Origine Paris

Myco Brain is a self-hosted, open-source (Apache-2.0) memory layer and MCP server for AI agents. Cross-session recall with a deterministic write path and source-backed answers (brain_why), on your own Postgres, no API keys to start. 11 brain_* tools; keyless semantic search via local Ollama.

Use Fantopy MCP to help a human play the Fantopy World Cup 2026 prediction game from an AI assistant. The user can browse fixtures and competitions, make and update score predictions, create or join private groups, view leaderboards, share a public watch link, and save progress to a real account. The AI is a companion for a human player, not a competitor. Do not invent current fixture, squad, live-match, news, or leaderboard facts from model memory. Use the Fantopy MCP tools.

Free AI research/OCR + agent-economy discovery tools (120+ tools, no-auth), includes engage_sasame to commission SaSame to build MCP/Claude/RAG/agents, full deliverables pay-per-call via x402

Playwright MCP server

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

Persistent memory API for AI agents. Store, semantically retrieve, and forget memories across sessions. Agents self-register via POST /signup — no human needed. Supports MCP natively, auth.md discovery, semantic search with vector embeddings, TTL, namespaces, and batch operations. Free during beta. Built for the agentic web.

Memlane is a personal library for links and notes you save from the web. This connector lets agents search your library by meaning, read full saved articles, capture new URLs, create and edit notes, and organize items by project or topic. Sign in once with OAuth; your assistant only sees your account. Tools include semantic search, filtered browsing, URL capture with automatic summarization, note creation, and topic tagging.

summarize chat message

Shinobi gives every AI coding agent on your machine — and every cloud Claude session — one shared task spine, decision log, and searched dead-ends ledger. Every failed approach is logged and semantically checked before an agent proposes a similar one, so agents stop repeating mistakes across sessions. Adds mobile approvals (request_approval pushes to your phone) and an autonomous dispatch/swarm that drains the backlog with N parallel agents in isolated git worktrees, all sharing one brain. Local-first SQLite over stdio, or remote streamable-HTTP MCP you can self-host for $0/mo. 39 tools, plugin system, MIT. Works with Claude Code, Claude Desktop, Cursor, Cline, Continue.dev, Zed.

Spimov MCP — AI video dubbing, inside your chat Spimov MCP connects the Spimov (https://spimov.com) dubbing engine to Claude and any Model Context Protocol client. Ask in plain language — "dub this YouTube short into German and upload it unlisted to my channel" — and the whole pipeline runs server-side: transcription, translation, voice synthesis, lip-sync, and publishing. What you can do - 🎬 Dub from a YouTube link or a local file — regular videos, Shorts, and YouTube Music all supported. - 🌍 17 target languages, with auto source-language detection. - 🗣️ Choose your voice engine — xtts (high-quality, default), chatterbox (emotion-aware), or elevenlabs. - ✍️ Edit before you publish — list transcript segments and fix any line's text, emotion, or speaker; only that segment is re-synthesized. - 💬 Subtitles your way — fetch SRT/VTT, burn them in, or embed soft tracks in extra languages. - 🎚️ Remix without re-dubbing — adjust the audio mix, subtitle styling, or lip-sync on a finished job. - 📺 Publish to YouTube automatically when the dub finishes. - 🔗 Get a shareable download link for the finished MP4 — works in the browser, no API key needed. Works everywhere MCP does - Claude Desktop / Claude Code (stdio) — supports local file upload. - Claude web & hosted clients — connect to the hosted Streamable HTTP server, no install required. Setup in 2 minutes — grab an API key from spimov.com, drop it into your MCP config, and start dubbing. --- 4. Launch / duyuru postu (X / LinkedIn) ▎ We just shipped Spimov MCP 🎬 ▎ ▎ Dub any video into 17 languages without leaving your AI chat. Paste a YouTube link → Claude transcribes, translates, voices, and can publish it straight to YouTube. ▎ ▎ • Local file or YouTube URL ▎ • Edit any line, re-synth just that segment ▎ • SRT/VTT, burned-in or soft subtitles ▎ • Works in Claude Desktop, Claude Code & Claude web ▎ ▎ pip install spimov-mcp → spimov.com ▎ #MCP #Claude #AIdubbing --- 5. MCP marketplace metadata (alanlar) - Name: Spimov - Category: Media / Video - Description: Dub videos into 17 languages, edit translations, generate subtitles, and publish to YouTube — from any MCP client. - Auth: API key (spk_live_…) - Homepage: https://spimov.com - Install: pip install spimov-mcp (stdio) or connect https://mcp.spimov.com/mcp (HTTP)

An MCP server that provides a tool for sending transactional emails via Mailtrap

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

Headless, API-first accounting engine. Remote MCP server exposes 84 tools — accounts, transactions, invoices, bills, multi-entity consolidation, financial statements, multi-currency, reconciliations — over Streamable HTTP. Connect with one Bearer key; org scope derived automatically. REST + GraphQL too. 500 free credits on signup.

test

NeuroRank exposes its esports cognitive-combine data over MCP. One free tool returns aggregate cohort stats with no key; two paid tools (get_player_report, get_team_report) return per-player and team scouting reports, gated by an x-api-key tied to a scout or team subscription. Streamable HTTP, stateless. Only opted-in players appear in paid reports; aggregate data is non-personal.

Secure file operations with configurable access controls

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.

Persistent memory API for AI agents. Store, semantically retrieve, and forget memories across sessions. Agents self-register via POST /signup — no human needed. Supports MCP natively, auth.md discovery, semantic search with vector embeddings, TTL, namespaces, and batch operations. Free during beta. Built for the agentic web.

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Seekstone is a filesystem-direct Obsidian MCP server that gives Claude (and any MCP client) direct read/write access to your Obsidian vault — straight from the filesystem. No running Obsidian instance, no REST API plugin, no proxy. Most Obsidian MCP servers proxy through the Local REST API plugin, which returns full note content on every search hit — one query on a 2,000-note vault returned 1.75 MB (~450,000 tokens). Seekstone returns ranked ~200-char excerpts instead: 575× smaller payloads, far less context tax, and it works even when Obsidian is closed. 16 tools cover full-text search, scoped reads (by heading/block/line range), writes, link navigation (backlinks/outlinks), tags, and structural edits. Install: npx -y seekstone Open source (MIT) · https://seekstone.dev

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

Pay-per-call German/EU energy intelligence for AI agents: prices, carbon intensity, grid load, renewables, battery arbitrage, charging decisions. USDC on Base.

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.