ModelLens MCP Server

by greatbeing Your server? Claim it

local only

ModelLens runs on your own machine — the client starts it, so there is no endpoint to ping. 1 541 installs a week from pypi. Last commit 7 Nov 2026.

See which models actually work: probe, rank and recommend across OpenAI-compatible gateways.

Installs per day peak 923 · avg 51

a month agotoday

1 541

Installs / week

pypi · modellens-mcp

Stars

0 open issues

7 Nov 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check ModelLens every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add modellens -- uvx modellens-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "modellens": {
      "command": "uvx",
      "args": [
        "modellens-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.modellens]
command = "uvx"
args = ["modellens-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "modellens": {
      "command": "uvx",
      "args": [
        "modellens-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "modellens": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "modellens-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: MODELLENS_CONFIG (Path to the endpoint configuration JSON), MODELLENS_DATA (Path to the probe history JSON).

Alternatives to ModelLens

same job, measured the same way

Hubris

by hubris

OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.

74 installs/wk answering

Proxyllm MCP

by proxyllm

OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup

118 installs/wk local only

PHASE MIND

by phase-ai

OpenAI-compatible LLM gateway: pay per request with an API key, signed receipt for each call.

7 tools answering

freellmpool

by 0xzr

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

1 209 installs/wk local only

Routara LLM Gateway

by 36412749-collab

OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).

52 installs/wk local only

by houtini-ai

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

378 installs/wk local only

Gateway Price Disclosure Check

by happy520ai

Checks whether an OpenAI-compatible endpoint publishes model prices without an account or key.

local only

Synap

by linkrra

Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.

4 tools answering

ModelLens — questions

Answers built from our own checks of this server.

Why is there no uptime for ModelLens?

ModelLens 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 modellens-mcp was installed 1 541 times last week.

How do I connect ModelLens?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls modellens-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use ModelLens?

The pypi package modellens-mcp was installed 1 541 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is ModelLens open source?

Yes — it is published under the MIT licence, written in Python and 1 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.