ModelCostSaver is a Model Context Protocol server. It gives any AI coding agent or IDE a free, zero-config tool that answers the three questions every agent should ask before an LLM call:
Modelcostsaver is an MCP project maintained in the sachinuppal/modelcostsaver repository. The maintainer describes its purpose as “ModelCostSaver is a Model Context Protocol server. It gives any AI coding agent or IDE a free, zero-config tool that answers the three questions every…”. Read the project documentation for the complete scope.
The documented npm package is @workswarm/modelcostsaver. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"modelcostsaver": {
"command": "npx",
"args": [
"-y",
"@workswarm/modelcostsaver"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Local read-only cyber evidence integrity checks and aggregate comparison (alpha).
Standardizes AI agent interactions for identity-related workflows using the Model Context Protocol (MCP).
Filesystem-based MCP server for Obsidian vaults — read, search, and edit notes, no app required.
A Model Context Protocol (MCP) server that provides tools from Vectara