How to integrate Outline MCP with LlamaIndex

Connect LlamaIndex to Outline MCP. Summarize latest engineering design documents, create onboarding page for new hires, and more using natural language, with authentication handled for you.

Get started for free Get a demo

Outline

Api Key

Outline is a team knowledge base and wiki for creating, organizing, and sharing documentation. It helps teams keep decisions, guides, and project knowledge easy to find.

101 Tools

Managed auth

Connect Outline without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

This guide walks you through connecting Outline to LlamaIndex using the Composio tool router. By the end, you'll have a working Outline agent that can summarize latest engineering design documents, create onboarding page for new hires, find outdated api documentation pages through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Outline account through Composio's Outline MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Outline with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Vercel AI SDK Mastra AI CrewAI

TL;DR

Here's what you'll learn:

Set your OpenAI and Composio API keys
Install LlamaIndex and Composio packages
Create a Composio Tool Router session for Outline
Connect LlamaIndex to the Outline MCP server
Build a Outline-powered agent using LlamaIndex
Interact with Outline through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

ReAct Agent: Reasoning and acting pattern for tool-using agents
MCP Tools: Native support for Model Context Protocol
Context Management: Maintain conversation context across interactions
Async Support: Built for async/await patterns

What is the Outline MCP server, and what's possible with it?

The Outline MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Outline account. It provides structured and secure access so your agent can perform Outline operations on your behalf.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step10 STEPS

Prerequisites

Before you begin, make sure you have:

Python 3.8/Node 16 or higher installed
A Composio account with the API key
An OpenAI API key
A Outline account and project
Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Outline

OpenAI API key (OPENAI_API_KEY)

Go to the OpenAI dashboard
Create an API key if you don't have one
Assign it to OPENAI_API_KEY in .env

Composio API key and user ID

Log into the Composio dashboard
Copy your API key from Settings
- Use this as COMPOSIO_API_KEY
Pick a stable user identifier (email or ID)
- Use this as COMPOSIO_USER_ID

Installing dependencies

npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv

Create a new Typescript project and install the necessary dependencies:

@composio/llamaindex: Composio's LlamaIndex integration
@llamaindex/openai: OpenAI LLM integration
@llamaindex/tools: MCP client for LlamaIndex
@llamaindex/workflow: Workflow framework for LlamaIndex
dotenv: Environment variable management

Set environment variables

bash

OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

Authenticate with OpenAI's GPT-5 model
Connect to Composio's Tool Router
Identify your Composio user session for Outline access

Import modules

import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

Create a new file called outline_llamaindex_agent.ts and import the required modules:

Key imports:

dotenv.config loads .env at runtime
readline gives us a simple CLI chat loop
Composio is the main Composio SDK client
mcp connects to an MCP endpoint
createAgent builds a LlamaIndex agent
openai configures the LLM backend

Load environment variables and initialize Composio

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["outline"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Outline actions." ,
    llm,
    tools,
  });

  return agent;
}

What's happening here:

We create a Composio client using your API key and configure it with the LlamaIndex provider
We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, outline)
The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
LlamaIndex will connect to this endpoint to dynamically discover and use the available Outline tools.
The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

What's happening:

We're creating a direct terminal interface to chat with Outline
The LLM's responses are streamed to the CLI for faster interaction.
The agent uses context to maintain conversation history
The agent processes the request, selects appropriate Outline tools, and returns a result
We extract the answer from the result data structure and display it to the user
You can type 'quit' or 'exit' to stop the chat loop gracefully
Agent responses and any errors are streamed in a clear, readable format

Define the main entry point

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();

What's happening here:

We're orchestrating the entire application flow
The agent gets built with proper error handling
Then we kick off the interactive chat loop so you can start talking to Outline

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Outline, then start asking questions.

Complete Code

Here's the complete code to get you started with Outline and LlamaIndex:

import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["outline"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Outline actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();

Conclusion

You've successfully connected Outline to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:

Tool Router dynamically exposes Outline tools through an MCP endpoint
LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
The agent becomes more capable without increasing prompt size
Async Python provides clean, efficient execution of agent workflows

You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

TOOLS

Supported Tools

Every Outline action and event your agent gets out of the box.

Activate User

Tool to activate a previously suspended user in Outline.

Add Group to Collection

Tool to add a group to a collection in Outline.

Add Document User

Tool to add a user membership to a document.

Add Group to Document

Tool to give all members in a group access to a document.

Add User to Group

Tool to add a user to a group.

Add User to Collection

Tool to add a user to a collection with specified permissions.

Archive Document

Tool to archive a document in Outline.

Create Attachment

Tool to create an attachment in Outline.

Create Collection

Tool to create a new collection in Outline.

Create Comment

Tool to create a comment on an Outline document.

Create Document

Tool to create a new document in Outline.

Create Group

Tool to create a new group in Outline.

Create OAuth Client

Tool to create a new OAuth client in Outline.

Create Share

Tool to create a public share link for an Outline document.

Create Star

Tool to create a star for a document or collection in Outline.

Create Template

Tool to create a new template in Outline.

Create View

Tool to create a view for a document.

Delete Attachment

Tool to delete an attachment from Outline.

Delete Collection

Tool to delete a collection and all of its documents from Outline.

Delete Comment

Tool to delete a comment in Outline.

Delete Document

Tool to delete a document in Outline.

Delete File Operation

Tool to delete a file operation and its associated files from Outline.

Delete Group

Tool to delete a group from Outline.

Delete OAuth Authentication

Tool to delete an OAuth authentication in Outline.

Delete OAuth Client

Tool to delete an OAuth client from Outline.

Delete Star

Tool to delete a star from a document in Outline.

Delete Template

Tool to delete a template in Outline.

Delete User

Tool to delete a user in Outline.

Duplicate Document

Tool to duplicate an Outline document.

Duplicate Template

Tool to duplicate an Outline template.

Empty Documents Trash

Tool to permanently delete all documents in the trash.

Export All Collections

Tool to export all collections and their documents in bulk.

Export Collection

Tool to export a collection in markdown, JSON, or HTML format.

Export Document

Tool to export a document from Outline in Markdown, HTML, or PDF format.

Get Attachment Redirect URL

Tool to retrieve an attachment redirect URL from Outline.

Get authentication config

Tool to retrieve authentication configuration options for an Outline workspace.

Get Collection Info

Tool to retrieve a collection by its unique identifier.

Get Collection Documents

Tool to retrieve a collection's document structure as a tree of navigation nodes.

Get Comment

Tool to retrieve a comment by its ID from Outline.

Get Document Info

Tool to retrieve a document from Outline by its UUID, urlId, or shareId.

Get Document Children Structure

Tool to retrieve a document's child structure.

Get File Operation Info

Tool to retrieve the details and current status of a file operation by its unique identifier.

Get Group Info

Tool to retrieve a group by its unique identifier.

Get OAuth Client Info

Tool to retrieve an OAuth client from Outline by its id or clientId.

Get Revision Info

Tool to retrieve a revision by its ID from Outline.

Get Share Info

Tool to retrieve a share object by its unique identifier or by the associated document ID.

Get Template Info

Tool to retrieve a template by its unique identifier.

Get User Info

Tool to retrieve a user by their unique identifier.

Invite Users

Tool to invite users to the Outline workspace.

List Archived Documents

List all archived documents in the Outline workspace.

List Collection Group Memberships

Tool to list all group memberships for a specific collection in Outline.

List collection memberships

Tool to list all individual user memberships for a collection.

List Collections

Tool to list all collections that the authenticated user has access to.

List Comments

Tool to retrieve all comments with optional filtering by document or collection.

List Data Attributes

Tool to list all data attributes in Outline.

List Deleted Documents

Tool to list all deleted documents in the workspace that the current user has access to.

List Document Group Memberships

Tool to list a document's group memberships.

List document memberships

Tool to list users with direct membership to a document.

List Documents

Tool to list all documents in your Outline workspace.

List Document Users

Tool to list all users with access to a document.

List Draft Documents

Tool to list all draft documents belonging to the current user.

List Events

Tool to list all events from the audit trail.

List File Operations

Tool to list all file operations for the workspace.

List Group Memberships

Tool to list all members of a specific group in Outline.

List Groups

Tool to list all groups in the workspace.

List OAuth Authentications

Tool to list all OAuth authentications for the current user.

List OAuth Clients

Tool to list all OAuth clients accessible to the authenticated user.

List Recently Viewed Documents

Tool to list all recently viewed documents by the current user.

List Revisions

Tool to list all revisions for a specific document.

List Shares

Tool to list all share links in the workspace.

List Stars

Tool to list all starred documents and collections for the authenticated user.

List Templates

Tool to list all templates available to the current user.

List Users

Tool to list all users in the workspace.

List Views

Tool to list all users that have viewed a specific document and the overall view count.

Move Document

Tool to move a document to a new location or collection in Outline.

Redirect File Operation

Tool to retrieve a file from Outline by file operation ID.

Remove Collection Group

Tool to remove a group from a collection, revoking access for all group members.

Remove Collection User

Tool to remove a user from a collection.

Remove Document User

Tool to remove a user membership from a document.

Remove Group from Document

Tool to remove a group from a document, revoking access for all group members.

Remove Group User

Tool to remove a user from a group.

Restore Document

Tool to restore a document in Outline.

Restore Template

Tool to restore a previously deleted template in Outline.

Retrieve Auth Info

Tool to retrieve authentication details for the current API key.

Revoke Share

Tool to revoke a share in Outline, making the share link inactive so it can no longer be used to access the document.

Rotate OAuth Client Secret

Tool to rotate the secret for an OAuth client in Outline.

Search Documents

Tool to search all documents in your Outline workspace using keywords.

Search Document Titles

Tool to search document titles in Outline workspace using keywords.

Suspend User

Tool to suspend a user in Outline.

Create Template from Document

Tool to create a template from an existing Outline document.

Unpublish Document

Tool to unpublish a document in Outline.

Update Collection

Tool to update an existing collection's properties in Outline.

Update Comment

Tool to update a comment in Outline.

Update Document

Tool to update a document in Outline.

Update Group

Tool to update an existing group's name in Outline.

Update OAuth Client

Tool to update an existing OAuth client in Outline.

Update Share

Tool to update a share in Outline.

Update Star

Tool to update a star's position in the Outline sidebar.

Update Template

Tool to update an existing template in Outline.

Update User

Tool to update a user's name, avatar, or language preference in Outline.

Update User Role

Tool to change a user's role in Outline workspace.

FRAMEWORKS

How to build Outline MCP Agent with another framework

OpenAI Agents SDK

Use Outline MCP with OpenAI Agents SDK

Claude Agent SDK

Use Outline MCP with Claude Agent SDK

Claude Code

Use Outline MCP with Claude Code

Claude Cowork

Use Outline MCP with Claude Cowork

Codex

Use Outline MCP with Codex

OpenClaw

Use Outline MCP with OpenClaw

Hermes

Use Outline MCP with Hermes

CLI

Use Outline MCP with CLI

Google ADK

Use Outline MCP with Google ADK

LangChain

Use Outline MCP with LangChain

Vercel AI SDK

Use Outline MCP with Vercel AI SDK

Mastra AI

Use Outline MCP with Mastra AI

CrewAI

Use Outline MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Google Drive

Oauth2

Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices.

Google Docs

Oauth2

Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze.

Google Super

Oauth2Api Key

Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization.

Affinda

Api Key

Affinda is an AI-powered document processing platform that automates data extraction from resumes, invoices, and more. It streamlines document-heavy workflows by turning files into structured, actionable data.

FAQ

Frequently asked questions

With a standalone Outline MCP server, the agents and LLMs can only access a fixed set of Outline tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Outline and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Outline tools.

Yes, absolutely. You can configure which Outline scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Outline data and credentials are handled as safely as possible.

Start with Outline.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Outline tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies