Skip to content
Conduit

mcp server

claude-plugins

Claude Code plugin marketplace for the n24q02m MCP servers -- install web search, memory, Notion, email, Telegram, Godot, code review, and image/video tools in one command.

n24q02m/claude-pluginscommunitylistedunreviewed

Set up

Runs on your computer. Pick your agent and operating system.

This project does not publish an install method we can turn into a config. Follow the README instead.

README

synced Oct 17, 2026

n24q02m Claude Plugins

ProjectTaglineTag
agent-chat-pluginPeer AI agents chat in a shared folder — no human relay, no orchestrator, wor...Tooling
better-code-review-graphKnowledge graph for token-efficient code reviews -- semantic search and call-...MCP
better-drive2-way Google Drive sync with .driveignore filter — rclone engine, Windows trayTooling
better-email-mcpIMAP/SMTP email for AI agents -- read, send, organize folders, and manage att...MCP
better-godot-mcpComposite MCP server for Godot Engine -- 17 composite tools for AI-assisted g...MCP
better-notion-mcpMarkdown-first Notion for AI agents -- pages, databases, blocks, and comments...MCP
better-semantic-releaseDrop-in python-semantic-release fork with built-in release-safety guards (orp...Tooling
better-telegram-mcpTelegram for AI agents -- messages, chats, media, and contacts across both bo...MCP
better-workspace-mcpGoogle Workspace MCP server (Docs/Drive/Calendar/Gmail/Sheets/Slides/Tasks/Ch...MCP
claude-pluginsClaude Code plugin marketplace for the n24q02m MCP servers -- install web sea...Marketplace
imagine-mcpImage and video understanding + generation for AI agents -- across Gemini, Op...MCP
jules-task-archiverChrome Extension for bulk operations on Jules tasks via batchexecute API -- a...Tooling
mcp-coreShared foundation for building MCP servers -- Streamable HTTP transport, OAut...MCP
mnemo-mcpPersistent AI memory with hybrid search and embedded sync. Open, free, unlimi...MCP
qwen3-embedLightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUFLibrary
skretSecrets without the server.CLI
tacetA self-distilling neuro-symbolic cascade that amortises LLM cost across knowl...Tooling
web-coreShared web infrastructure package for search, scraping, HTTP security, and st...Library
wet-mcpOpen-source MCP server for AI agents: web search, content extraction, and lib...MCP

Table of contents

9 MCP servers and a portable Agent Chat coordination plugin for AI coding agents.

Full documentation: mcp.n24q02m.com — setup and tool references for all 9 servers, Agent Chat coordination, the mcp-core foundation, and Fastretrieval. Libraries and coordination plugins do not gain an MCP transport by appearing in the same documentation site.

Install

/plugin marketplace add n24q02m/claude-plugins
/plugin install <plugin-name>@n24q02m-plugins

Or browse all plugins: run /plugin and go to the Discover tab.

Plugins

PluginCategoryDescriptionConfig (env / userConfig)
wet-mcpResearchWeb search, content extraction, library docs, media downloadAll optional: JINA_AI_API_KEY, GEMINI_API_KEY, GOOGLE_VERTEX_EXPRESS_API_KEY, OPENAI_API_KEY, COHERE_API_KEY, GITHUB_TOKEN
mnemo-mcpProductivityPersistent AI memory across sessionsAll optional: JINA_AI_API_KEY, GEMINI_API_KEY, GOOGLE_VERTEX_EXPRESS_API_KEY, OPENAI_API_KEY, COHERE_API_KEY
better-notion-mcpProductivityNotion API — 11 composite tools, ~95% coverageNOTION_TOKEN (required)
better-email-mcpCommunicationEmail IMAP/SMTP — multi-accountEMAIL_CREDENTIALS (required)
better-telegram-mcpCommunicationTelegram dual-mode (Bot API + MTProto) — messages, chats, mediaTELEGRAM_BOT_TOKEN (optional; required for bot mode)
better-godot-mcpDevelopmentGodot Engine — 17 composite tools for game devGODOT_PATH, GODOT_PROJECT_PATH (both optional)
better-code-review-graphDevelopmentKnowledge graph for token-efficient code reviewsAll optional: JINA_AI_API_KEY, GEMINI_API_KEY, GOOGLE_VERTEX_EXPRESS_API_KEY, OPENAI_API_KEY, COHERE_API_KEY
imagine-mcpMultimodalImage/video understanding + generation across Gemini, OpenAI, GrokAll optional: XAI_API_KEY (default provider), GEMINI_API_KEY, GOOGLE_VERTEX_EXPRESS_API_KEY, OPENAI_API_KEY
better-workspace-mcpProductivityGoogle Workspace — 10 domains plus local time helpers, config, help, and multi-account OAuthGOOGLE_OAUTH_CLIENT_ID, GOOGLE_OAUTH_CLIENT_SECRET (both required)
agent-chat-pluginDevelopmentPortable CLI/Skill peer coordination through Markdown/JSON messages, tasks, leases, and path locks; not an MCP serverShared folder and agent identity; no provider API keys

Fastretrieval is the retrieval library used by Wet, Mnemo, and CRG. Install it as a Python dependency, not as a marketplace plugin or MCP endpoint.

Configuration

When you run /plugin install, Claude Code prompts for that plugin's credentials (declared in each plugin's userConfig) and stores sensitive values in your system keychain. You can also set them via the env block in ~/.claude/settings.local.json, or export them in your shell profile.

better-notion-mcp, better-email-mcp, and better-workspace-mcp require credentials for their upstream APIs. better-telegram-mcp needs a bot token only for bot mode. Wet, Mnemo, and CRG preserve local Fastretrieval-based retrieval without provider API keys. Wet web search additionally needs a runnable backend: credential-free DuckDuckGo/Startpage, an external SearXNG endpoint, a configured cloud provider, or a local installation that can run SearXNG.

Cloud providers (wet-mcp, mnemo-mcp, better-code-review-graph)

Cloud model selection is separate from installing a plugin. Configure the model fields and matching provider keys in the server's environment for stdio or in the authenticated subject's relay form for multi-user HTTP. Do not infer a fallback chain just because several keys are present.

  • Wet and Mnemo use EMBEDDING_MODELS, RERANK_MODELS, and LLM_MODELS.
  • CRG uses EMBEDDING_MODELS and SUMMARY_MODELS; its optional query reranker is selected by LOCAL_RERANK_MODEL, not a cloud rerank chain.
  • Empty/local configuration and cloud behavior are server-specific; consult the setup references.

The managed Cloudflare route uses exactly openrouter/minimax/minimax-m3:free for completion and cohere/embed-v4.0 / cohere/rerank-v4.0-fast for supported embedding/rerank paths through Cloudflare AI Gateway. Cohere is paid and requires explicit spending authorization with a cap before calls. There is no Jina, GLM, or paid completion fallback in that route. CRG does not currently implement cloud reranking. This server-side policy does not change user-owned OMP model/profile settings or remove public local capabilities.

imagine-mcp

XAI_API_KEY=xai-...      # default provider
GEMINI_API_KEY=AIza...   # optional alternative
GOOGLE_VERTEX_EXPRESS_API_KEY=AQ...  # optional alternative
OPENAI_API_KEY=sk-...    # optional alternative

Telegram

TELEGRAM_BOT_TOKEN=123456:ABC-DEF...

Required for bot mode (from @BotFather); leave empty for user mode.

Email

EMAIL_CREDENTIALS=user@gmail.com:app-password

Multiple accounts: user1@gmail.com:pass1,user2@outlook.com:pass2

Notion

NOTION_TOKEN=ntn_xxx

Get your token from notion.so/my-integrations.

Godot

GODOT_PATH=/path/to/godot           # optional; auto-detects from PATH if empty
GODOT_PROJECT_PATH=/path/to/project # optional default project root

Google Workspace

GOOGLE_OAUTH_CLIENT_ID=<your-client-id>.apps.googleusercontent.com
GOOGLE_OAUTH_CLIENT_SECRET=<your-client-secret>

Create the OAuth client yourself at console.cloud.google.com/apis/credentials — type Desktop app for the default stdio mode, Web application for self-hosted HTTP. The first run opens Google's consent screen once, then reuses the stored refresh token.

Skills

Most plugins ship skills, invoked in Claude Code as <plugin>:<skill>:

PluginSkills
wet-mcpfact-check, compare, research-topic, lock-project-stack
mnemo-mcpsession-handoff, knowledge-audit, recall-context, memory-commit, passport-bootstrap
better-notion-mcporganize-database, bulk-update
better-email-mcpinbox-review, follow-up
better-telegram-mcpsetup-bot, channel-post
better-godot-mcpbuild-scene, debug-issue, add-mechanic
better-code-review-graphreview-pr, review-delta, refactor-check
imagine-mcpimage-describe

Other MCP Clients

Each plugin works with any MCP client. Run directly:

Python plugins (uvx / pipx / docker):

uvx --python 3.13 wet-mcp
uvx --python 3.13 mnemo-mcp
uvx --python 3.13 better-telegram-mcp
uvx --python 3.13 better-code-review-graph
uvx --python 3.13 imagine-mcp

TypeScript plugins (npx / bunx / docker):

npx -y @n24q02m/better-notion-mcp
npx -y @n24q02m/better-email-mcp
npx -y @n24q02m/better-godot-mcp

Add to any MCP client's settings.json:

{
  "mcpServers": {
    "wet": {
      "command": "uvx",
      "args": ["--python", "3.13", "wet-mcp"]
    }
  }
}

Deployment

The docs site (mcp.n24q02m.com) lives in this repo (docs/, Astro). Every push to main that changes docs/** or a plugin doc source (plugins/*/*.md, plugin manifests) triggers .github/workflows/deploy-docs.yml, which builds the site with Bun and deploys docs/dist to the Cloudflare Pages project mcp-n24q02m. Pages under docs/src/content/docs/servers/ are generated at build time by docs/scripts/sync-plugin-docs.mjs from the plugins/<name>/*.md sources — edit those source files, never the generated tree, and do not deploy the site manually with wrangler.

Plugin assets are synced separately: when a server repo cuts a release, cd.yml (plugin-sync) copies that release tag's plugin.json, skills, hooks, and commands into plugins/<name>/ on main, and the docs site redeploys if doc sources changed.

Contributing

See CONTRIBUTING.md.

License

Apache-2.0

↑↓ navigate openesc close