Skip to main content
Glama

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

Network

Only the Open Notebook server you configure (KNOWLEDGE_OPEN_NOTEBOOK_URL). Open Notebook fetches the links you add, not Knowledge. Nothing else, no telemetry.

Files

Reads 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).

Secrets

API keys and passwords come from your environment or config file. They are never tool arguments and never returned to the model.

Read-only tools

6: open_notebook_notebooks, open_notebook_search, open_notebook_notes, open_notebook_note_get, open_notebook_source_get, knowledge_modules

Needs your approval

open_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 cost

about 4,600 tokens (8 tools, 7 skill prompts)

Changes

Tool descriptions are locked by hash (tool-manifest.lock.json); CI fails if they change silently.

Skills

Skill

What it does

Source

getting-started

Checks the settings, runs the first calls, explains approvals and errors

Seaynic Labs (MIT)

research-with-sources

Answers from your notebooks, cites each claim, flags sources that disagree

Seaynic Labs (MIT)

weekly-review

Done, open and next-week items from the notes you changed this week

Seaynic Labs (MIT)

meeting-notes

Structured meeting notes as a Markdown file, optionally saved to a notebook

Seaynic Labs (MIT)

decision-record

A numbered Architecture Decision Record in a Decisions/ folder

Seaynic Labs (MIT)

icm-architect

Organises a knowledge base as a folder structure that agents can walk

Jake Van Clief (MIT), credits

obsidian-markdown

Obsidian-flavoured Markdown: wikilinks, callouts, properties

Steph 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.

Related MCP server: Obsidian MCP Server

Install

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

uvx knowledge-bundle-mcp --version

Or with pip:

pip install knowledge-bundle-mcp

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

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:

    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.

Variable

Module

What it is

KNOWLEDGE_OPEN_NOTEBOOK_URL

open_notebook

Address of your Open Notebook server, e.g. https://notebook.example.com. No path.

KNOWLEDGE_OPEN_NOTEBOOK_PASSWORD

open_notebook

Only if your server has a password (OPEN_NOTEBOOK_PASSWORD on the server). Leave it unset otherwise.

KNOWLEDGE_OPEN_NOTEBOOK_REQUIRE_CONFIRM

open_notebook

true 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_NOTEBOOKS

open_notebook

Optional. Comma-separated notebook names the assistant may save links and notes to without asking, e.g. Research,Inbox

KNOWLEDGE_APPROVAL_LOG

any

Optional. Where the approval log is written. Default: ~/.local/state/knowledge/approvals.jsonl

KNOWLEDGE_<MODULE>_ENABLED

any

false 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.

[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:

{
  "mcpServers": {
    "knowledge": {
      "command": "uvx",
      "args": ["knowledge-bundle-mcp"],
      "env": {
        "KNOWLEDGE_OPEN_NOTEBOOK_URL": "https://notebook.example.com"
      }
    }
  }
}

Client

Where the config goes

Claude Desktop

claude_desktop_config.json (Settings → Developer → Edit Config)

Claude Code

claude 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, others

Any 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:

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

Tool

What it returns

knowledge_modules

Which modules are on, which settings are missing, the skills, and the publisher. Call this first.

open_notebook_notebooks

Your notebooks, most recently updated first, paged

open_notebook_search

Matching sources and notes. mode is text (keywords) or vector (meaning; needs an embedding model on the server). Optional notebook_id. Paged.

open_notebook_notes

The notes in one notebook, titles only, paged

open_notebook_note_get

One note's content, cut at max_chars

open_notebook_source_get

One source: title, topics, extracted text, notebooks, processing status

open_notebook_note_create

Saves a note after you approve it. Without confirm=true it only returns a preview.

open_notebook_add_source

Adds 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

uv venv && uv pip install -e '.[dev]'
.venv/bin/pytest
python3 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.

Available Tools

8 tools
knowledge_modulesA
Read-only

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

Inputs: module. Returns: skills, modules, version, homepage, +2 more

open_notebook_add_sourceA

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.

Inputs: notebook_id (required), url, title, confirm, +1 more. Returns: kind, note, path, status, +8 more

open_notebook_notebooksA
Read-only

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

Inputs: limit, offset, include_archived. Returns: limit, offset, has_more, notebooks, +1 more

open_notebook_note_createA

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.

Inputs: title (required), content (required), notebook_id (required), confirm. Returns: id, note, title, created, +6 more

open_notebook_note_getA
Read-only

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

Inputs: note_id (required), max_chars. Returns: id, title, content, created, +4 more

open_notebook_notesA
Read-only

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

Inputs: notebook_id (required), limit, offset. Returns: limit, notes, offset, has_more, +2 more

open_notebook_source_getA
Read-only

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

Inputs: source_id (required), max_chars. Returns: id, title, status, topics, +8 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 8 tools

    Disambiguation4/5

    Each tool maps to a distinct resource+action pair, and the suffix conventions (notes = list, note_get = read) plus explicit descriptions keep the list/read pairs separable. Minor overlap between open_notebook_search scoped to a notebook and open_notebook_notes listing within a notebook, but the descriptions clarify the boundary.

    Naming Consistency3/5

    Seven of eight tools share the open_notebook_ prefix and snake_case, which is good. However, verb placement is mixed: noun_verb (open_notebook_note_get, open_notebook_source_get), verb_noun (open_notebook_add_source), and bare nouns (open_notebook_notebooks, open_notebook_notes), and the final tool (knowledge_modules) breaks the prefix entirely.

    Tool Count5/5

    Eight tools is well within a comfortable range for a notebook/source/note management server. Each tool serves a distinct role: browsing, reading, searching, creating, and one meta/introspection tool.

    Completeness3/5

    Read paths and creation are covered (list notebooks, list/read notes, read sources, search, create note, add source), but there is no way to list sources belonging to a notebook and no update or delete operations for notes, sources, or notebooks. The surface supports ingestion and reading but leaves lifecycle management and source browsing as notable gaps.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to read and write to a personal knowledge vault of markdown notes, projects, and tasks, with tooling for search, capture, daily logs, and project management across different AI tools.
      23
      44 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to capture, search, update, and delete notes in a local Markdown vault with automatic categorization and tagging, making knowledge management seamless.
      6 npm
      1
      MIT