5 tagged llm cost, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
Query your MCPSpend usage: cost today, top tools, recent sessions, budget projections. Runs locally from the @mcpspend/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Analyze Claude Code session cost & context attribution: output, cached re-reads, cache writes. Runs locally from the @wartzar-bee/tokenscope-mcp npm package.
MCP server Claude CodeCodexCursor
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run. Remote server at api.runvouch.com.
MCP server Claude CodeCodexCursor +2
Vendor-neutral CLI and MCP server that verifies the token and cost savings AI-coding-agent context-reduction proxies (rtk, headroom) actually deliver, measured against a real 23-task labeled corpus with a local tokenizer instead of the proxy's own claimed. Runs locally from the tokentrust-cli npm package.
MCP server Claude CodeCodexCursor
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network. Runs locally from the @workswarm/modelcostsaver npm package.