CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

nb-mcp-server

emcd/nb-mcp-server
STDIOregistry active
Summary

Wraps the nb CLI to give Claude proper note-taking capabilities without shell escaping headaches. Exposes operations for creating, editing, searching, and organizing Markdown notes, todos, and bookmarks through JSON parameters instead of raw shell commands. Handles notebook context explicitly so you can maintain separate note collections per project. Commands include nb.add for new notes with tags and folders, nb.search for full-text queries, nb.todo for task management, and nb.move for reorganization. Automatically creates notebooks and manages Git commits in the background. Particularly helpful if you're coordinating multiple LLMs on the same codebase and need structured, searchable notes that survive backticks and code blocks. Requires nb installed locally and supports configuration via environment variables or CLI flags.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

nb-mcp

MCP server wrapping the nb CLI for LLM-friendly note-taking.

Motivation

Using nb directly via shell has two problems for LLM assistants:

  1. Backtick escaping: Markdown content with backticks triggers shell command substitution, corrupting notes.

  2. Notebook context: nb assumes a default notebook, making per-project use awkward.

This MCP server solves both by:

  • Accepting content as JSON parameters (no shell escaping needed)
  • Qualifying all commands with an explicit notebook

Quick Start

Prerequisites

Install nb by following the official instructions: nb installation guide.

Installation

From crates.io:

cargo install nb-mcp-server

Or download a prebuilt binary from GitHub Releases.

Build from Source

cargo build --release

Run

With default notebook from environment:

NB_MCP_NOTEBOOK=myproject ./target/release/nb-mcp

Or via CLI argument (takes precedence):

./target/release/nb-mcp --notebook myproject

Disable commit and tag signing in the notebook repository:

./target/release/nb-mcp --notebook myproject --no-commit-signing

Allow new notes at the notebook root instead of requiring a folder:

./target/release/nb-mcp --notebook myproject --allow-top-level-notes

Print the installed version:

./target/release/nb-mcp --version

Show the resolved notebook path and state directory:

./target/release/nb-mcp --show-paths

MCP Configuration

Add to your MCP client configuration (e.g., .mcp.json):

{
  "mcpServers": {
    "nb": {
      "command": "/path/to/nb-mcp",
      "args": ["--notebook", "myproject"]
    }
  }
}

Commands

The canonical access path is the multiplexed nb tool with a command parameter, which reduces the token footprint of the MCP server. The args field must be a JSON object. Stringified JSON payloads are rejected. Unknown args fields are rejected instead of ignored; use the exact command schema fields or documented aliases. Returned identifiers such as coordination/mcp/1 or myproject:coordination/mcp/1 are nb selectors, not filesystem paths in the current repository. Notebook storage is managed by nb configuration. The notebook argument must be a bare notebook name. Use folder for folder paths and id / selector for note selectors. Existing-item commands accept copied selectors such as myproject:coordination/mcp/1, but reject conflicts with a separate notebook argument.

First-Class Tools

All commands are also available as direct first-class tools with typed schemas: add, show, edit, delete, move, list, search, todo, do, undo, tasks, bookmark, folders, mkdir, import, status, notebooks. These bypass the multiplexed command dispatch. The multiplexed nb tool remains as the compact/backcompat compatibility surface.

Notes

CommandDescriptionKey Arguments
nb.addCreate a notetitle, content, tags[], folder required by default
nb.showRead a noteid (alias: selector)
nb.editUpdate a noteid (alias: selector), content, mode (replace default, append, prepend)
nb.deleteDelete a noteid (alias: selector)
nb.moveMove or rename a noteid (alias: selector), destination
nb.listList notesfolder, tags[], limit ([ ] / [x] indicate todo status; leading glyphs are item markers)
nb.searchFull-text searchqueries[] (required), mode (any default, all), tags[]

Todos

CommandDescriptionKey Arguments
nb.todoCreate a todofolder required by default, title, optional description (alias: content), optional tasks[], tags[]
nb.doMark completeid (alias: selector), optional task_number
nb.undoReopenid (alias: selector), optional task_number
nb.tasksList todosoptional status (open or closed), optional recursive (true default)

Organization

CommandDescriptionKey Arguments
nb.bookmarkSave a URLurl, folder required by default, title, tags[], comment
nb.importImport file/URLsource, folder required by default, filename, convert
nb.foldersList foldersparent
nb.mkdirCreate folderpath
nb.notebooksList notebooks only(none)
nb.statusNotebook info(none)

Examples

Create a note with code:

{
  "command": "nb.add",
  "args": {
    "title": "API Design Notes",
    "content": "# API Design\n\nUse `GET /items` for listing.\n\n```python\nresponse = client.get('/items')\n```",
    "tags": ["design", "api"],
    "folder": "docs"
  }
}

Search for notes:

{
  "command": "nb.search",
  "args": {
    "queries": ["API", "design"],
    "mode": "any",
    "tags": ["design"]
  }
}

Tagging Suggestions

For multi-LLM projects, consider using consistent tag prefixes (optional). Example categories and prefixes:

CategoryPatternExamples
Collaboratorllm-<name>llm-claude, llm-gpt
Componentcomponent-<name>component-api, component-ui
Task typetask-<type>task-bug, task-feature
Statusstatus-<state>status-review, status-blocked

Configuration

Notebook Resolution

Priority order:

  1. Per-command notebook argument (highest)
  2. CLI --notebook flag
  3. NB_MCP_NOTEBOOK environment variable
  4. Git-derived default from the master worktree path

If no notebook can be resolved, commands fail with a configuration error. The server does not fall back to nb's default notebook.

If the resolved notebook does not exist, the server creates it automatically. Use --no-create-notebook to disable automatic creation.

Logging

Logs are written to ~/.local/state/nb-mcp/{project}--{worktree}.log (XDG-compliant).

For Git worktrees, logs are named after both the master project and the worktree basename to avoid collisions between multiple MCP server instances.

Use --show-paths to print the resolved notebook path and state directory.

Folder Requirement

By default, note-creating commands require a folder argument so agents do not accidentally litter project notebook roots. This applies to nb.add, nb.todo, nb.bookmark, and nb.import. Use nb.mkdir to create new folders and nb.folders to list existing folders.

Set NB_MCP_ALLOW_TOP_LEVEL_NOTES=true or pass --allow-top-level-notes to permit root-level note creation.

Notebook Overrides

Mutating commands warn after successful writes when the notebook argument targets a notebook other than the project default. Cross-notebook writes remain allowed for collaboration across teams, but the warning helps catch accidental notebook/folder confusion.

The notebook argument accepts only bare notebook names, not selector syntax. For example, use notebook: "other-team" with folder: "todos/mcp", not notebook: "other-team:todos/mcp".

Control log level with RUST_LOG:

RUST_LOG=debug nb-mcp --notebook myproject

Commit Signing

Use --no-commit-signing to disable commit and tag signing in the notebook repository. The server updates the notebook repository's local Git config so signing prompts do not block MCP tool calls.

Contributing

See the contribution guide and code of conduct:

  • Contribution guide
  • Code of conduct

License

Apache 2.0

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
AI & LLM ToolsDocuments & Knowledge
Registryactive
Packagehttps://github.com/emcd/nb-mcp-server/releases/download/v0.12.0/nb-mcp-server-0.12.0-aarch64-apple-darwin.mcpb
TransportSTDIO
UpdatedJun 2, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f