Ashby MCP Server

Candidates, interviews and pipeline stages in Ashby, run by your agent.

View on cotlet.dev

Hosted MCP Server

npx add-mcp 'https://cotlet.dev/mcp/v1/ashby'

Installs into Claude Code, Codex, Cursor and more

Documentation

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Ashby API and MCP server

Yes. Ashby has a public API (API key, JSON calls) and, since 29 Jun 2026, an official MCP server in open beta, but the MCP changes only four things: it creates candidates, adds notes, moves an application to another stage and considers a candidate for a job (checked 16 Oct 2026).

Candidates, interviews and pipeline stages in Ashby, run by your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Applicant tracking system for recruiting teams: jobs, candidate profiles, interview plans and stages, interview scheduling, emails, offers and e-signatures in one place.

What is the Ashby API?

Cotlet's Ashby API exposes 12 endpoints for your own Ashby account: list jobs, search candidates, get candidate, list applications, list interviews, list archive reasons, list email templates, schedule interview, send email to candidate, archive (reject) application, create offer and send offer letter. The list_jobs endpoint returns jobs with title, status, department and hiring team, open jobs by default. Each endpoint takes simple JSON inputs like candidate_id, application_id or cursor and works both as an operation of the ashby_read or ashby_write MCP tool for agents and as a REST call for scripts.

  • Category: HR & recruiting
  • Endpoints: 12 (7 read, 5 write)
  • Updated: 2026-11-10

Yes. Cotlet is a hosted MCP server and REST API for Ashby with 12 endpoints (7 read, 5 write): you sign in once in your own cloud browser, your AI agent does the work.

Does Ashby have an official API?

Yes. Ashby has a public API (API key, JSON calls) and, since 29 Jun 2026, an official MCP server in open beta, but the MCP changes only four things: it creates candidates, adds notes, moves an application to another stage and considers a candidate for a job (checked 16 Oct 2026).

TaskAshby officialCotlet
Search candidates and read their profilesYes: Official MCP reads candidates, notes, emails and feedbackYes
List open jobs and applications by stageYes: Official MCP filters applications, jobs and openingsYes
Schedule an interviewPartly: No scheduling tool in the official MCP; the public API lists interviewSchedule.createYes
Send an email to a candidatePartly: No email tool in the official MCP; the public API lists candidate.addEmailMessageYes
Reject a candidate with an archive reason and emailPartly: No reject tool in the official MCP; the public API lists archiveReason.list and application.changeStageYes
Create an offerPartly: No offer tool in the official MCP; the public API lists offer.create and offer.startYes
Send the offer letterNo: No offer letter endpoint in the API indexYes

Sources: Ashby Knowledge Base: Ashby MCP Server (Beta), Ashby product update: Ashby MCP, Ashby API reference: Introduction, Ashby API reference: endpoint index (llms.txt)

Quick reference

Yes. Ashby has a public API (API key, JSON calls) and, since 29 Jun 2026, an official MCP server in open beta, but the MCP changes only four things: it creates candidates, adds notes, moves an application to another stage and considers a candidate for a job (checked 16 Oct 2026).
Cotlet provides a hosted MCP server and REST API for Ashby: 12 tools (7 read, 5 write).
Access       Sign up at https://cotlet.dev/app/signup?app=ashby and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    ashby_read, ashby_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/ashby, each operation at its own route, e.g. POST /api/v1/ashby/applications/{application_id}/archive
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_jobs, search_candidates, get_candidate, list_applications, list_interviews, list_archive_reasons, list_email_templates, schedule_interview, send_email, archive_application, create_offer, send_offer_letter
Confirm      schedule_interview, send_email, archive_application, create_offer, send_offer_letter (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/ashby-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=ashby and requests Ashby in the Cotlet console.
2. The user signs in to Ashby once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Ashby for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Ashby server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Ashby MCP server instead.

Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Ashby in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Ashby only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Ashby login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Ashby's terms; Cotlet is not affiliated with Ashby.

What can an AI agent do in Ashby?

Cotlet is best for recruiters and talent teams who want their AI agent to schedule interviews, send emails, reject candidates and create offers in Ashby, the steps its official MCP does not do, without running or fixing a server.

  • Reject candidates and send rejection emails (runs: weekly): "List active applications in the Senior Backend Engineer job that sit in Application Review and were submitted more than 14 days ago. Reject the ones whose resume shows under 3 years of backend work with the archive reason "Not a fit", send the rejection email template "After screen" and show me the rest." → list_applications, get_candidate, list_archive_reasons, archive_application
  • Schedule interviews for candidates in a stage (runs: daily): "For candidates who just moved to Technical Screen in the Senior Backend Engineer job, schedule the "Technical screen" interview with priya.nair@example.com for the first free slot on Thursday at 14:00, send the invite to the candidate and add a Google Meet link." → list_applications, get_candidate, list_interviews, schedule_interview
  • Create an offer and send the offer letter (runs: daily): "Ana Costa is in the Offer stage for Product Designer. Create her offer with base salary 95,000 and start date 16 Nov 2026, request approval, and when it is approved send the letter with the "Offer letter" email template." → get_candidate, create_offer, send_offer_letter
  • Email candidates waiting in a stage (runs: weekly): "Find candidates who have been in the Hiring Manager Screen stage for more than 10 days, and send each the "Still interested" email template with a note that we are close to a decision." → list_applications, list_email_templates, send_email
  • Weekly pipeline digest by job (runs: weekly): "Every Monday, list my open jobs and the number of active applications in each stage, and flag stages where candidates have waited more than 7 days." → list_jobs, list_applications

Can Ashby automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Ashby connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to reject candidates and send rejection emails, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

WhereHow to connectHow to schedule
Your AI agentAdd https://cotlet.dev/mcp/v1 with your API key.A scheduled agent run, for example a Claude Code routine.
n8nMCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/ashby/jobs/{job_id}/applications.Schedule Trigger node.
MakeHTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH.Scenario schedule.
ZapierWebhooks by Zapier, Custom Request: the same method, URL, header and body.Schedule by Zapier trigger.
Your own scriptGET https://cotlet.dev/api/v1/ashby/jobs/{job_id}/applications with your API key.cron or GitHub Actions.

Tools

For AI agents: Every endpoint and its schema is public. The 12 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Ashby.

list_jobs

Jobs with title, status, department and hiring team, open jobs by default. Access: read. REST: GET /api/v1/ashby/jobs. MCP: ashby_read → list_jobs.

ParameterTypeRequiredDescription
statusstringnoJob status as Ashby shows it in the Jobs list, for example 'Open'. Default: Open.
cursorstringnoNext page cursor from the previous call.

Returns the jobs of your Ashby organization that your account can see, open ones by default. Use the job_id from each item in list_applications. The status is the one Ashby shows in the Jobs list. Pass next_cursor back as cursor for the next page.

Example response:

{
  "jobs": [
    {
      "job_id": "4e8a1d73-2b60-4c95-9f1e-a7d3560b82c1",
      "title": "Senior Backend Engineer",
      "status": "Open",
      "department": "Engineering",
      "hiring_manager": "Priya Nair",
      "active_applications": 41
    },
    {
      "job_id": "b05c93e7-8a14-4f2d-b6c0-1e7d94a3f528",
      "title": "Product Designer",
      "status": "Open",
      "department": "Design",
      "hiring_manager": "Ana Costa",
      "active_applications": 18
    }
  ],
  "next_cursor": null
}

search_candidates

Candidates by name or email, with their applications and current stage. Access: read. REST: GET /api/v1/ashby/candidates/search. MCP: ashby_read → search_candidates.

ParameterTypeRequiredDescription
querystringyesName or email, or part of it.
tagstringnoOnly candidates with this tag from Add tags.

Finds candidates whose name or email matches the query and returns each with the jobs they applied to and the stage of every application. Use candidate_id in get_candidate and send_email, and application_id in the write tools.

Example response:

{
  "candidates": [
    {
      "candidate_id": "e1f7a309-4c52-4d8b-a063-9b25d7c1e840",
      "name": "Ana Costa",
      "email": "ana.costa@example.com",
      "applications": [
        {
          "application_id": "9c41b7a2-6e03-4d58-a1f9-3b8d25e07c64",
          "job": "Product Designer",
          "stage": "Offer",
          "status": "Active"
        }
      ]
    }
  ]
}

get_candidate

One candidate profile: applications, stage, notes, recent emails and scheduled interviews. Access: read. REST: GET /api/v1/ashby/candidates/{candidate_id}. MCP: ashby_read → get_candidate.

ParameterTypeRequiredDescription
candidate_idstringyesCandidate ID from search_candidates.

Returns the profile fields Ashby shows on the candidate page, plus every application with its stage and archive reason if archived. Notes and emails come newest first. Private fields appear only if your account can see them.

Example response:

{
  "candidate_id": "e1f7a309-4c52-4d8b-a063-9b25d7c1e840",
  "name": "Ana Costa",
  "email": "ana.costa@example.com",
  "source": "Referral",
  "applications": [
    {
      "application_id": "9c41b7a2-6e03-4d58-a1f9-3b8d25e07c64",
      "job": "Product Designer",
      "stage": "Offer",
      "status": "Active",
      "offer": null
    }
  ],
  "notes": [
    {
      "author": "Priya Nair",
      "created_at": "2026-10-14T10:12:00+02:00",
      "text": "Strong portfolio, wants a start in mid November."
    }
  ],
  "recent_emails": [
    {
      "direction": "sent",
      "subject": "Next steps",
      "sent_at": "2026-10-12T09:30:00+02:00"
    }
  ],
  "interviews": [
    {
      "interview": "Design review",
      "start": "2026-10-13T15:00:00+02:00",
      "status": "Completed"
    }
  ]
}

list_applications

Applications of a job with candidate, stage, status and days in stage, newest update first. Access: read. REST: GET /api/v1/ashby/jobs/{job_id}/applications. MCP: ashby_read → list_applications.

ParameterTypeRequiredDescription
job_idstringyesJob ID from list_jobs.
stagestringnoStage name as in the job's interview plan, for example 'Application Review'.
updated_beforestringnoISO date. Only applications not updated since then.
archivedbooleannotrue lists archived applications with their archive reason. Default: false.
cursorstringnoNext page cursor from the previous call.

Lists applications of one job, filtered by stage name and by how long ago they were last updated. Active applications by default; set archived to true to read archived ones with their reasons. Pass next_cursor back as cursor for the next page.

Example response:

{
  "applications": [
    {
      "application_id": "7d2e4c18-5f3a-4b09-8a61-c0e9d3f1a742",
      "candidate": "Chris Nowak",
      "candidate_id": "a6d30b95-7e12-4c48-8f05-2c91e4b7d3a0",
      "stage": "Application Review",
      "status": "Active",
      "days_in_stage": 19
    },
    {
      "application_id": "3f60c8d1-9a27-4e53-b184-d7a05e2c9b36",
      "candidate": "Mei Tanaka",
      "candidate_id": "c82e5f17-0b94-4a6d-93e8-5f1a7d0c4b29",
      "stage": "Application Review",
      "status": "Active",
      "days_in_stage": 16
    }
  ],
  "next_cursor": null
}

list_interviews

Scheduled interviews with time, interviewers and candidate, for one candidate or a date range. Access: read. REST: GET /api/v1/ashby/interviews. MCP: ashby_read → list_interviews.

ParameterTypeRequiredDescription
candidate_idstringnoOnly interviews of this candidate.
fromstringnoISO date. Default: today.
tostringnoISO date. Default: 14 days after from.

Returns the interviews already scheduled in Ashby, soonest first. Pass candidate_id to see one candidate, or a date range to see what is booked across the team, for example to check an interviewer for clashes before schedule_interview.

Example response:

{
  "interviews": [
    {
      "interview": "Technical screen",
      "candidate": "Lena Fischer",
      "start": "2026-10-23T11:00:00+02:00",
      "duration_minutes": 45,
      "interviewers": [
        "priya.nair@example.com"
      ],
      "location": "Google Meet"
    }
  ]
}

list_archive_reasons

The archive reasons your admin set up, to use in archive_application. Access: read. REST: GET /api/v1/ashby/archive-reasons. MCP: ashby_read → list_archive_reasons.

No parameters.

Returns the archive reasons an Ashby admin keeps under Admin > Jobs & Applications > Archive Reasons. archive_application accepts only these names. Ashby asks for a reason on every archive.

Example response:

{
  "archive_reasons": [
    {
      "name": "Not a fit"
    },
    {
      "name": "Position filled"
    },
    {
      "name": "Candidate withdrew"
    }
  ]
}

list_email_templates

The email templates your account can apply, with name and purpose. Access: read. REST: GET /api/v1/ashby/email-templates. MCP: ashby_read → list_email_templates.

No parameters.

Returns the templates shown in the template dropdown of the Ashby email editor that your account can use, such as rejection, scheduling and offer emails. Pass a name to send_email, archive_application or send_offer_letter.

Example response:

{
  "templates": [
    {
      "name": "After screen"
    },
    {
      "name": "Still interested"
    },
    {
      "name": "Offer letter"
    }
  ]
}

schedule_interview

Schedule an interview for an application with interviewers, time, video link and invite settings. Access: write, asks the user first. REST: POST /api/v1/ashby/applications/{application_id}/interview/schedule. MCP: ashby_write → schedule_interview.

ParameterTypeRequiredDescription
application_idstringyesApplication ID from list_applications or get_candidate.
interviewstringyesInterview type name from the job's interview plan, for example Technical screen.
startstringyesISO 8601 start time with offset.
duration_minutesintegeryesLength of the interview.
interviewersarrayyesInterviewer emails, one slot each.
location_typestringno'google_meet', 'zoom', 'microsoft_teams' or 'custom'. Default: custom.
locationstringnoLocation text, only with location_type 'custom'.
notify_candidatebooleannoSend the calendar invite to the candidate. Default: false.
notify_interviewersbooleannoSend the calendar invite to interviewers. Default: false.
confirmation_emailbooleannoSend the Candidate Confirmation Email. Default: false.

Creates an interview the way Manual Schedule does: interview type, start time, length and interviewers, with a Google Meet, Zoom or Microsoft Teams link or custom location text. The candidate and interviewers get calendar invites only if you set notify_candidate and notify_interviewers; the confirmation email is off unless you turn it on. Needs Elevated Access as Hiring Manager or Admin, or Organization Admin. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "interview_id": "f4a1c096-3d78-4e25-8b9c-0a6e57d2b813",
  "interview": "Technical screen",
  "start": "2026-10-22T14:00:00+02:00",
  "duration_minutes": 45,
  "interviewers": [
    "priya.nair@example.com"
  ],
  "location": "Google Meet",
  "candidate_invited": true,
  "confirmation_email_sent": false
}

send_email

Send an email to a candidate from a template or your own text, now or at a set time. Access: write, asks the user first. REST: POST /api/v1/ashby/candidates/{candidate_id}/emails. MCP: ashby_write → send_email.

ParameterTypeRequiredDescription
candidate_idstringyesCandidate ID from search_candidates.
templatestringnoTemplate name from list_email_templates. Or set subject and body.
subjectstringnoSubject, when no template is used.
bodystringnoEmail body, when no template is used.
sendstringno'immediately' or 'scheduled'. Default: immediately. With 'scheduled', set send_at.
send_atstringnoISO 8601 date and time with offset, only with send set to scheduled.

Sends an email to the candidate from the Ashby profile, so it appears in the candidate's email history. Give either a template name or a subject and body; substitution tokens in a template are filled by Ashby. Scheduled emails can be viewed and rescheduled only by the person who drafted them, which is your connected account. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "email_id": "a09d3e72-5b16-4c84-97f0-e2c48b1d6a35",
  "candidate_id": "e1f7a309-4c52-4d8b-a063-9b25d7c1e840",
  "subject": "Still interested?",
  "status": "sent",
  "sent_at": "2026-10-16T09:00:00+02:00"
}

archive_application

Reject an application with an archive reason, an optional note and an optional rejection email. Access: write, asks the user first. REST: POST /api/v1/ashby/applications/{application_id}/archive. MCP: ashby_write → archive_application.

ParameterTypeRequiredDescription
application_idstringyesApplication ID from list_applications or get_candidate.
archive_reasonstringyesReason name from list_archive_reasons.
notestringnoOptional note stored with the archive reason.
email_templatestringnoRejection email template from list_email_templates. Without it no email is sent.
sendstringno'immediately' or 'scheduled'. Default: immediately. With 'scheduled', set send_at.
send_atstringnoISO 8601 date and time with offset, only with send set to scheduled.

Archives the application for that job only and moves the candidate to the Archived stage, like Archive in Ashby. The reason must be one from list_archive_reasons. A rejection email goes out only if you name a template, immediately or at the time you set. Other applications of the same candidate stay active. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "application_id": "7d2e4c18-5f3a-4b09-8a61-c0e9d3f1a742",
  "status": "Archived",
  "archive_reason": "Not a fit",
  "note_added": true,
  "rejection_email": {
    "template": "After screen",
    "status": "sent"
  }
}

create_offer

Create an offer for an application in the Offer stage from your offer form fields. Access: write, asks the user first. REST: POST /api/v1/ashby/applications/{application_id}/offers. MCP: ashby_write → create_offer.

ParameterTypeRequiredDescription
application_idstringyesApplication ID from list_applications or get_candidate.
fieldsobjectyesOffer form values keyed by field title, for example {"Base salary": "95000"}.
opening_idstringnoOpening ID, required when your organization turned on Require Openings for Hires.
request_approvalbooleannoSubmit the approval request after creating. Default: false.

Fills the Offer Details form with the values you give, keyed by field title as set under Admin > Offers > Offer Custom Fields, and submits it. The application must be in the Offer stage. With request_approval set it also submits the approval request, which notifies the approvers; with approvals on, no letter can go out until every step is done. Needs Organization Admin, or the permissions Can See Candidate Profiles, Can Add/Edit Candidates and Can See Private Fields. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "offer_id": "6b3e90d4-1f87-4a52-8c06-d94a7e215b03",
  "application_id": "9c41b7a2-6e03-4d58-a1f9-3b8d25e07c64",
  "fields": {
    "Base salary": "95000",
    "Start date": "2026-11-16"
  },
  "approval_requested": true,
  "approvers": [
    "Hiring Manager",
    "Finance"
  ]
}

send_offer_letter

Generate the offer letter, email it to the candidate and optionally request an e-signature. Access: write, asks the user first. REST: POST /api/v1/ashby/offers/{offer_id}/letter. MCP: ashby_write → send_offer_letter.

ParameterTypeRequiredDescription
offer_idstringyesOffer ID from create_offer or get_candidate.
email_templatestringyesEmail template from list_email_templates.
request_signaturebooleannoAlso send the e-signature request. Default: false.
signatorystringnoCompany signatory email, when the template has company tokens.

Runs Generate Offer Letter, drafts the email from the template and sends it, as View Offer does in Ashby. If your organization uses approvals, the call is refused until every approval step is complete. An e-signature request is added only if the letter template has candidate e-signature tokens and you set request_signature. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "offer_id": "6b3e90d4-1f87-4a52-8c06-d94a7e215b03",
  "letter_generated": true,
  "email_template": "Offer letter",
  "email_status": "sent",
  "signature_requested": true
}

How do I connect Ashby to ChatGPT, Claude, Cursor or Codex?

Connecting Ashby takes three steps: sign up, sign in to Ashby once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.

Connect Ashby to your agent.

  1. Create an account Sign up and add Ashby in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.

  2. Sign in to Ashby in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Ashby there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

  3. Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

    ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:

claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

Cursor:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
  1. Ask your agent Ask in plain words. Your agent finds the Ashby tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
List active applications in the Senior Backend Engineer job that sit in Application Review and were submitted more than 14 days ago. Reject the ones whose resume shows under 3 years of backend work with the archive reason "Not a fit", send the rejection email template "After screen" and show me the rest.

Call Ashby from your scripts.

  1. Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
  1. Call a tool Every tool is an endpoint under /api/v1/ashby with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/ashby/applications/7d2e4c18-5f3a-4b09-8a61-c0e9d3f1a742/archive \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"archive_reason":"Not a fit","note":"About 1 year of backend work; the role asks for 3 or more.","email_template":"After screen","send":"immediately"}'
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "application_id": "7d2e4c18-5f3a-4b09-8a61-c0e9d3f1a742",
  "status": "Archived",
  "archive_reason": "Not a fit",
  "note_added": true,
  "rejection_email": {
    "template": "After screen",
    "status": "sent"
  }
}

How to use the Ashby REST API

Create your Cotlet API key

Create a Cotlet API key with access to Ashby and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Ashby in Cotlet and enable it for agents. Account access: Your own Ashby account (Elevated Access or Organization Admin for scheduling and offers).

Make your first Ashby API request

REST:

curl https://cotlet.dev/api/v1/ashby/jobs \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read jobs and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "ashby",
  "tool": "list_jobs",
  "result": {
    "jobs": [
      {
        "job_id": "4e8a1d73-2b60-4c95-9f1e-a7d3560b82c1",
        "title": "Senior Backend Engineer",
        "status": "Open",
        "department": "Engineering",
        "hiring_manager": "Priya Nair",
        "active_applications": 41
      },
      {
        "job_id": "b05c93e7-8a14-4f2d-b6c0-1e7d94a3f528",
        "title": "Product Designer",
        "status": "Open",
        "department": "Design",
        "hiring_manager": "Ana Costa",
        "active_applications": 18
      }
    ],
    "next_cursor": null
  }
}

Returns the jobs of your Ashby organization that your account can see, open ones by default. Use the job_id from each item in list_applications.

The status is the one Ashby shows in the Jobs list. Pass next_cursor back as cursor for the next page.

cursor: Next page cursor from the previous call.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Ashby workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestApplications of a job with candidate, stage, status and days in stage, newest update first. Use list_applications in your configured team report.
MakeHTTP > Make a requestOne candidate profile: applications, stage, notes, recent emails and scheduled interviews. Use get_candidate in your configured team report.
Python or Node.jsREST APIScheduled interviews with time, interviewers and candidate, for one candidate or a date range. Use list_interviews in your configured team report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Ashby; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Why use Cotlet for Ashby?

Built for agents

  • One MCP server for every app you connect.
  • The same tools as a REST API for scripts and cron jobs.
  • Works with ChatGPT, Claude, Claude Code, Codex and Cursor.

Your login stays yours

  • You sign in to Ashby yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
  • A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
  • The model never sees a login.
  • No stored passwords, no MFA bypass.

You stay in control

  • Scope each API key: its apps, its tools, read only or read and write.
  • Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
  • Every background request listed in your Background activity. Disable for agents in one click.

Kept working for you

  • We test every integration every 6 hours.
  • When Ashby changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect Ashby to Cotlet?

Yes. You sign in to Ashby yourself, in your own Cloud Browser, and we never save your password. Your agents only get Ashby once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

  • A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
  • A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
  • A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
  • Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result

How Cotlet protects your access

Common concerns

Who runs Cotlet?

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

Is this an official Ashby integration?

No, Cotlet is independent of Ashby. Ashby's own API is too limited for this work. Cotlet works through your own Ashby account, the way you use Ashby in the browser, so you need no partner approval and no developer setup.

What about client data and GDPR?

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

Can I start with read only?

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

Is it reliable?

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

How do I stop?

Press Disable for agents next to Ashby in your console: your agents lose access at once and you stay signed in. Signing out of Ashby in the browser works too, and Reset browser deletes the whole profile.

Is there a Ashby MCP server on GitHub?

Yes. Community Ashby MCP servers exist on GitHub, usually maintained by one person. You install one on your own computer, give it access to Ashby, and keep it running yourself; when Ashby changes, it stops working until you or the maintainer fix it. Cotlet hosts the same kind of server for you, and our team keeps it working.

GitHub MCP serverCotlet
SetupClone the repo, install it, give it access to Ashby, add it to each MCP clientSign up, sign in to Ashby once, add one MCP server or API key
When Ashby changesIt breaks until you or the maintainer fix itOur team tests it daily and fixes it for you; failed calls are free
Your Ashby accessCredentials in a file on your computer, readable by any program you runSigned in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click
When the session expiresTools fail until you sign in again by handYour Cloud Browser keeps you signed in; if Ashby logs you out, your agent gets a link to sign in again
UpkeepYou update, monitor and debug it yourselfNothing to host or update
Where it runsYour computer, while it is onHosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule
PriceFree, paid for with your timeFree 7-day trial, then pay-as-you-go credit packs, no subscription

Which one fits you

Pick Cotlet if

  • you are not a developer, or you do not want to maintain a server
  • you need it to keep working when Ashby changes, without checking it yourself
  • your agent or a script should run it on a schedule, also while your computer is off

Pick an open-source server if

  • you are comfortable installing, updating and fixing it yourself
  • you want your sign-in to stay on your own computer
  • you only need it now and then, from one MCP client

How much does the Ashby API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Ashby API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

CreditsPrice, one timeCalls at 10 creditsPer 1,000 credits
5,000$29500$5.80
15,000$791,500$5.27
32,000$1493,200$4.66
60,000$2496,000$4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing

How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Ashby account.

  • Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
  • Your sign-in: You sign in to Ashby yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Ashby only after you enable it. When Ashby signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to Ashby, sign out of Ashby in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
  • What we never do: Store passwords or bypass MFA.
  • Ashby's terms: You use your own Ashby account and stay responsible for following Ashby's terms. Cotlet is independent and not affiliated with Ashby. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

Ashby API and MCP: questions

How do I get access?

Sign up free, open Ashby in the console and press Activate. Then you create your API key and connect Ashby there.

Do I need to be technical?

No. You sign in to Ashby once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

Is it safe to connect Ashby to Cotlet?

Yes. You sign in to Ashby yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Ashby once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

Is a hosted server safer than a local one? My Ashby sign-in would leave my computer.

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Ashby cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

Why does Cotlet send requests instead of clicking in my browser?

To be fast, Cotlet doesn't click through Ashby's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Ashby sees the same browser and IP you signed in with, and every request is listed in your Background activity.

What if someone gets my Cotlet API key?

The key holds no Ashby login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

Why a signed-in browser and not OAuth, like other integration platforms?

Ashby offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

How do I connect Ashby to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Ashby once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Ashby account through Cotlet, in their phone apps too.

What can ChatGPT do in Ashby?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Ashby: reject candidates and send rejection emails; schedule interviews for candidates in a stage; create an offer and send the offer letter. You ask in plain words, and anything that reaches other people waits for your OK first.

Why not just use the official Ashby MCP server?

Use it for reads and for its four writes: create a candidate, add a note, change an application's stage and consider a candidate for a job. It has no tool for scheduling interviews, sending emails, rejecting candidates or creating offers, and it is an open beta that an Organization Admin must turn on under Admin > Organization Setup > Opt-In Features. Cotlet covers those missing writes and works next to it.

What role does my Ashby account need?

It depends on the tool. Manual interview scheduling needs Elevated Access as Hiring Manager or Admin, Admin (Private) or Organization Admin. Creating offers needs Organization Admin or the permissions Can See Candidate Profiles, Can Add/Edit Candidates and Can See Private Fields. Approvals need the Plus, Enterprise or Legacy Plus plan.

Can my agent post or send messages in Ashby without asking me?

No. Every call to schedule_interview, send_email, archive_application, create_offer or send_offer_letter waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.

Can I use the Ashby API in n8n?

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/ashby from the HTTP Request node.

Can I use the Ashby API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.

Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.