An MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add tokencost -- npx -y tokencost-mcp-server~/.codex/config.toml
[mcp_servers.tokencost]
command = "npx"
args = ["-y", "tokencost-mcp-server"]
# codex mcp add tokencost -- npx -y tokencost-mcp-server~/.cursor/mcp.json
{
"mcpServers": {
"tokencost": {
"command": "npx",
"args": [
"-y",
"tokencost-mcp-server"
]
}
}
}.vscode/mcp.json
{
"servers": {
"tokencost": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tokencost-mcp-server"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"tokencost": {
"command": "npx",
"args": [
"-y",
"tokencost-mcp-server"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"tokencost": {
"command": "npx",
"args": [
"-y",
"tokencost-mcp-server"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"tokencost": {
"command": "npx",
"args": [
"-y",
"tokencost-mcp-server"
]
}
}
}