How to integrate Slackbot MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Slackbot logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Slackbot to LlamaIndex using the Composio tool router. By the end, you'll have a working Slackbot agent that can send daily standup reminder to #engineering, add a custom emoji for our new logo, archive the #old-projects channel this week through natural language commands.

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

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

Also integrate Slackbot with

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 Slackbot
  • Connect LlamaIndex to the Slackbot MCP server
  • Build a Slackbot-powered agent using LlamaIndex
  • Interact with Slackbot 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 Slackbot MCP server, and what's possible with it?

The Slackbot MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Slackbot account. It provides structured and secure access to your Slack workspace, so your agent can automate reminders, manage conversations, add emoji reactions, organize channels, and streamline team notifications on your behalf.

  • Automated reminders and notifications: Ask your agent to create timely Slack reminders for you or your team using natural language or custom schedules—never miss a deadline or meeting again.
  • Message reactions and engagement: Let your agent add emoji reactions to messages, star important items, or highlight key conversations to keep team morale up and draw attention where needed.
  • Channel and conversation management: Have your agent archive inactive channels, close direct messages, or organize your workspace by cleaning up conversations—all with just a simple command.
  • Custom emoji and file integration: Direct your agent to add new custom emoji, set emoji aliases, or reference external files (like Google Drive docs) for richer, more expressive communication.
  • Participant and workflow automation: Empower your agent to add call participants, automate onboarding flows, or handle repetitive Slack tasks to keep your team focused and productive.

Supported Tools & Triggers

Tools
Triggers
Add call participantsRegisters new participants added to a Slack call.
Add reaction to messageAdds a specified emoji reaction to an existing message in a Slack channel, identified by its timestamp; does not remove or retrieve reactions.
Add a remote fileAdds a reference to an external file (e.
Archive a Slack conversationArchives a Slack conversation by its ID, rendering it read-only and hidden while retaining history, ideal for cleaning up inactive channels; be aware that some channels (like #general or certain DMs) cannot be archived and this may impact connected integrations.
Close conversation channelCloses a Slack direct message (DM) or multi-person direct message (MPDM) channel, removing it from the user's sidebar without deleting history; this action affects only the calling user's view.
Create a reminderCreates a Slack reminder with specified text and time; time accepts Unix timestamps, seconds from now, or natural language (e.
Create Slack CanvasCreates a new Slack Canvas with the specified title and optional content.
Create channelInitiates a public or private channel-based conversation in a Slack workspace.
Create a Slack user groupCreates a new User Group (often referred to as a subteam) in a Slack workspace.
Customize URL unfurlCustomizes URL previews (unfurling) in a specific Slack message using a URL-encoded JSON in `unfurls` to define custom content or remove existing previews.
Delete Slack CanvasDeletes a Slack Canvas permanently and irreversibly.
Delete a file by IDPermanently deletes an existing file from a Slack workspace using its unique file ID; this action is irreversible and also removes any associated comments or shares.
Delete file commentDeletes a specific comment from a file in Slack; this action is irreversible.
Delete a Slack reminderDeletes an existing Slack reminder, typically when it is no longer relevant or a task is completed; this operation is irreversible.
Delete a message from a chatDeletes a message, identified by its channel ID and timestamp, from a Slack channel, private group, or direct message conversation; the authenticated user or bot must be the original poster.
Delete scheduled chat messageDeletes a pending, unsent scheduled message from the specified Slack channel, identified by its `scheduled_message_id`.
Disable a Slack user groupDisables a specified, currently enabled Slack User Group by its unique ID, effectively archiving it by setting its 'date_delete' timestamp; the group is not permanently deleted and can be re-enabled.
Download Slack fileTool to download Slack file content and convert it to a publicly accessible URL.
Edit Slack CanvasEdits a Slack Canvas with granular control over content placement.
Share file public urlEnables public sharing for an existing Slack file by generating a publicly accessible URL; this action does not create new files.
Enable a user groupEnables a disabled User Group in Slack using its ID, reactivating it for mentions and permissions; this action only changes the enabled status and cannot create new groups or modify other properties.
End a callEnds an ongoing Slack call, identified by its ID (obtained from `calls.
Fetch conversation historyFetches a chronological list of messages and events from a specified Slack conversation, accessible by the authenticated user/bot, with options for pagination and time range filtering.
Fetch item reactionsFetches reactions for a Slack message, file, or file comment.
Retrieve conversation repliesRetrieves replies to a specific parent message in a Slack conversation, using the channel ID and the parent message's timestamp (`ts`).
Fetch team infoFetches comprehensive metadata about the current Slack team, or a specified team if the provided ID is accessible.
Find channelsFind channels in a Slack workspace by any criteria - name, topic, purpose, or description.
Lookup users by emailRetrieves the Slack user object for an active user by their registered email address; requires the users:read.
Find usersFind users in a Slack workspace by any criteria - email, name, display name, or other text.
Fetch bot user informationFetches information for a specified, existing Slack bot user; will not work for regular user accounts or other integration types.
Retrieve call informationRetrieves a point-in-time snapshot of a specific Slack call's information.
Get reminder informationRetrieves detailed information for an existing Slack reminder specified by its ID; this is a read-only operation.
Get remote fileRetrieve information about a remote file added to Slack via the files.
Retrieve team profile detailsRetrieves all profile field definitions for a Slack team, optionally filtered by visibility, to understand the team's profile structure.
Get team DND statusRetrieves a user's current Do Not Disturb status.
Retrieve user presenceRetrieves a Slack user's current real-time presence (e.
Invite users to a Slack channelInvites users to an existing Slack channel using their valid Slack User IDs.
Join conversation by channel idJoins an existing Slack conversation (public channel, private channel, or multi-person direct message) by its ID, if the authenticated user has permission.
Leave conversation channelLeaves a Slack conversation given its channel ID; fails if leaving as the last member of a private channel or if used on a Slack Connect channel.
List all channelsLists conversations available to the user with various filters and search options.
List all usersRetrieves a paginated list of all users with profile details, status, and team memberships in a Slack workspace; data may not be real-time.
List conversationsList conversations (channels/DMs) accessible to a specified user (or the authenticated user if no user ID is provided), respecting shared membership for non-public channels.
List team custom emojisRetrieves all custom emojis for the Slack workspace (image URLs or aliases), not standard Unicode emojis; does not include usage statistics or creation dates.
List Slack filesLists files and their metadata within a Slack workspace, filterable by user, channel, timestamp, or type; returns metadata only, not file content.
List pinned items in a channelRetrieves all messages and files pinned to a specified channel; the caller must have access to this channel.
List remindersLists all reminders with their details for the authenticated Slack user; returns an empty array if no reminders exist (valid state, not an error).
List remote filesRetrieve information about a team's remote files.
List all users in a user groupRetrieves a list of all user IDs within a specified Slack user group, with an option to include users from disabled groups.
List user groupsLists user groups in a Slack workspace, including user-created and default groups; results for large workspaces may be paginated.
List user reactionsLists all reactions added by a specific user to messages, files, or file comments in Slack, useful for engagement analysis when the item content itself is not required.
Lookup Canvas SectionsLooks up section IDs in a Slack Canvas for use with targeted edit operations.
Open DMOpens or resumes a Slack direct message (DM) or multi-person direct message (MPIM) by providing either user IDs or an existing channel ID.
Pin an item to a channelPins a message to a specified Slack channel; the message must not already be pinned.
Remove call participantsRegisters participants removed from a Slack call.
Remove reaction from itemRemoves an emoji reaction from a message, file, or file comment in Slack.
Remove remote fileRemoves the Slack reference to an external file (which must have been previously added via the remote files API), specified by either its `external_id` or `file` ID (one of which is required), without deleting the actual external file.
Remove user from conversationRemoves a specified user from a Slack conversation (channel); the caller must have permissions to remove users and cannot remove themselves using this action.
Rename a conversationRenames a Slack channel, automatically adjusting the new name to meet naming conventions (e.
Retrieve conversation informationRetrieves metadata for a Slack conversation by ID (e.
Get conversation membersRetrieves a paginated list of active member IDs (not names, emails, or presence) for a specified Slack public channel, private channel, DM, or MPIM.
Retrieve user DND statusRetrieves a Slack user's current Do Not Disturb (DND) status to determine their availability before interaction; any specified user ID must be a valid Slack user ID.
Retrieve detailed file informationRetrieves detailed metadata and paginated comments for a specific Slack file ID; does not download file content.
Retrieve detailed user informationRetrieves comprehensive information for a valid Slack user ID, excluding message history and channel memberships.
Retrieve user profile informationRetrieves profile information for a specified Slack user (defaults to the authenticated user if `user` ID is omitted); a provided `user` ID must be valid.
Revoke a file's public urlRevokes a Slack file's public URL, making it private; this is a no-op if not already public and is irreversible.
Schedule messageSchedules a message to a Slack channel, DM, or private group for a future time (`post_at`), requiring `text`, `blocks`, or `attachments` for content; scheduling is limited to 120 days in advance.
Search all contentTool to search all messages and files.
Search messagesWorkspace‑wide Slack message search with date ranges and filters.
Send ephemeral messageSends an ephemeral message visible only to the specified `user` in a channel; other channel members cannot see it.
Share a me message in a channelSends a 'me message' (e.
Send messagePosts a message to a Slack channel, DM, or private group; requires at least one content field (`markdown_text`, `text`, `blocks`, or `attachments`) — omitting all causes a `no_text` error.
Set a conversation's purposeSets the purpose (a short description of its topic/goal, displayed in the header) for a Slack conversation; the calling user must be a member.
Set conversation read cursorMarks a message, specified by its timestamp (`ts`), as the most recently read for the authenticated user in the given `channel`, provided the user is a member of the channel and the message exists within it.
Set conversation topicSets or updates the topic for a specified Slack conversation.
Set user presenceManually sets a user's Slack presence, overriding automatic detection; this setting persists across connections but can be overridden by user actions or Slack's auto-away (e.
Share a remote file in channelsShares a remote file, which must already be registered with Slack, into specified Slack channels or direct message conversations.
Start callRegisters a new call in Slack using `calls.
Unarchive channelReverses conversation archival.
Unpin message from channelUnpins a message, identified by its timestamp, from a specified channel if the message is currently pinned there; this operation is destructive.
Update call informationUpdates the title, join URL, or desktop app join URL for an existing Slack call identified by its ID.
Update an existing remote fileUpdates metadata or content details for an existing remote file in Slack; this action cannot upload new files or change the fundamental file type.
Update a Slack messageUpdates a Slack message, identified by `channel` ID and `ts` timestamp, by modifying its `text`, `attachments`, or `blocks`; provide at least one content field, noting `attachments`/`blocks` are replaced if included (`[]` clears them).
Update Slack user groupUpdates an existing Slack User Group, which must be specified by an existing `usergroup` ID, with new optional details such as its name, description, handle, or default channels.
Update user group membersReplaces all members of an existing Slack User Group with a new list of valid user IDs.
Upload or create a file in SlackUpload files, images, screenshots, documents, or any media to Slack channels or threads.

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:

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

Step-by-step Guide

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 Slackbot account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Slackbot

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

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-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 Slackbot access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called slackbot_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

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 def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["slackbot"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Slackbot actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Slackbot actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

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, slackbot)
  • 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 Slackbot tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Slackbot database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

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 Slackbot

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

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

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["slackbot"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Slackbot actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Slackbot actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Slackbot to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Slackbot 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.

How to build Slackbot MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Slackbot MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Slackbot MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Slackbot MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Slackbot MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Slackbot MCP with Claude Cowork

Codex logo

Codex

Use Slackbot MCP with Codex

Cursor logo

Cursor

Use Slackbot MCP with Cursor

OpenClaw logo

OpenClaw

Use Slackbot MCP with OpenClaw

Hermes logo

Hermes

Use Slackbot MCP with Hermes

CLI logo

CLI

Use Slackbot MCP with CLI

Google ADK logo

Google ADK

Use Slackbot MCP with Google ADK

LangChain logo

LangChain

Use Slackbot MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Slackbot MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Slackbot MCP with Mastra AI

CrewAI logo

CrewAI

Use Slackbot MCP with CrewAI

OpenCode logo

OpenCode

Use Slackbot MCP with OpenCode

VS Code logo

VS Code

Use Slackbot MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Slackbot MCP?

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

Can I use Tool Router MCP with LlamaIndex?

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 Slackbot tools.

Can I manage the permissions and scopes for Slackbot while using Tool Router?

Yes, absolutely. You can configure which Slackbot 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.

How safe is my data with Composio Tool Router?

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 Slackbot data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗