modelcostsaver MCP Server
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.
Install
{
"mcpServers": {
"sachinuppal-modelcostsaver": {
"command": "npx",
"args": [
"-y",
"@workswarm/modelcostsaver@0.1.1"
]
}
}
}Related servers
SuperLocalMemory
78GoodLocal-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.
Codebase Memory
77GoodCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.