AI & Machine Learning MCP Servers

Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Codex and Claude Code Switch with custom configurations, MCP servers, plugins, and commands.

A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

Bridge server connecting Agent Communication Protocol (ACP) agents with Model Context Protocol (MCP) clients

Agentic AI Engineering is a production-grade engineering resource for building modern agentic AI systems with LangChain, LangGraph, RAG, MCP, local models, and deployable Python services.

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS

MCP server for domain management via Claude, Cursor, and any Model Context Protocol client. 108 Dynadot API actions across 10 generic tools: domain search, registration, renewal, DNS, WHOIS, nameservers, transfers, and aftermarket.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

A Model Context Protocol server to assist with development of customisations for the Pulse Platform

MCP server for running OpenAI Codex as a subagent with stall detection and auto-recovery

TypeScript client for total-agent-memory (server v8.0+) — local-first MCP memory layer for AI coding agents

Persistent memory organ for AI agents — vector store, strategies, cognitive state, knowledge manifests. Mockable defaults so it runs without SQLite, Ollama, or NextCloud.

```js import {mcp_ollama_tools, mcp_server, run_tools} from './mcp-cli/index.js' import ollama from "ollama";

Model Context Protocol server for local vector search

OpenAI Web Search MCP - Model Context Protocol for enhanced web search capabilities

An MCP server exposing GPT-5 inference with optional Web Search Preview.

DCP-AI bridge for the Model Context Protocol (MCP): signed receipts for tool calls, DCP tools and resources

Provider-agnostic MCP relay SDK — embed Chat Completions, Anthropic Messages, Google Gemini, and (future) unified-gateway tools in any MCP server.

Laila: An advanced, local-first AI developer assistant with MCP, Vision, and Multi-Agent Swarm capabilities.