MCP server that offloads coding tasks to local LLM (Ollama) to save Claude API tokens
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add claude-token-saver -- npx -y claude-token-saver-mcp~/.codex/config.toml
[mcp_servers.claude-token-saver]
command = "npx"
args = ["-y", "claude-token-saver-mcp"]
# codex mcp add claude-token-saver -- npx -y claude-token-saver-mcp~/.cursor/mcp.json
{
"mcpServers": {
"claude-token-saver": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"claude-token-saver": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"claude-token-saver": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"claude-token-saver": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"claude-token-saver": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
}