Obsidian

Files and knowledge

Obsidian for AI agents. Managed auth, ready-made tools.

Search, read and write the Markdown notes in a user's Obsidian vault on behalf of each of your users.

About Obsidian

With the Obsidian connector, your agent works with the notes in a user’s vault: it searches notes, reads them, writes new notes and adds to existing ones, all as plain Markdown. Each user connects the vault they choose, and your agent stays within it and the operations your project allows.

Obsidian is a note-taking app that keeps notes as Markdown files in a folder the user owns, called a vault.

Tools

What your agent can do in Obsidian.

Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Obsidian connection.

  • Search notes

    Read
    obsidian_search_notes

    Find notes by title or text.

  • List notes

    Read
    obsidian_list_notes

    List the notes and folders inside a folder of the vault.

  • Read a note

    Read
    obsidian_get_note

    Read a note's Markdown, including its properties.

  • Create a note

    Write
    obsidian_create_note

    Write a new Markdown note in a folder.

  • Append to a note

    Write
    obsidian_append_note

    Add text to the end of an existing note.

Control

Limits you can set.

You decide what your agent may do in Obsidian, and Agent200 runs every call within those limits.

  • Turn single tools on or off

    Keep obsidian_search_notes and reading on, and switch off obsidian_create_note and obsidian_append_note if your agent should only read.

  • Restrict what the agent reaches

    Choose the endpoints and scopes a project may use. A call outside them is refused.

Get started

Connect Obsidian
in three steps.

  1. 1

    Set up the SDK

    Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

    agent.js
    Conceptual example
    Set up the SDK with the Agent200 API key
    // One Agent200 API key covers every connector enabled for the project.
    const agent200 = new Agent200({
      apiKey: process.env.AGENT200_API_KEY,
    });
  2. 2

    Let your user connect Obsidian

    Each end user authorizes their own Obsidian account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

    connect.js
    Conceptual example
    Let an end user connect their account (managed OAuth)
    // Each end user authorizes their own Obsidian account, once.
    const connection = await agent200
      .user("user_123")
      .connect("obsidian");
    
    if (connection.authorizationUrl) {
      // Show this link to your user; Agent200 handles the rest.
      console.log(connection.authorizationUrl);
    }
  3. 3

    Run with the Obsidian tools

    Name the user, the model and the tools. The model decides which Obsidian tools to call, and Agent200 executes them with that user's connection.

    run.js
    Conceptual example
    Run a request with the connector's tools
    const result = await agent200
      .user("user_123")
      .run({
        model: "openai/gpt-5.6-sol",
        input: "What did I write about the pricing research last month",
        tools: ["obsidian"],
      });
    
    console.log(result.output);

Access

Sign-in and permissions.

  • Who connects

    Each of your users connects their own vault. Their other vaults stay out of reach.

  • What the agent sees

    The notes in that vault, as plain Markdown files with their properties.

For agents

Instructions for AI agents.

Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Obsidian connector and how to use it.

Agent brief
Connector: Obsidian, through Agent200. In code: "obsidian".
What it does: Search, read and write the Markdown notes in a user's Obsidian vault on behalf of each of your users.
Page: https://www.agent200.com/tools/obsidian/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Obsidian's own page, through the authorization link Agent200 returns. Never ask a user for a Obsidian password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: obsidian_search_notes, obsidian_list_notes, obsidian_get_note. Write tools: obsidian_create_note, obsidian_append_note. Name "obsidian" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/tools/obsidian/framework/claude/
   https://www.agent200.com/tools/obsidian/framework/chatgpt/
   https://www.agent200.com/tools/obsidian/framework/claude-code/
   https://www.agent200.com/tools/obsidian/framework/muse/
   https://www.agent200.com/tools/obsidian/framework/grok-bot/
   https://www.agent200.com/tools/obsidian/framework/openai-dots/
   https://www.agent200.com/tools/obsidian/framework/claude-duet/
   https://www.agent200.com/tools/obsidian/framework/hermes-agent/
   https://www.agent200.com/tools/obsidian/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

This page is also available as Markdown, for agents and LLMs: /tools/obsidian.md

Guides

Use Obsidian with the AI you build on.

Step-by-step setup for Obsidian with a specific model, assistant or agent framework.

FAQ

Obsidian and Agent200, answered.

Who handles the Obsidian OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Obsidian.

Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Obsidian connection, never another user's. It cannot reach anything the user or Obsidian has not authorized.

Can I limit what my agent can do in Obsidian?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

  • Google Drive

    Google Drive

    Find, read and organize the files in each user's Drive.

    Managed OAuth Files and knowledge
  • OneDrive

    OneDrive

    Search, read, upload and share OneDrive files, including Word, Excel and PowerPoint documents, on behalf of each of your users.

    Managed OAuth Files and knowledge
  • Dropbox

    Dropbox

    Search, read, upload and organize Dropbox files, and create shared links, on behalf of each of your users.

    Managed OAuth Files and knowledge
  • Notion

    Notion

    Search, read and write Notion pages and databases on behalf of each of your users.

    Managed OAuth Files and knowledge
200 OK

Start with Obsidian.
Your agent does the rest.

Your users connect their own Obsidian accounts. Agent200 handles the OAuth, the tokens and every tool call.

Book a demo.
See it in action.

Tell us who you are, then pick a time for a 1:1 session with an expert from our team.

We use your details only to email you about Agent200. See the Privacy Policy.

Pick a time. We'll take it from there.

A 1:1 session with an expert from our team, about what you are building.

Open in Calendly (opens in a new tab)