"A lightweight, self-hosted Git service" matching MCP servers:

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

This MCP server enables employees to ask IT questions, receive evidence-backed answers, and trigger traceable work orders or escalations through authenticated MCP tools. It also supports status checks, durable action jobs, and auditable work-order, Excel ledger, and escalation workflows.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

AI Self Audit - MCP server providing AI-powered tools and automation by MEOK AI Labs

Self-healing MCP server that monitors database schema changes, detects differences, and automatically updates ontology mappings using AI to ensure agents continue working without manual intervention.

A self-updating MCP system that analyzes design and code inputs with an LLM, refines them through conversation, and crystallizes approved patterns into a local skill library for MCP agents.

Enables AI-to-AI consultation for critical thinking and complex reasoning via OpenRouter, allowing one AI to delegate tasks to another AI model.

A lightweight topological arbitration MCP server for multi-agent clusters, using Topological Data Analysis to resolve decision conflicts and enable consensus among agents.

Automates the AWS Foundational Technical Review (FTR) partner self-assessment by evaluating SOC 2 and WAFR reports against defined controls, returning structured PASS/FAIL decisions with reasoning.

A self-hosted MCP server for building a reusable AI-video reference library. It stores named Elements as structured reference images and provides them to MCP-compatible agents via @tags.

Enables AI-powered multi-provider routing and chat through an MCP interface, with smart fallback, persistent sessions, and learning from historical performance.

Enables generating Power BI .pbit dashboards from CSV files or live SQL databases using plain-English prompts and optional reference-image layouts, with local-only processing and MCP tools for Claude Desktop.

A local, fully vectorized computational engine for stock market analysis that enables AI to perform factor calculation, strategy backtesting, IC analysis, and GPU-based multi-dimensional visualization using local DuckDB data.

An MCP server that provides a unified API to access multiple AI models and Chinese compliance tools, including ad keyword detection, GEO visibility checks, and SEO scanning.

Self-hosted ML inference MCP server providing embeddings and summarization tools using sentence-transformers and Ollama, with low-latency preloaded models and API-key authentication.

Enables local programs to push text and images to AI assistants via HTTP and retrieve AI-generated responses, acting as a local data bridge between your code and MCP-capable AI tools.

Enables evaluation of local models by giving each agent session its own sandboxed wiki folder where the model ingests sources, creates and cross-links pages, answers questions, and lints its notes, with the results graded as an Obsidian vault.

Enables AI-powered UI component generation from natural language descriptions, integrating with IDEs like Cursor and Windsurf.

An MCP server for generating images and checking generation status through ComfyUI's API. It allows interaction with local ComfyUI instances by providing workflow-based image generation and status checking tools.

Provides a local-first MCP tool surface for generating images and videos across dozens of Higgsfield AI models (Sora, Veo, Kling, Seedance, FLUX, Soul, and more), including Soul character training, speech/talking-head video, batch submission, job status polling, model recommendation and param validation, and account/history access. It routes requests across both the official REST API and the experimental cloud web backend with retries, circuit breaking, and typed structured output.

Enables interactive AI chat through the Anthropic API, with document retrieval, slash commands, and extensible MCP tool integrations.

MCP server for deterministic, zero-dependency context-window math, enabling token estimation, text truncation, and budget reporting without a tokenizer.

Enables any agent to ask typed questions (Noul, Choice, Score) against Jev's decision model and receive structured answers with probabilities, confidence, and an auditable act/review/abstain decision.

Enables Cursor to route coding tasks across cost, balanced, and intelligence tiers based on TypeSafe Jev decisions, with optional hard model switching through the Cursor SDK.

Self-hosted prompt library with an MCP server: list, fetch, save and version prompt templates with {{variables}} from ChatGPT or any MCP client, with OAuth sign-in. Also available as a hosted service on neadlab.com.

Enables MCP clients to ask questions over the indexed document corpus and search handbook passages, returning cited answers and ranked results.

Enables MCP clients and OpenAI-compatible tools to generate images through a self-hosted browser-backed service protected by a single API key. Exposes image generation endpoints plus health and diagnostic status.

An open source biomedical research agent that provides LLMs with 28 tools for drug discovery, protein analysis, literature search, medical imaging, omics, and sandbox execution, all running locally via Ollama and MedGemma.

Enables agents to interact with Google NotebookLM — ask questions, manage notebooks and sources, generate audio overviews, and extract citations — via a stealth Chrome automation layer.