About this integration
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.1
- Package
- @workswarm/modelcostsaver
- Last compatibility test
- Not independently tested
Connect your agent
@workswarm/modelcostsaverPublisher README and npm manifest reviewed from pinned captures. The package was not executed, and pricing accuracy or security was not independently verified.
Capabilities: Estimate and predict LLM request costs, Compare model pricing, Recommend lower-cost models under documented constraints
Connected profiles
Additional details
io.github.sachinuppal/modelcostsaver
Source ↗ · Checked 2026-09-170.1.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17@workswarm/modelcostsaver
Source ↗ · Checked 2026-09-190.1.1
Source ↗ · Checked 2026-09-19The publisher documents a zero-configuration npx process whose default operation is local and offline.
Source ↗ · Checked 2026-09-19Core tools require no API keys; optional catalog refresh and local usage ledger features are disabled by default.
Source ↗ · Checked 2026-09-19The documented MCP client configuration launches @workswarm/modelcostsaver with npx over stdio.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19