Vaaya MCP server
{
"mcpServers": {
"vaaya": {
"command": "npx",
"args": [
"-y",
"@vaaya/mcp@latest"
]
}
}
}{
"mcpServers": {
"vaaya": {
"command": "npx",
"args": [
"-y",
"@vaaya/mcp@latest"
]
}
}
}{
"mcpServers": {
"vaaya": {
"command": "npx",
"args": [
"-y",
"@vaaya/mcp@latest"
]
}
}
}{
"servers": {
"vaaya": {
"command": "npx",
"args": [
"-y",
"@vaaya/mcp@latest"
]
}
}
}{
"mcpServers": {
"vaaya": {
"command": "npx",
"args": [
"-y",
"@vaaya/mcp@latest"
]
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsoninstall npx -y @vaaya/mcpversion 0.6.8
What it does
An MCP server that allows AI agents to call paid APIs (search, scraping, media generation, research, compute, and more) from a single balance with spend limits set per call. Agents can access services like web search, video generation, market research, and contact data without storing vendor API keys in their environment.
- Set a spend ceiling on each API call and have it refused before execution if the quoted price exceeds your limit.
- Generate product demo videos by recording a screen capture and having the system auto-author narration and render the finished video.
- Run market research tasks that pull company information, competitor pricing, hiring signals, and product reviews with cited sources.
Tools this server exposes
| Tool | Does |
|---|---|
| consult | Describe a goal in plain language and receive a priced plan with available options. |
| use | Execute a paid API call with parameters specifying the service, action, and maximum cost in cents; refuses if quoted price exceeds the limit. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.