Browse the directory

Open-source, self-hostable AI engine that runs LLMs, vision, voice, image, and video models on your own hardware behind one API, with drop-in OpenAI, Anthropic, and ElevenLabs API compatibility, composable on-demand backends, and no GPU required.

Run the parts of your AI dev workflow that touch your code and data — tools, memory, and auxiliary models — on infrastructure you control, while still using Claude as the orchestrator. A practical architecture for a self-hosted, privacy-first developer stack.

Expert code-review capability pack for deterministic PR audits, risk-ranked findings, and low-noise fix planning without SaaS lock-in.

Ship smart contracts on Base with secure deployment, verification, environment management, and production-readiness checklists.

Configure MCP servers in the Claude Desktop app by editing claude_desktop_config.json. Grounded walkthrough covering config file locations, the mcpServers JSON structure, the filesystem server, and how to verify and troubleshoot the connection.

Open-source status companion for Claude Code and Codex with live local session state, your-turn alerts, usage views, and native macOS and Windows applications.

Local-first GoodMemory MCP server for giving Claude durable, scoped memory with SQLite storage, auditable recall, explicit deletion, and opt-in governed writes.

The official Codacy MCP server (@codacy/codacy-mcp) that gives AI assistants access to the Codacy API for code quality, security, and coverage — listing repository and pull-request issues, retrieving file coverage and duplication, searching security (SRM) findings, inspecting analysis tools and patterns, and running local analysis with the Codacy CLI.

Framework-agnostic agent memory lifecycle skill and Rust-native CLI for explicit recall, evidence-backed memory, forgetting, audit, consolidation, DOX/Revolve sync, and local SQLite/FTS storage.

Official AWS Labs fully-managed remote MCP server providing up-to-date AWS documentation, code samples, agent skills, API and CloudFormation regional availability, and CDK/Amplify/Strands guidance over a hosted HTTP endpoint.

Local-first AccInt MCP server that gives Claude a scored Work Model through `acc_retrieve` and `acc_act`, so agent work can compound from real outcomes while the `acc.db` substrate stays on the user's machine.

Local-first AI application for private chat, document RAG, workspace agents, MCP-compatible tools, model routing, memories, scheduled tasks, multimodal workflows, multi-user Docker deployments, and self-hosted agent automation.

Cross-platform AI desktop client with multiple LLM providers, local model support, 300+ assistants, document and image handling, WebDAV backup, MCP server support, mini programs, and enterprise deployment options.

Create, update, publish, and manage content in Contentful from Claude — entries, assets, content types, locales, spaces, environments, and AI actions — with the official Contentful Management API MCP server supporting semantic search and vector-based content discovery.

Index any documentation — websites, GitHub repos, npm/PyPI packages, local files — and give Claude always-current, version-specific answers with the open-source Grounded Docs MCP server. An offline-first alternative to Context7, Nia, and Ref.Tools.

Official Flutter team Agent Skills for AI coding agents building Flutter apps, fixing layout issues, adding widget and integration tests, creating widget previews, applying layered architecture, routing, localization, JSON serialization, and HTTP workflows.

Hugging Face Python agent library for CodeAgent and ToolCallingAgent workflows, where agents write Python actions, call tools, use MCP tool collections, connect to Hub tools and spaces, run with LiteLLM or local models, and use optional sandboxes.

Read and write any local SQLite database from Claude — get database info, list tables, inspect schemas, create/read/update/delete records, and run raw SQL queries — with the MCP SQLite server that connects to any `.db` file you specify.

Security scanner from Snyk for discovering local AI agent components, including MCP servers and Agent Skills, and checking them for prompt injection, tool poisoning, tool shadowing, toxic flows, malware payloads, credential handling, and hardcoded secrets.

Community slash command runbook for frontend visual QA using documented Claude Code Chrome integration workflows: enable /chrome, open a local page, read console messages, and follow the design verification checklist from the Chrome integration guide.

SpotDB local MCP server that exposes an ephemeral DuckDB sandbox for AI agents to upload CSV data, run guarded SQL queries, and explore datasets without touching production databases.

Expert Claude Code champion kit rollout capability pack for selecting advocates, localizing kit assets, running enablement sessions, and measuring adoption with source-backed rollout checklists aligned to official champion kit docs.

BoolsAI hosted MCP server with no authentication required for tech stack scanning via boolsai_scan and boolsai_scan_paths tools on boolsai.ai/mcp.

Connect Claude to BorealHost's MCP server for hosting and infrastructure management — 47 tools spanning servers, domains, DNS, SSL, and deployments. Add it remotely with claude mcp add --transport http, or run it locally over stdio via pip install borealhost-mcp with a BOREALHOST_API_KEY.

Local-first Basic Memory MCP server for giving Claude a persistent Markdown knowledge base with note editing, semantic search, recent activity, knowledge graph context, projects, schema tools, and optional cloud sync.

Browser-control MCP server and CLI that lets AI agents use a real Chrome session, including logged-in browser state, site adapters, DOM snapshots, authenticated fetches, network traces, screenshots, and page actions.

Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.

Local code indexing MCP server that lets AI assistants search repositories, build symbol indexes, inspect file summaries, monitor changes, and navigate multi-language codebases.

Code intelligence MCP server with a Zig core for local project indexing, structural outlines, symbol lookup, search, dependency graphs, snapshots, remote public-repo queries, and fallback edits.

Connect Claude to a Google Colab runtime. Colab MCP starts a local FastMCP server and websocket proxy, waits for an authorized Colab-origin browser connection, then exposes the session's notebook and runtime tools to your MCP client over stdio.