Tokencast MCP Server

Pre-execution cost estimation for LLM agent workflows with calibration learning

Local serverstdioPython

What is the Tokencast MCP server?

Pre-execution cost estimation for LLM agent workflows with calibration learning. That is what the tokencast mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Pre-execution cost estimation for LLM agent workflows. Get a cost estimate before running any agent task, then let tokencast learn from actuals to improve accuracy over time.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • estimate_cost — Estimate API cost for a planned task before running it
  • get_calibration_status — Check whether your estimates are well-calibrated
  • get_cost_history — Browse past estimates vs actuals
  • report_session — Report actual cost at session end to improve calibration
  • report_step_cost — Record the cost of a single pipeline step during a session
  • Cursor — The Cursor tool exposed by this server
  • Windsurf — Full config examples are in docs/ide-configs/

Getting it running

The server ships on PyPI as tokencast, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Tokencast's toolset — estimate_cost, get_calibration_status, get_cost_history and 4 more — is a fair guide to whether it matches your workflow. It is maintained by krulewis; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Tokencast's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
estimate_costEstimate API cost for a planned task before running it
get_calibration_statusCheck whether your estimates are well-calibrated
get_cost_historyBrowse past estimates vs actuals
report_sessionReport actual cost at session end to improve calibration
report_step_costRecord the cost of a single pipeline step during a session
CursorThe Cursor tool exposed by this server.
WindsurfFull config examples are in [docs/ide-configs/](docs/ide-configs/).

How to install the Tokencast MCP server

{
  "mcpServers": {
    "tokencast": {
      "command": "uvx",
      "args": ["tokencast"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Tokencast to estimate cost.
  • Use Tokencast to get calibration status.
  • Use Tokencast to get cost history.

Frequently asked questions

It connects Tokencast to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (estimate_cost, get_calibration_status, get_cost_history, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tokencast directly.