Tap into 20+ purpose-built recruiting tools in one node and get structured data you can trust for automation.
What is Ashby MCP?
Ashby MCP creates a customized node that understands the Ashby platform and its data model. You can describe what you need in natural language, and it will perform the requested action or fetch the right records from Ashby. The node returns structured data so you can pass specific fields into the next step of your workflow.What Can It Do for You?
- Find and manage candidates, users, applications, and jobs with search and filters
- Create, update, and cancel interview schedules with clear time and participant details
- Maintain job status and metadata as roles open, pause, or close
- Keep applications moving by updating stages, sources, notes, tags, and hiring team
Available Tools
Tool | What It Does | Example Use |
---|---|---|
List Interviewer Pools | List all interviewer pools with optional filtering and pagination support | ”List interviewer pools matching pool name and return name, id, and member count as structured data” |
Get Interviewer Pool Info | Get detailed information about a specific interviewer pool | ”Using interviewer pool name , find the pool id with List Interviewer Pools, then return pool name, id, training stages, and member emails as structured data” |
Add User To Interviewer Pool | Add a user to an interviewer pool with optional training stage assignment | ”Using user email to get user id from List Users, and pool name to get pool id from List Interviewer Pools, add the user to the pool with training stage training stage , and return user id, pool id, and training stage as structured data” |
List Users | List or search Ashby users with pagination support | ”Search users matching name or email and return user id, name, email, and role as structured data” |
Get User Info | Get detailed information about a specific Ashby user | ”Given user email , find the user via List Users and return user id, name, email, manager, and active status as structured data” |
List Interviews | List all interviews with optional filtering and pagination support | ”List interviews scheduled in date range and return interview id, candidate name, interviewer names, start time, and time zone as structured data” |
Get Interview Info | Get detailed information about a specific interview | ”Using interview id from a previous step, return candidate name, job title, interviewer names, start time, end time, and interview format as structured data” |
List Interview Schedules | Get all interview schedules with filtering and pagination support | ”List interview schedules for candidate name on job title and return schedule id, start time, end time, and interviewer names as structured data” |
Create Interview Schedule | Create a new interview schedule with events, interviewers, and timing | ”Create an interview schedule for candidate name on date between start time and end time with interviewer interviewer name , and return schedule id, event start, event end, and interviewer names as structured data” |
Update Interview Schedule | Update an existing interview schedule with new events or timing | ”Update schedule id from previous step to new date with new start time to new end time , keep interviewer interviewer name , and return schedule id and updated times as structured data” |
Cancel Interview Schedule | Cancel an existing interview schedule with optional reschedule allowance | ”Cancel schedule id from previous step with reschedule allowed true or false , and return schedule id and status as structured data” |
List Jobs | List or search jobs with comprehensive filtering and pagination support | ”List jobs filtered by status and location , and return job id, title, location, and hiring manager as structured data” |
Update Job | Update job properties including title, team, location, and interview plans | ”Using job title to find the job via List Jobs, update location to location and team to team name , and return job id, title, team, and location as structured data” |
Set Job Status | Change the status of a job with validation and transition rules | ”Using job title , find the job via List Jobs, set status to Open or Closed , and return job id, title, and new status as structured data” |
List Applications | Get all applications with comprehensive filtering and pagination support | ”List applications for job title at stage stage , and return application id, candidate name, job title, and stage as structured data” |
Get Application Info | Get detailed information about a specific application | ”For candidate name on job title , find the application and return application id, stage, source, credited user, and owner as structured data” |
Update Application | Update application properties including source, credited user, and dates | ”Using application id from a previous step, set credited user to user email and add applied date YYYY-MM-DD , and return application id, credited user, and applied date as structured data” |
Remove Application Hiring Team Member | Remove a user from the hiring team at the application level | ”Using application id from a previous step, remove hiring team member user email , and return application id and updated hiring team as structured data” |
Change Application Source | Change the source of an application or unset it | ”For candidate name on job title , set application source to source name , and return application id and source as structured data” |
Change Application Stage | Move an application to a different interview stage | ”Move application for candidate name on job title to stage target stage , and return application id and new stage as structured data” |
List Candidates | List or search candidates with pagination support | ”Search candidates matching name or email and return candidate id, full name, email, and current company as structured data” |
Get Candidate Info | Get detailed information about a specific candidate | ”Given candidate name , find the candidate and return candidate id, full name, email, phone, and LinkedIn URL as structured data” |
Create Candidate | Create a new candidate with comprehensive profile information | ”Create a candidate with full name full name , email email address , and LinkedIn URL profile url , and return candidate id, name, and email as structured data” |
Update Candidate | Update candidate profile information including contact details and social links | ”Using candidate email to find the candidate, update phone to phone number and location to location , and return candidate id, name, phone, and location as structured data” |
Add Candidate To Project | Add a candidate to a specific project for organization and tracking | ”Using candidate id from List Candidates or Create Candidate, add to project project name , and return candidate id and project name as structured data” |
Add Candidate Tag | Add a tag to a candidate for categorization and filtering | ”Using candidate email to find the candidate, add tag tag name , and return candidate id and tags as structured data” |
Create Candidate Note | Create a note on a candidate with plain text or HTML formatting support | ”Add a note to candidate with candidate email using text note content , and return note id, author, and created time as structured data” |
Anonymize Candidate | Anonymize a candidate (irreversible action) | “Using candidate email to find the candidate, anonymize the record, and return candidate id and anonymization status as structured data” |
How to Use
1
Create Your Ashby MCP Node
Go to your node library, search for Ashby, and click “Create a node with AI”
2
Add Your Prompt
Drag the Ashby MCP node to your canvas and add your prompt in the text box.
3
Test Your Node
Run the node to see the results. If it works as expected, you’re all set! If you run into issues, check the troubleshooting tips below.
4
Save and Reuse
Once your Ashby MCP node is working, save it to your library. You can now use this customized node in any workflow.
Example Prompts
Here are some prompts that work well with Ashby MCP. Feel free to adapt the variables to suit your workflow. JobsStart simple. Build one node for each action you want to automate, return only the fields you need, then chain nodes together. Use names, emails, and search terms in your prompts and have earlier nodes fetch any required ids for later steps.
Troubleshooting
If your Ashby MCP node isn’t working as expected, try these best practices:Keep Prompts Simple and Specific
- Good: “Search for
job title
and return job id and status” - Bad: “Find
candidate name
, update their email, add a note, and schedule an interview tomorrow at 10am withinterviewer name
”
While the complex prompt might run, it’s more efficient to break it into separate nodes. Ashby MCP works best with focused, single-action prompts.
Match What Ashby Can Do
- Good: “Move the application for
candidate name
onjob title
to stagetarget stage
and return application id and new stage” - Bad: “Send a Slack message to the candidate about the interview time”
Ashby MCP excels at applicant tracking and scheduling. For messaging, combine it with Slack Message Sender/Reader or Gmail Sender/Reader in your workflow.
Break Complex Tasks Into Steps
Instead of trying to do everything in one prompt (which might cause timeouts or added complexity):1
Step 1: Get Candidates
Search candidates matching
department
and return candidate ids and emails as structured data2
Step 2: Update Application Stage
Using candidate names and
job title
, move applications to target stage
and return application ids and new stage as structured data3
Step 3: Schedule Interviews
For each
candidate name
, create an interview schedule on date
from start time
to end time
with interviewer name
, and return schedule id and event times as structured dataIn your workflow, connect these nodes sequentially. The candidate ids output from Step 1 become inputs for Step 2, and the application or candidate details from Step 2 feed into Step 3.
Focus on Data Retrieval
Ashby MCP is great at getting information from Ashby. For analysis or content creation, connect it to other nodes. Example:- Good prompt: “List applications for
job title
at stagestage
and return application id, candidate name, and stage as structured data” - Bad prompt: “List applications and create a hiring funnel summary with suggested next steps”
Use Ask AI to interpret or summarize data. Keep your Ashby node focused on retrieval or a single update action.
Troubleshooting Node Creation
Empty Outputs
Empty Outputs
In the node creation window, click “Request changes” and ask the AI to add debug logs and verify the API response.
Incorrect Results
Incorrect Results
In the node creation window, click “Request changes” and describe what you expected versus what you received.
Errors
Errors
First click “Fix with Gummie”. If multiple attempts fail, simplify your prompt or contact support.
Iterate with Request Changes
Iterate with Request Changes
MCP node creation often requires a few tweaks. Use “Request changes” (in the node creation window) to refine filters, output fields, or pagination.
Need More Help?
- Watch What are MCP Nodes video tutorial
- Check out MCP Best Practices in Gumloop University
- Join the Gumloop Community for support
- View the Ashby MCP setup guide for Claude and Cursor
- Contact support at support@gumloop.com