What models are supported with 📝 MCP Notes?
Any model that supports function calls and your client supports MCP. Tested models include Claude 3.5, Gemini 1.5/2.0, GPT‑4, Mistral Large, Grok‑2, and DeepSeek Chat.
@9Ninety
基本信息
A simple note-taking MCP server for recording and managing notes with AI models.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"MCPNotes": {
"command": "npx",
"args": [
"-p",
"mcp-notes",
"mcp-notes-web-server",
"--dynamodb",
"dynamodb://access_key:secret_key@region/table"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
📝 MCP Notes is a note-taking application built on the Model Context Protocol (MCP). It lets users record and view complex notes and tasks while interacting with AI models, without creating project files or making notes public. It requires an AWS DynamoDB database for storage.
Run directly via npx -p mcp-notes mcp-notes-server --dynamodb "<connection_string>" or bunx. Configure your MCP client (e.g., Claude Desktop, Cline) with the command and DynamoDB connection string. A separate web server is available at npx -p mcp-notes mcp-notes-web-server and accessible at http://localhost:3100.
Any model that supports function calls and your client supports MCP. Tested models include Claude 3.5, Gemini 1.5/2.0, GPT‑4, Mistral Large, Grok‑2, and DeepSeek Chat.
Yes, it requires an AWS account and DynamoDB for storing notes. AWS offers a generous free tier for DynamoDB.
Use a DynamoDB connection string: `dynamodb://<access_key>:<secret_key>@<region>/<table>`, or set environment variables `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` and supply the URI without credentials.
Cody (VS Code) currently does not support tool calls; you must use the web interface to manage notes and can only mention notes as resources. Claude Desktop and Cline have full tool-calling functionality. Resources are not working in Cline.
Four tools: `listNotes` (optional tag filter), `getNote` (by ID), `writeNote` (requires id, title, summary, tags, content), and `deleteNote` (by ID).
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.
评论