Knowledge

io.github.seayniclabsPublished by GitHub account seayniclabsv0.2.1Updated Nov 3, 2026

Search, read and write your self-hosted Open Notebook knowledge base from an AI assistant.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Connects an AI assistant to your self-hosted Open Notebook knowledge base so it can list, search and read notebooks, notes and sources, and save new notes or…

What you can do
  • List notebooks and the notes inside them, paged and most recently updated first
  • Search sources and notes by keyword or by meaning, optionally limited to one notebook
  • Read a single note or source, including title, topics, extracted text and processing status
  • Create a note in a notebook, or add a web link or local file as a source, after a preview and your approval
  • Inspect which modules are enabled, which settings are missing and what each tool does
  • Use bundled skill prompts for getting started, source-backed research, weekly reviews, meeting notes, decision records and Markdown conventions
When to use it
Useful when your notes and research live in a self-hosted Open Notebook instance and you want an assistant to answer from them with citations, draft reviews or decision records, or file new notes and links back into the right notebook.
Requirements
Runs locally as a Python package (Python 3.11 or newer, via uvx or pip) over stdio, or optionally as a local HTTP transport. Needs the address of your Open Notebook server in KNOWLEDGE_OPEN_NOTEBOOK_URL, and KNOWLEDGE_OPEN_NOTEBOOK_PASSWORD only if that server has a password. Optional settings: KNOWLEDGE_OPEN_NOTEBOOK_REQUIRE_CONFIRM, KNOWLEDGE_OPEN_NOTEBOOK_ALLOWED_NOTEBOOKS, KNOWLEDGE_APPROVAL_LOG, module enable flags, and a config file. Vector search needs an embedding model on the server.
Before you install
Two tools write to your notebooks: note creation and adding sources. By default each write needs your approval through the MCP client; setting KNOWLEDGE_OPEN_NOTEBOOK_REQUIRE_CONFIRM to false or pre-approving notebooks in KNOWLEDGE_OPEN_NOTEBOOK_ALLOWED_NOTEBOOKS lets the assistant write without asking. Local files you name are uploaded to your Open Notebook server, and the server fetches any links you add. Text resembling credentials is refused, and approvals are logged locally. Use an https…

Installation

In SourceWeft

  1. Open Knowledge in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Knowledge

Made by Seaynic Labs. Need tools like this built around your own systems? We do that.

Knowledge lets an AI assistant search, read and write the notes in your self-hosted Open Notebook, and comes with skills that teach it to do that work well: meeting notes, decision records, weekly reviews and source-backed research.

It is a bundle: tools, skills and instructions in one install. The tools are one server made of modules. You switch on the modules you use. New modules arrive switched off, so an update never changes what your assistant can do until you choose to.

Security card
NetworkOnly the Open Notebook server you configure (KNOWLEDGE_OPEN_NOTEBOOK_URL). Open Notebook fetches the links you add, not Knowledge. Nothing else, no telemetry.
FilesReads its config file (/.config/knowledge/config.toml). Reads a local file only when you name it in open_notebook_add_source, and only after you approve it (the file goes to your Open Notebook server). Writes one local approval log (/.local/state/knowledge/approvals.jsonl).
SecretsAPI keys and passwords come from your environment or config file. They are never tool arguments and never returned to the model.
Read-only tools6: open_notebook_notebooks, open_notebook_search, open_notebook_notes, open_notebook_note_get, open_notebook_source_get, knowledge_modules
Needs your approvalopen_notebook_note_create, open_notebook_add_source: you approve each write in your app, or pre-approve notebooks in settings (not for local files). The AI cannot approve for you.
Startup costabout 4,600 tokens (8 tools, 7 skill prompts)
ChangesTool descriptions are locked by hash (tool-manifest.lock.json); CI fails if they change silently.

Skills

SkillWhat it doesSource
getting-startedChecks the settings, runs the first calls, explains approvals and errorsSeaynic Labs (MIT)
research-with-sourcesAnswers from your notebooks, cites each claim, flags sources that disagreeSeaynic Labs (MIT)
weekly-reviewDone, open and next-week items from the notes you changed this weekSeaynic Labs (MIT)
meeting-notesStructured meeting notes as a Markdown file, optionally saved to a notebookSeaynic Labs (MIT)
decision-recordA numbered Architecture Decision Record in a Decisions/ folderSeaynic Labs (MIT)
icm-architectOrganises a knowledge base as a folder structure that agents can walkJake Van Clief (MIT), credits
obsidian-markdownObsidian-flavoured Markdown: wikilinks, callouts, propertiesSteph Ango (MIT), credits

Skills reach every app. Claude Code and other skill-aware apps read the skills/ folder. Any MCP app gets the same text as prompts: getting-started, for example, is the prompt named getting-started. Third-party skills keep their own license files. See CREDITS.md.

Install

Knowledge needs Python 3.11 or newer. With uv you don't install anything ahead of time:

bash
uvx knowledge-bundle-mcp --version

Or with pip:

bash
pip install knowledge-bundle-mcp

Pinned install. For a fixed setup, pin the exact version. The plugin manifest pins it the same way:

bash
uvx knowledge-bundle-mcp==0.2.1 --version

As a Claude Code plugin. One install gives you the MCP server and the skills. This needs the seayniclabs/plugins marketplace, which is published with the release:

/plugin marketplace add seayniclabs/plugins/plugin install knowledge@seayniclabs

The plugin still needs your Open Notebook address in its settings. The plugin file is .claude-plugin/plugin.json.

First five minutes

  1. Set KNOWLEDGE_OPEN_NOTEBOOK_URL to your server's address (step 2 below shows where).

  2. Run the check. It prints ok or FIX for each item and exits 0 when everything is ready:

    bash
    knowledge-bundle-mcp --doctor
  3. Start your assistant and ask it to list your notebooks. It calls open_notebook_notebooks and shows you the names.

  4. Ask it to search a word you know is in one of your notes. It calls open_notebook_search.

  5. Ask it to save a note. It shows a preview first, then asks you to approve the save in your app.

Settings

Set these as environment variables in your MCP client's config, or put them in a config file (see below). Knowledge starts without any of them and tells you what's missing when you call a tool.

VariableModuleWhat it is
KNOWLEDGE_OPEN_NOTEBOOK_URLopen_notebookAddress of your Open Notebook server, e.g. https://notebook.example.com. No path.
KNOWLEDGE_OPEN_NOTEBOOK_PASSWORDopen_notebookOnly if your server has a password (OPEN_NOTEBOOK_PASSWORD on the server). Leave it unset otherwise.
KNOWLEDGE_OPEN_NOTEBOOK_REQUIRE_CONFIRMopen_notebooktrue by default: you approve each new note and link. false lets the assistant save them on its own. Local files always need your approval.
KNOWLEDGE_OPEN_NOTEBOOK_ALLOWED_NOTEBOOKSopen_notebookOptional. Comma-separated notebook names the assistant may save links and notes to without asking, e.g. Research,Inbox
KNOWLEDGE_APPROVAL_LOGanyOptional. Where the approval log is written. Default: ~/.local/state/knowledge/approvals.jsonl
KNOWLEDGE_<MODULE>_ENABLEDanyfalse turns a module off, e.g. KNOWLEDGE_OPEN_NOTEBOOK_ENABLED=false

Config file (optional). Knowledge also reads ~/.config/knowledge/config.toml, or the file named by KNOWLEDGE_CONFIG. Environment variables win over the file.

toml
[open_notebook]url = "https://notebook.example.com"password = "change-me"require_confirm = true

Add it to your MCP client

Most clients use the same JSON shape. Put it where your client keeps MCP servers:

json
{  "mcpServers": {    "knowledge": {      "command": "uvx",      "args": ["knowledge-bundle-mcp"],      "env": {        "KNOWLEDGE_OPEN_NOTEBOOK_URL": "https://notebook.example.com"      }    }  }}
ClientWhere the config goes
Claude Desktopclaude_desktop_config.json (Settings → Developer → Edit Config)
Claude Codeclaude mcp add knowledge -- uvx knowledge-bundle-mcp, then add the env values, or a project .mcp.json
Cursor~/.cursor/mcp.json, or .cursor/mcp.json in a project
VS Code.vscode/mcp.json, using "servers" instead of "mcpServers"
Sonique, Hermes, OpenClaw, othersAny client that launches a stdio MCP server: command uvx, args ["knowledge-bundle-mcp"], plus the env values

Over HTTP. For clients that connect to a URL instead of launching a process:

bash
knowledge-bundle-mcp --transport http --port 8765

It serves streamable HTTP at http://127.0.0.1:8765/mcp. It listens only on your own machine by default. Put authentication in front of it before exposing it anywhere else.

Try these

Paste any of these into your assistant once Knowledge passes --doctor:

  1. "List my notebooks and tell me which one changed most recently."
  2. "Search my notebooks for what I wrote about the Q3 budget, and cite each note."
  3. "Write a weekly review of the notes I changed this week, using the weekly-review skill."
  4. "Make an ADR for choosing SQLite over Postgres for the prototype, with the alternatives table filled in."
  5. "Save this link to my Research notebook: https://example.com/article. Show me the preview first."

Tools

ToolWhat it returns
knowledge_modulesWhich modules are on, which settings are missing, the skills, and the publisher. Call this first.
open_notebook_notebooksYour notebooks, most recently updated first, paged
open_notebook_searchMatching sources and notes. mode is text (keywords) or vector (meaning; needs an embedding model on the server). Optional notebook_id. Paged.
open_notebook_notesThe notes in one notebook, titles only, paged
open_notebook_note_getOne note's content, cut at max_chars
open_notebook_source_getOne source: title, topics, extracted text, notebooks, processing status
open_notebook_note_createSaves a note after you approve it. Without confirm=true it only returns a preview.
open_notebook_add_sourceAdds a web link, or a local file you name, as a source. Preview first; you approve it. Processed in the background.

Every tool returns structured data with a published schema, so an assistant can work with the results instead of parsing text. Errors always look like knowledge.<module>.<code>: <message> Fix: <hint>.

Safety

  • Knowledge only calls the Open Notebook server you configure. It sends nothing anywhere else and keeps no data of its own.
  • open_notebook_note_create and open_notebook_add_source change your notebooks, so you approve each one. When the assistant asks to save, Knowledge asks you directly through your MCP client (MCP elicitation) and shows the notebook, the title and the full text or link. The assistant can't answer that question for you.
  • A local file is read only after you name it, and it is uploaded only after you approve its full path and size. Files named like credential stores (.env, .netrc, private keys, *.pem, *.key) and files in ~/.ssh, ~/.aws or ~/.gnupg are refused.
  • Some MCP clients can't ask you questions yet. In those, Knowledge refuses to write unless you've pre-approved the notebook with KNOWLEDGE_OPEN_NOTEBOOK_ALLOWED_NOTEBOOKS, or turned approval off with KNOWLEDGE_OPEN_NOTEBOOK_REQUIRE_CONFIRM=false. Local files are never pre-approved.
  • Before anything is written or sent, text that looks like a credential (API keys, tokens, private keys, passwords in URLs) is refused. The error names the kind of credential found, never the value.
  • Use an https:// address for your server, and give the password only to Knowledge, not to other tools.

Develop

bash
uv venv && uv pip install -e '.[dev]'.venv/bin/pytestpython3 scripts/check_skills.py.venv/bin/python scripts/tool_lock.py --check.venv/bin/python scripts/security_card.py --check

scripts/tool_lock.py (without --check) rewrites tool-manifest.lock.json after a deliberate change to a tool, prompt or instruction. Add a changelog line in the same commit.

Security

Report a vulnerability privately through GitHub (Security tab, "Report a vulnerability"). See SECURITY.md. Every approval, decline and refusal is logged locally in ~/.local/state/knowledge/approvals.jsonl: titles, notebook names and sizes, never the text. Set KNOWLEDGE_APPROVAL_LOG to move it.

License

MIT. Published by Seaynic Labs. Third-party skills are credited in CREDITS.md and keep their own licenses.


Built by Seaynic Labs. We build tools like this around a business's own systems: local-first, with a person approving every change. See custom integrations.

Source: README.md at commit 604dc67

Tools

8

open_notebook_notebooks

List your notebooks, most recently updated first. Page with offset=<next_offset>.

Parameterslimitoffsetinclude_archived

open_notebook_notes

List the notes in one notebook, titles only. Read a note with open_notebook_note_get. Page with offset=<next_offset>.

Parameterslimitoffsetnotebook_idrequired

open_notebook_note_get

Read one note. Long content is cut at max_chars (up to 50000) and marked truncated.

Parametersnote_idrequiredmax_chars

open_notebook_source_get

Read one source: its title, topics, extracted text (cut at max_chars, up to 50000) and the notebooks it belongs to.

Parametersmax_charssource_idrequired

open_notebook_note_create

Create a note in a notebook. Without confirm=true it only returns a preview. With confirm=true you are asked to approve it (unless the notebook is pre-approved in settings); the assistant cannot approve on your behalf. Text that looks like a credential is refused.

Parameterstitlerequiredconfirmcontentrequirednotebook_idrequired

open_notebook_add_source

Add a web link or a local file as a source in one notebook. Give exactly one of url or file_path. Without confirm=true it only returns a preview. With confirm=true you are asked to approve it; the assistant cannot approve for you. A local file is always approved by you, with its full path and size shown, and is never pre-approved in settings. Open Notebook processes the source in the background: check progress with open_notebook_source_get.

Parametersurltitleconfirmfile_pathnotebook_idrequired

knowledge_modules

Which modules are on, what settings are missing, and what each tool does. Pass a module name for its full settings list.

Parametersmodule

Version history

1
  1. v0.2.1LatestOct 29, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts