Local memory for agents: stores conversations and project files verbatim and retrieves them with semantic search over MCP
MCP servers
An MCP server connects an agent to external data and tools over a single protocol: files, databases, APIs and services. This section lists servers with their transport, auth method and environment variables, an install command and an honest read on the risks.
Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.
An MCP server and CLI from Sentry for building, running and testing Xcode iOS and macOS projects from an AI agent
The official draw.io MCP server: an agent builds diagrams from XML or Mermaid and opens them in the draw.io editor
The official MathWorks MCP server: the agent starts and quits MATLAB, writes and runs code, and checks it for errors and style
Official Cloudflare MCP server: the agent drives the whole Cloudflare API by searching the spec and running code
Connects an agent to a running Next.js 16+ dev server: errors, routes, logs and docs for your installed version
Yandex Wiki MCP server
MCP-сервер Яндекс Вики
Yandex Wiki official MCP: an agent searches and reads knowledge base pages, builds summaries and creates new pages on behalf of the employee
MCP tools and a CLI for a 3D building editor: the agent creates, inspects and edits architectural scenes
Local screen and audio recording with natural language search, feeding your activity history to an agent via MCP
A local codebase index with ten MCP tools: dependency graph, git history, code health and architectural decisions without re-grepping on every step
A self-hosted control plane for running several agents: task dispatch, run review, spend tracking, connected via MCP, CLI or REST
Fast semantic code search for agents: returns the exact snippets instead of reading whole files and spends far fewer tokens
A local-first workflow engine in a single binary with a built-in MCP server so an agent can inspect and run jobs
A local development environment with a built-in MCP server: the agent inspects services, sites, configs and logs and manages their lifecycle
An MCP server for the Godot engine: connects Claude Code, Claude Desktop and Codex to a live editor to build scenes, scripts and materials
Minutes
minutes
A local-first MCP server for meeting memory: on-device recording and transcription into Markdown, searchable from Claude Code, Codex, Cursor and any MCP client
A local browser automation platform: MCP server, CLI and skills so an agent can drive Chrome, fill forms and pull data from pages
An MCP server for voice conversations with Claude Code and other MCP agents: speech recognition and voice synthesis, local or cloud
A Game Boy emulator with a debugger and a built-in MCP server: the agent controls execution, reads memory and inspects hardware state
A self-hosted task manager for human and agent collaboration through MCP
A PDF-reading MCP server: structured text, tables, OCR, visual crops and page-level citations
An open macOS app for code context engineering: an MCP server and agent orchestrator that helps agents understand a project before editing
MCP server and skills for product analytics: user paths, funnels, segments and transition graphs over event logs
iai-memory
iai-memory (Personal Memory Engine)
A local long-term memory MCP server for agents: keeps conversations verbatim and returns the right context at the start of a session
Frequently asked questions
What is an MCP server?
An MCP server connects an agent to external data and tools over a single protocol: files, databases, APIs and services. The agent calls its tools while it works.
How do I connect an MCP server to an agent?
The entry lists how to run it (npx, uvx, docker or a remote URL) and the environment variables. A config snippet goes into the agent settings.
Do I need a key or a paid account?
It depends on the server. Each entry states the auth method and requirements, including paid accounts, in the limitations block.