mercury-mcp

by norika1207-lab · MCP Server · ★ 24

About mercury-mcp

Mercury MCP: Cross-Architecture LLM Internal Observation, as Agent Tools "Most AI coding agents don't know what's inside the model they're talking to. Mercury does." Mercury MCP exposes a 23-LLM cross-architecture observation database to any agent that speaks the Model Context Protocol (Claude Code, Cursor, Cline, Goose, etc.). Built entirely on consumer hardware (one Mac mini + one NVIDIA DGX Spark) at near-zero compute cost.

ai-agentsanchor-dimensionsconsumer-hardwarecross-architecturefrankenstein-mergellmmcpmechanistic-interpretabilitymodel-context-protocolopen-data

Quick Facts

Stars24
Forks7
LanguagePython
CategoryMCP Server
Quality Score73.2517050925967/100
Last Updated2026-05-24
Created2026-05-23
Platformsmcp, python
Est. Tokens~2k

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is mercury-mcp?

mercury-mcp is Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.. It is categorized as a MCP Server with 24 GitHub stars.

What programming language is mercury-mcp written in?

mercury-mcp is primarily written in Python. It covers topics such as ai-agents, anchor-dimensions, consumer-hardware.

How do I install or use mercury-mcp?

You can find installation instructions and usage details in the mercury-mcp GitHub repository at github.com/norika1207-lab/mercury-mcp. The project has 24 stars and 7 forks, indicating an active community.

View on GitHub → Browse MCP Server tools