MCP

Habit Pocket is a habit tracker that logs numbers, times, and checkmarks to help users spot patterns in sleep, mood, energy, and daily routines. It also connects to AI assistants over MCP for chat-based logging and analysis.

Local-first change control for agent skills, with evidence-gated promotion, SkillOpt optimization, and MCP-based serving of skills.

Self-hosted registry and analytics platform for internal AI components like Skills, MCP servers, agents, hooks, and prompts. The page explains the problem it solves, supported harnesses, and the basic server/CLI setup flow.

Local codebase indexer and MCP server for Claude Code that watches project files, builds a private index on-device, and serves relevant snippets to Claude and other MCP clients.

Hearth is an open-source local AI agent that can control a Windows PC: it opens apps, reads and writes files, drives a browser, uses voice, and keeps memory across sessions.

Figmaboy is a local-first desktop design workspace with Codex CLI built into the canvas. It combines design, review, and command-line actions in one app, with offline saved designs and MCP-based context sharing.

Open standard, SDK, and live hub for personally-owned AI agents, with a protocol, reference hub, value routing, and live market mechanics.

Local-first task and context manager for humans and AI coding agents. It stores tasks, plans, docs, and memory in a shared SQLite database, with CLI commands, a web UI, and agent attribution built in.

A plugin and MCP server for Claude Code and Codex that gives AI agents access to FactIQ’s real-time finance and economics data, read-only SQL, market data, and shareable charts or reports.

Python toolkit for building LLM agents with MCP servers, skills folders, memory, streaming, and metrics support.

TypeScript SDK that adds an agent-facing visualize tool and embedded interactive charts to an MCP server. It supports SQL-backed chart rendering, text fallbacks for non-widget clients, and adapters for several warehouse systems.

FERNme is an open-source memory engine for AI agents that uses fuzzy graphs and Hebbian-style updates to store user preferences with near-zero LLM calls. The repository highlights editable user-owned memory, flat token usage, outcome-based reinforcement, and deployable plumbing via REST and MCP.

KINETK is an AI infrastructure product that turns social-web content into a real-time IP graph for creators, communities, and narratives. The site highlights an API and MCP for agents, multimodal embeddings, and a query layer for grounded retrieval.

A weekly security audit of Atlassian’s remote MCP server, focused on OAuth 2.1, RFC 9728 discovery, PKCE, DCR, and token handling. The page documents why the server’s discovery chain fails and includes HTTP evidence links.

Gread is a Skill and MCP server that gives coding agents access to the source code and docs of public GitHub repositories, with support for both skill-based and MCP client integrations.

Local-first long-term memory engine for AI agents with MCP, HTTP API, CLI, and Python usage. The page shows installation paths, IDE integrations, ingestion sources, and a live feature set focused on durable context, retrieval, and privacy.

A CLI tool that exposes a local MCP server through a public URL with one command. It supports anonymous ephemeral tunnels, OAuth 2.1 by default, and a self-hosted relay option.

Aidress is a coordination layer for autonomous AI agents with a live API, Python SDK, CLI, and MCP server for verifying, matching, registering, and reviewing agents.

A GitHub repo section documenting a benchmark for Vestige, a local-first Rust MCP memory layer for multi-agent coding fleets. The page explains the benchmark setup, what is being measured, how to reproduce the main claim, and where to find transcripts, evidence, and harness code.

A macOS Model Context Protocol server that gives AI agents local voice output and persona-based speaking styles.

Open-source CLI for spinning up disposable local or remote sandboxes for AI agents. It uses a manifest and Dockerfile to build fresh boxes, then exposes a single shell tool through MCP so an agent can work inside the sandbox without touching the host.

A Python MCP server that lets a parent LLM delegate work to named sub-agents defined in YAML, with per-agent prompts, model settings, and downstream MCP tool access.

Cast is an open-source, self-hosted harness for multi-user Claude agents. It focuses on routing, identity, and access control outside the prompt, with support for agent building, review flows, and extensions like email, calendar, web fetch, and WhatsApp.

A Claude Code plugin that adds persistent semantic memory via MCP, with support for Cursor and Claude Code setup, plus exposed write/search tools.