How to integrate Ashby MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Ashby logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Ashby to LlamaIndex using the Composio tool router. By the end, you'll have a working Ashby agent that can list all candidates for open roles, post a new job opening for engineering, summarize candidates in interview stage through natural language commands.

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

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

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

The Ashby MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ashby account. It provides structured and secure access to your recruiting data, so your agent can perform actions like managing job postings, tracking candidate progress, scheduling interviews, and generating hiring reports on your behalf.

  • Automated job posting management: Easily create, update, or close job listings across your organization with direct agent assistance.
  • Candidate pipeline tracking: Have your agent fetch, organize, and update candidate progress through every stage of the hiring process.
  • Interview scheduling and coordination: Let your agent schedule interviews, send calendar invites, and manage interviewer assignments to streamline the process.
  • Data-driven hiring analytics: Generate reports and insights about your hiring funnel, candidate sources, and time-to-hire with a simple agent request.
  • Centralized communication with applicants: Enable your agent to send status updates, feedback, or reminders to candidates, keeping everyone in the loop automatically.

Supported Tools & Triggers

Tools
Add Candidate to ProjectAdd a candidate to a project in Ashby.
Add Candidate TagAdd a tag to a candidate in Ashby.
Add Hiring Team MemberAdd an Ashby user to a hiring team at the application, job, or opening level.
Add User to Interviewer PoolAdd a user to an interviewer pool.
Add Opening JobAdds a job to an opening (job requisition) in Ashby ATS.
Add Opening LocationTool to add a location to an opening (job requisition).
Anonymize CandidateAnonymize a candidate by removing personally identifiable information.
Approve OfferApprove an offer or a specific approval step within an offer's approval process.
Archive DepartmentArchive a department by its unique identifier.
Archive Interviewer PoolArchive an interviewer pool in Ashby.
Archive LocationArchives a location or location hierarchy in Ashby.
Change Application SourceChange the source attribution of an application.
Change Application StageMove an application to a different interview stage in the hiring pipeline.
Create ApplicationCreate a new job application by associating a candidate with a job opening in Ashby ATS.
Create CandidateCreate a new candidate in the system.
Create Candidate NoteCreate a note on a candidate profile.
Create Candidate TagCreate a new candidate tag in Ashby for categorizing and organizing candidates.
Create Custom FieldCreate a new custom field in Ashby.
Create DepartmentCreate a new department.
Create Interviewer PoolCreate a new interviewer pool.
Create JobCreate a new job opening in Ashby ATS.
Create LocationCreate a new location or location hierarchy.
Create OfferCreate a new offer for a candidate in Ashby ATS.
Create OpeningCreate a new opening (job requisition) in Ashby ATS.
Create ReferralCreate a referral in Ashby ATS by submitting a referral form with candidate information.
Create Survey RequestGenerate a survey request and receive a survey URL to send to a candidate.
Create Survey SubmissionCreate a new survey submission for a candidate's application.
Get API Key InfoRetrieve information about the current API key, including associated organization, user details, and permissions.
Get Application InfoRetrieve detailed information about a specific application by its ID.
Get Candidate InfoRetrieve detailed information about a specific candidate by their ID.
Get Custom Field InfoRetrieve detailed information about a specific custom field by its ID.
Get Department InfoRetrieve detailed information about a specific department by its ID.
Get Feedback Form DefinitionRetrieve detailed information about a specific feedback form definition by its ID.
Get File InfoRetrieve the URL of a file associated with a candidate.
Get Interviewer Pool InfoRetrieve detailed information about a specific interviewer pool by its ID.
Get Interviewer User SettingsGet interviewer settings for a specific user by their ID.
Get Interview InfoRetrieve detailed information about a specific interview type by its ID.
Get Interview Stage InfoTool to fetch interview stage details by ID.
Get Job InfoRetrieve detailed information about a specific job by its ID.
Get Job Interview Plan InfoRetrieve the interview plan information for a specific job.
Get Job Posting InfoRetrieve detailed information about a specific job posting by its ID.
Get Location InfoRetrieve detailed information about a specific location by its ID.
Get Offer InfoRetrieve detailed information about a specific offer by its ID.
Get Opening InfoRetrieve detailed information about a specific opening (job requisition) by its ID.
Get Referral FormFetches the default referral form or creates a default referral form if none exists.
Get Survey Form DefinitionRetrieve detailed information about a specific survey form definition by its ID.
Get User InfoRetrieve detailed information about a specific user by their ID.
List Application Criteria EvaluationsRetrieve AI-generated criteria evaluations for an application.
List Application FeedbackRetrieve all feedback submissions for an application.
List Application Hiring Team RolesRetrieve all available hiring team roles for applications in the organization.
List Application HistoryRetrieve the complete history of stage transitions for an application.
List ApplicationsRetrieve a list of applications with optional pagination and sync-token filtering for incremental updates.
List ApprovalsRetrieve a list of approvals (offer approvals, job approvals, etc.
List Archive ReasonsRetrieve a list of all archive reasons.
List BrandsRetrieve a list of all brands for the organization.
List Candidate Client InfoRetrieve all client info records for a specific candidate with pagination support.
List Candidate NotesRetrieve all notes for a specific candidate in Ashby.
List Candidate ProjectsRetrieve all projects associated with a candidate.
List CandidatesRetrieve a list of candidates.
List Candidate TagsRetrieve a list of all candidate tags in your Ashby account.
List Close ReasonsLists all close reasons for jobs or openings.
List Communication TemplatesRetrieve a list of all communication templates.
List Custom FieldsRetrieve a list of all custom field definitions configured in Ashby.
List DepartmentsRetrieve a list of all departments in the organization.
List Feedback Form DefinitionsRetrieve all feedback form definitions from your Ashby organization.
List Hiring Team RolesRetrieve a list of possible hiring team roles in the organization.
List Interviewer PoolsRetrieve a list of all interviewer pools.
List Interview EventsRetrieves all interview events for a specific interview schedule.
List Interview PlansRetrieve a list of interview plans.
List Interview TypesList all interview types defined in Ashby.
List Interview SchedulesRetrieve a list of interview schedules.
List Interview Stage GroupsRetrieve a list of interview stage groups.
List Interview StagesRetrieve all interview stages for an interview plan in order.
List Job BoardsRetrieve a list of job boards.
List Job PostingsRetrieve a list of job postings.
List JobsRetrieve a list of all jobs from Ashby ATS (Applicant Tracking System).
List Job TemplatesRetrieve a list of all job templates from Ashby ATS.
List LocationsRetrieve a list of all locations.
List OffersRetrieve a list of job offers with their latest versions.
List OpeningsRetrieve a list of openings (job requisitions).
List ProjectsRetrieve a list of all projects.
List SourcesRetrieve a list of all candidate sources.
List Source Tracking LinksRetrieve all source tracking links configured in Ashby.
List Survey Form DefinitionsRetrieve a list of all survey form definitions from Ashby.
List Survey SubmissionsLists all survey submissions of a given survey type from Ashby.
List UsersRetrieve a list of all users in the organization.
Move DepartmentTool to move a department to another parent in the organizational hierarchy.
Move LocationTool to move a location to a different parent in the location hierarchy.
Remove Hiring Team MemberRemove an Ashby user from a hiring team at the application, job, or opening level.
Remove User from Interviewer PoolRemove a user from an interviewer pool.
Remove Opening JobRemove a job from an opening (job requisition) in Ashby ATS.
Remove Opening LocationTool to remove a location from an opening (job requisition).
Restore DepartmentRestore an archived department by its unique identifier.
Restore Interviewer PoolRestore an archived interviewer pool in Ashby.
Restore LocationRestores an archived location or location hierarchy in Ashby.
Search CandidatesSearch for candidates by email or name.
Search JobsSearch for jobs by title in Ashby ATS (Applicant Tracking System).
Search OpeningSearch for openings by identifier.
Search ProjectsSearch for projects by title in Ashby.
Search UsersSearch for an Ashby user by email address.
Set Custom Field ValueSet the value of a custom field for a given object (candidate, application, job, etc.
Set Custom Field ValuesSet the values of multiple custom fields for a given object in a single call.
Set Job StatusSet the status of a job in Ashby ATS (Applicant Tracking System).
Set Opening ArchivedSets the archived state of an opening.
Set Opening StateSet the workflow state of an opening (job requisition).
Start OfferCreate a new offer version instance for an in-progress offer process.
Start Offer ProcessStart an offer process for a candidate's application in Ashby ATS.
Submit Application FeedbackSubmit structured feedback for an application using a feedback form.
Transfer ApplicationTransfer an application to a different job position in Ashby ATS.
Update ApplicationUpdate an application's properties in Ashby.
Update Application HistoryUpdate the complete history of an application's stage transitions.
Update CandidateUpdate an existing candidate's profile information in Ashby ATS.
Update Job CompensationUpdate a job's compensation tiers in Ashby ATS.
Update DepartmentUpdate an existing department's information such as its name.
Update Interviewer PoolUpdate an existing interviewer pool's title or training requirements.
Update JobUpdate an existing job's properties in Ashby ATS.
Update Job PostingUpdate an existing job posting's details including title, description, and visibility status.
Update Location AddressUpdate the address of a location or location hierarchy.
Update Location External NameUpdate a location's external (candidate-facing) name.
Update Location NameUpdate a location's name.
Update Location Remote StatusTool to update a location's remote status.
Update Location Workplace TypeTool to update a location's workplace type (OnSite, Remote, or Hybrid).
Update OpeningUpdate properties of an existing opening (job requisition).
Update Selectable Values Custom FieldUpdate the selectable values for a ValueSelect or MultiValueSelect custom field.
Update User Interviewer SettingsUpdate interviewer settings for a user, including daily and weekly interview limits.

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

Getting API Keys for OpenAI, Composio, and Ashby

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 Ashby 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 ashby_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=["ashby"],
    )

    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 Ashby actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Ashby 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, ashby)
  • 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 Ashby 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 Ashby 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 Ashby

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Ashby 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=["ashby"],
    )

    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 Ashby actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Ashby 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 Ashby to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Ashby 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 Ashby MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ashby MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ashby MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Ashby MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ashby MCP with Claude Cowork

Codex logo

Codex

Use Ashby MCP with Codex

OpenClaw logo

OpenClaw

Use Ashby MCP with OpenClaw

Hermes logo

Hermes

Use Ashby MCP with Hermes

CLI logo

CLI

Use Ashby MCP with CLI

Google ADK logo

Google ADK

Use Ashby MCP with Google ADK

LangChain logo

LangChain

Use Ashby MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Ashby MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Ashby MCP with Mastra AI

CrewAI logo

CrewAI

Use Ashby MCP with CrewAI

FAQ

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

With a standalone Ashby MCP server, the agents and LLMs can only access a fixed set of Ashby tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ashby 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 Ashby tools.

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

Yes, absolutely. You can configure which Ashby 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 Ashby 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↗