Outline connector for AI agents

Tools your knowledge base agent reaches for on Outline, scoped per user.

CALL ANY TOOL

82 tools for your knowledge base in Outline: search, read, create, and update documents, organize collections, ask questions over your docs, and manage comments, shares, pins, and permissions.

outline_attachment_create_from_url

Attachment create from url

Store a file from a public URL as an Outline attachment. Outline downloads the file itself. Returns the attachment with its id, name, size and url, ready to use at once. Use outline_attachment_create_from_url to add an image or file to Outline; then reference its url in a document's Markdown with outline_document_update.

Parameters

Name

Type

Required

Description

url

string

Required

Public URL of the file to fetch. Example: https://example.com/diagram.png.

document_id

string

Optional

UUID of the document the attachment belongs to. Use the `id` field returned by outline_document_get or outline_documents_list (a UUID, not the short urlId).

outline_attachments_list

List attachments

outline_collection_archive

Archive collection

outline_collection_delete

Delete collection

outline_collection_duplicate

Duplicate collection

outline_collection_get

Get collection

outline_collection_group_add

Add collection group

outline_collection_group_remove

Remove collection group

outline_collection_memberships_list

List collection memberships

outline_collection_restore

Restore collection

outline_collection_update

Update collection

outline_comment_create

Create comment

outline_current_user_get

Get current user

outline_document_duplicate

Duplicate document

outline_document_group_memberships_list

List document group memberships

outline_document_move

Move document

outline_document_unpublish

Document unpublish

outline_document_update

Update document

outline_document_users_list

List document users

outline_documents_drafts_list

List documents drafts

outline_documents_search

Search documents

Search the content of documents the user can access, by keyword, optionally within one collection. Returns ranked results, each with a context snippet showing the match, a ranking score and the full document object, plus pagination. Use outline_documents_search to find documents by what they say. Use outline_documents_search_titles for a faster title-only match, or outline_documents_answer_question for an AI answer.

Parameters

Name

Type

Required

Description

query

string

Required

Keywords to search for in document titles and text. Supports quoted phrases. Example: hiring policy.

collection_id

string

Optional

UUID of a collection to search within. Get it from outline_collections_list.

direction

string

Optional

Sort order: ASC (oldest or A first) or DESC (newest or Z first). One of: `ASC`, `DESC`.

filters

array

Optional

Advanced structured filters, combined with AND. Each entry is a condition with a field, an operator and usually a value, or a group with an operator of AND or OR and its own list of filters. Supported fields: createdAt, updatedAt, publishedAt, archivedAt, title, templateId, collectionId, userId, documentId and parentDocumentId. Operators include eq, neq, lt, lte, gt, gte, contains, startsWith, endsWith, in, notIn, isNull and isNotNull. Date fields accept an ISO 8601 date or an ISO 8601 duration relative to now. Example: [{"field": "updatedAt", "operator": "gte", "value": "2026-01-01"}].

limit

integer

Optional

Maximum number of results to return in this page. Outline's default is 25; up to 100 per page. Example: 25.

offset

integer

Optional

Number of results to skip, for paging. Use the previous offset plus limit to get the next page. Example: 25.

snippet_max_words

integer

Optional

Maximum number of words in each result's context snippet. Outline's default is 30.

snippet_min_words

integer

Optional

Minimum number of words in each result's context snippet. Outline's default is 20.

sort

string

Optional

Field to sort results by: createdAt, updatedAt or title. Leave empty to sort by relevance (best match first). One of: `createdAt`, `updatedAt`, `title`.

outline_events_list

List events

outline_file_operation_get

Get file operation

outline_group_memberships_list

List group memberships

outline_pin_delete

Delete pin

outline_pins_list

List pins

outline_share_create

Create share

outline_share_get

Get share

outline_shares_list

List shares

outline_templates_list

List templates

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Outline tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["outline"], toolNames: [
    "outline_documents_search",
    "outline_document_get",
    "outline_document_update"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find the Engineering Weekly doc and append today's standup notes" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["outline"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find the Engineering Weekly doc and append today's standup notes" }],
  tools,
});

// Execute the tool call with the user's vaulted Outline OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["outline"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find the Engineering Weekly doc and append today's standup notes" }],
  tools,
});

// Tool call runs with the user's vaulted Outline OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["outline"] }, pageSize: 100,
});

const agent = new Agent({
  name: "knowledge_agent",
  model: "gemini-2.5-pro",
  instruction: "Outline tools scoped to this user",
  tools,
});

await agent.run("Find the Engineering Weekly doc and append today's standup notes");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Outline tool. Click to copy, paste into your agent, done.

Find

Copy the prompt

Copied

Search our Outline docs for the incident postmortem template.

Copy the prompt

Copied

What does our handbook say about expense approvals?

Copy the prompt

Copied

List documents I viewed recently.

Write

Copy the prompt

Copied

Create a draft called Q4 Launch Plan in the Marketing collection.

Copy the prompt

Copied

Append today's standup notes to the Engineering Weekly doc.

Copy the prompt

Copied

Move the API Guidelines doc under the Engineering Handbook.

Collaborate

Copy the prompt

Copied

List comments on the Pricing FAQ.

Copy the prompt

Copied

Give the Support group access to the Help Center collection.

Copy the prompt

Copied

Create a share link for the Onboarding Guide.

SEE HOW AUTH WORKS

Each user signs in to Outline once, and Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Outline

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Outline

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Outline

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Outline

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other docs and knowledge connectors.

Support and Ops Teams

Support triage agent

Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Outline token looks fine in a demo. In production every document edit looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Outline today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Outline as the user or through a shared service account?

As the user. Each user signs in to Outline once, and Scalekit stores and refreshes their tokens. Documents and comments the agent creates or edits are attributed to that user in your audit trail, not a shared service account.

Where is the Outline OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Outline?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the search and read tools without outline_collection_delete, which deletes a collection and every document in it and cannot be undone. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Outline access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent answer questions from Outline docs?

Yes, when AI answers are enabled for the Outline workspace. outline_documents_answer_question returns an AI-written answer drawn from the documents the user can access, and outline_documents_search returns the matching documents for a keyword search.