GEMINI.md context files, MCP servers, TOML commands under .gemini/commands, and the extensions that bundle them. 55,505 indexed, measured the same four ways as everything else here.
Plugin Gemini CLI
A research assistant for producing Markdown reports on mainland Chinese stocks using several investment factors and cited data. It is for research, not investment advice or trading decisions.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for Rider-Waite tarot card readings. Runs locally from the tarot-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Browser Without Bloat — 76KB MCP server that gives AI agents browser superpowers. Natural language interaction, live event watching, persistent sessions, multi-tab. Runs on Termux/Android, desktop, and CI. Zero heavy dependencies. Runs locally from the bwb-browser npm package.
MCP server Claude CodeCodexCursor +2
MCP server "symgraph" as configured in grahambrooks/symgraph. Launched with cargo run -- serve. Needs 1 environment variable to run.
ip2location/mcp-ip2location-io
MCP server Claude CodeCodexCursor +2
Add your description here. Runs locally from the mcp-ip2location-io Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance. Runs locally from the prodlint npm package.
MCP server Claude CodeCodexCursor +2
MCP Server for JFrog, providing tools for development and artifact management. Remote server at myplatform.jfrog.github.io.
MCP server Claude CodeCodexCursor +2
MCP server "qlik-sense" as configured in arthurfantaci/qlik-mcp-server. Launched with /opt/homebrew/bin/python3.11 -m src.server. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Mirror MCP: Introspection for LLMs. Runs locally from the mirror-mcp npm package.
MCP server Claude CodeCodexCursor +2
Open-source MCP server for Indian (NSE/BSE) + Global financial data with built-in AI analytics. Runs locally from the finstack-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "kawaiidra" as configured in wagonbomb/kawaiidra-mcp. Runs run_server.py with python. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server for checking RU counterparties via FNS open data (EGRUL/EGRIP, EFRSB, KAD, FSSP). Runs locally from the atomno-mcp-fns-check Python package.
MCP server Claude CodeCodexCursor +2
Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes. Runs locally from the agent-aegis Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
An MCP server for deep research or task groups. Remote server at task-mcp.parallel.ai.
MCP server Claude CodeCodexCursor +2
MCP server "gpu-mcp-server" as configured in pmady/gpu-mcp-server. Runs in Docker (ghcr.io/pmady/gpu-mcp-server:v0.1.0).
MCP server Claude CodeCodexCursor +2
MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX). Runs locally from the mcp-imagenate npm package.
MCP server Claude CodeCodexCursor +2
MCP server for the Krónan grocery store API (Iceland). Runs locally from the kronan-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Local-first image, vector and document toolkit that measures its own output. Nothing uploaded. Runs locally from the vecline npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Dynamically load Claude Code skills into AI agents without copying files. Runs locally from the agent-skill-loader npm package.
MCP server Claude CodeCodexCursor +2
Open, Git-native memory protocol for MCP agents. Portable, versioned, human-editable. Runs locally from the elefante-mcp npm package.
MCP server Claude CodeCodexCursor +2
Universal memory layer for AI applications. Self-host in minutes. Runs locally from the remembra Python package.
MCP server Claude CodeCodexCursor +2
The Fastest Way to Audit Your RAG - Generate QA datasets & evaluate RAG systems in Colab, Jupyter, or CLI. Privacy-first, any LLM, visual reports. Runs locally from the ragscore Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Unofficial MCP server for Yandex Lavka: search, cart, and place grocery orders from an AI assistant. Runs locally from the yandex-lavka-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "nonmem-mcp-server" as configured in sueinchoi/nonmem-mcp-server. Runs locally from the nonmem-mcp-server Python package.