://vaaya.ai/mcp" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"vaaya","type":"http","url":"https://vaaya.ai/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "vaaya": { "type": "http", "url": "https://vaaya.ai/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": { "vaaya": { "serverUrl": "https://vaaya.ai/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 vaaya --url https://vaaya.ai/mcp codex mcp login vaaya ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.vaaya] url = "https://vaaya.ai/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http vaaya https://vaaya.ai/mcp ``` Then, inside Gemini CLI, run `/mcp auth vaaya` 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": { "vaaya": { "type": "http", "url": "https://vaaya.ai/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://vaaya.ai/mcp`. ## Details - Server version: 0.6.8 - Last checked: 2026-10-04 (reachable, asks for credentials) - Listed: 2026-10-04 - Updated: 2026-10-04 --- Source: https://mcp.tc/i/vaaya (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report