1. Conduid
  2. Communication
  3. io.github.sachinuppal/modelcostsaver
MCP server · Communication

io.github.sachinuppal/modelcostsaver

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

Unclaimed comms
37Low

Scored 4 months ago · breakdown

About io.github.sachinuppal/modelcostsaver

io.github.sachinuppal/modelcostsaver is an MCP server in the Communication category: offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

Install

Claude Code
claude mcp add io-github-sachinuppal-modelcostsaver -- npx -y @workswarm/modelcostsaver
npx
npx -y @workswarm/modelcostsaver

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (6)

compare_modelsA side-by-side cost table for a fixed token shape, with `relativeToCheapest`.

Parameters not published.

estimate_costCost of one call when you already know (or can estimate) the token counts.

Parameters not published.

optimize_request"I plan to call model X, can I do better?" Returns the cheaper option and the savings.

Parameters not published.

predict_costForecast cost across a candidate set from a prompt, before the call. Ranked cheapest-first.

Parameters not published.

record_usageAppend a local usage record (opt-in; off unless `MODELCOSTSAVER_LEDGER=on`).

Parameters not published.

select_optimal_modelThe cheapest model that meets the task tier, capabilities, and budget, with full reasoning.

Parameters not published.

Ask AI

✦

Ask AI about io.github.sachinuppal/modelcostsaver

Powered by Claude · Grounded in docs

I know everything about io.github.sachinuppal/modelcostsaver. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About io.github.sachinuppal/modelcostsaver

How do I install io.github.sachinuppal/modelcostsaver?

Run claude mcp add io-github-sachinuppal-modelcostsaver -- npx -y @workswarm/modelcostsaver, then add the server to your MCP client's configuration.

Is io.github.sachinuppal/modelcostsaver safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is io.github.sachinuppal/modelcostsaver still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.