mcpbeat Sign in

tokencast MCP Server

local only

tokencast runs on your own machine — the client starts it, so there is no endpoint to ping. 41 installs a week from pypi. Last commit 8 Apr 2026.

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

Installs per day peak 22 · avg 7 · -29% w/w
a month agotoday
41
Installs / week
pypi · tokencast
2
Stars
0 open issues
8 Apr 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 21 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add tokencast -- uvx tokencast
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "tokencast": {
      "args": [
        "tokencast"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.tokencast]
command = "uvx"
args = ["tokencast"]
.cursor/mcp.json
{
  "mcpServers": {
    "tokencast": {
      "args": [
        "tokencast"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "tokencast": {
      "args": [
        "tokencast"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to tokencast

same job, measured the same way
Slang Workflows
by shofer-dev

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

32 installs/wk local only
costwright — agent budget analysis
by hernaninverso

Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.

43 installs/wk local only
Koda
by aabxtract

Verification and memory layer for coding-agent workflows.

48 installs/wk local only
MCP Cost Tracker Router
by dbsectrainer

Real-time cost awareness for MCP agent workflows

25 installs/wk local only
Task Graph MCP
by oortonaut

MCP server for agent task workflows with phases, prompts, gates, and multi-agent coordination

local only
Kagan
by kagan-sh

AI-powered Kanban TUI for autonomous development workflows with agent orchestration

563 installs/wk local only
SAGE Wrapper
by psycgod

Command wrapper MCP server for coding agents, compression, workflows, and local automation.

341 installs/wk local only
Aichat
by rcgalbo

Inter-agent communication for multi-agent Claude Code workflows.

51 installs/wk local only

tokencast — questions

Answers built from our own checks of this server.

Why is there no uptime for tokencast?
tokencast runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package tokencast was installed 41 times last week.
How do I connect tokencast?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls tokencast straight from pypi; nothing to host, nothing to sign up for.
How many people use tokencast?
The pypi package tokencast was installed 41 times in the last week. Week over week that is -29%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is tokencast open source?
Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.