Anvx

io.github.tje8xPublished by GitHub account tje8xv0.1.0Updated Oct 25, 2026

Track and optimize AI API spending across 16 providers with live pricing.

VerifiedSTDIODesktop onlyFinanceAI & ML

Overview

AI-generated overview

Anvx is a local MCP server that lets an assistant track and optimize AI API spending across 16 providers with live pricing.

What you can do
Track and optimize AI API spending across 16 providers using live pricing data, per the registry description. The README describes a unified view of the token economy combining LLM API costs, crypto holdings and Stripe revenue. It is offered as an MCP server for Claude Desktop and ChatGPT, alongside an OpenClaw skill and a command-line entry point. No individual tools are listed in the manifest, so the exact operations an assistant can call are not documented here.
When to use it
Worth considering when you want an assistant to help monitor or reduce what you spend on LLM APIs across multiple providers, or to see API costs alongside crypto and Stripe figures in one place.
Requirements
Runs as a local process over stdio, installed from the PyPI package token-economy-intel; desktop only. The README's development notes use uv for dependency sync and running the CLI. No authentication, environment variables or headers are declared in the manifest.
Before you install
The README says it covers crypto holdings and Stripe revenue, so it may involve financial account data; the manifest declares no authentication or credentials, so how that data is accessed is unclear. No tools are listed, so what it reads or changes cannot be verified before installing.

Installation

In SourceWeft

  1. Open Anvx in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Token Economy Intelligence

Unified intelligence across your token economy - LLM API costs, crypto holdings, and Stripe revenue in one view.

Surfaces:

  • OpenClaw skill: clawhub install token-economy-intel
  • MCP server: works with Claude Desktop and ChatGPT
  • CLI: uv run python -m engine.main --synthetic --status

Development:

  • Install deps: uv sync
  • Run tests: uv run python -m pytest engine/testing/ -v

License: MIT-0

Source: README.md at commit 40c0489

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.