Skip to main content

Once your AI client is connected to the Reactive Resume MCP server, you can run your job search from a chat: add roles you find, move applications through their stages, log notes and interviews, attach the PDFs you sent, and ask for match scores or tailored resumes. This guide gives you prompts that work well and explains what each one does behind the scenes.

Before you start#

  • Connect your client to the MCP server with OAuth or an API key. See Using the MCP server.
  • Ask the client to list its Reactive Resume tools. You should see list_applications, create_application, update_application and the other application tools.
  • For match scores, tailored resumes, drafted letters and job-posting autofill, set up and test a default AI provider in Reactive Resume. See Connecting an AI provider. These tools send your resume and the job description to that provider.

How applications are organized#

Every application sits in one stage: saved, applied, screening, interview, offer or closed. Closing an application takes a reason: not-selected, withdrew, accepted-other or no-response. Each application also has a timeline of stage changes, notes and interviews, optional contacts, tags, a follow-up date, a linked resume and letter, and the resume and cover-letter PDFs you sent.

If you’ve added your own stages, such as Take-home assignment or Ghosted, each one has an ID and counts as one of those six. The client reads your stages with api_applications_lanes_get and passes a stage’s ID as laneId to list_applications, create_application, update_application or bulk_update_applications. Moving to a Closed stage with a preset outcome, such as Ghosted, doesn’t need a reason. See Customizing application stages.

These are the same applications you see in the app’s List, Board, Insights and Calendar views. See Tracking job applications.

Review your pipeline first#

Start each session by having the client read what’s already there. That gives it valid IDs and stops it from creating duplicates.

The client uses list_applications (which can filter by stage and tags), read_application and get_application_stats.

Add applications#

When you know the details, ask for the application directly. Only company and role are required.

If you have a job posting, paste it and ask the client to read it first. The autofill tool works on pasted text; it doesn’t open links.

To bring in many rows at once, paste them and ask for an import. import_applications takes up to 500 rows per call.

For spreadsheets you can also import a CSV file in the web app. See Importing applications from CSV.

Move stages and add notes#

The client uses update_application for stages, contacts, tags and follow-up dates, and add_application_note for notes. When update_application changes a list such as contacts or tags, the list it sends replaces the old one, so a careful client reads the application first and sends the full list.

When an application with a linked resume reaches Applied or a later stage, Reactive Resume saves that resume, and the linked letter, as a sent version named after the company. You can see later exactly what you sent.

Schedule interviews#

Interviews have a type (screening, technical, behavioral, onsite or other), a start time, a duration (60 minutes if you don’t say), and an optional location and notes. They appear on the application’s timeline and on the Applications calendar. The client uses add_application_interview, update_application_interview and, to cancel, delete_application_timeline_entry. See Scheduling interviews.

Attach what you sent#

attach_application_document accepts one resume PDF and one cover-letter PDF per application, up to 10 MB each, sent as base64. Attaching a new file replaces the old one.

Warning

Anyone with the address of an attached PDF can download it without signing in. Attaching a file never sends it to an employer.

If your client can’t read files from your computer, attach the PDF in the app instead. See Managing an application.

Use AI on an application#

These tools need a tested default AI provider. Scoring and tailoring also need a job description and a linked resume on the application. Drafting uses them when they’re there.

ToolWhat it changes
score_application_matchSaves a new match score on the application, replacing the previous one.
tailor_resume_for_applicationCreates a private copy of the linked resume with a rewritten summary, links the copy to the application in place of the original and adds a timeline note. The original resume is unchanged.
draft_application_messageIn cover-letter mode, saves a new cover letter and returns its text and ID. In follow-up mode, returns the text only. It never sends anything.
autofill_application_from_jobReturns suggested company, role, location and salary from a pasted posting. It saves nothing.

Read anything the AI writes before you use it. You can also tailor resumes and write letters from the app; see Tailoring a resume for a job.

Clean up#

bulk_update_applications moves up to 200 applications to a stage or adds tags to them. delete_application and bulk_delete_applications delete permanently, including uploaded PDFs that no other application uses; there is no Trash for applications.

Suggested client instructions#

Add this to your client’s project or session instructions so it handles your applications carefully:

Troubleshooting#

ProblemWhat to do
The client can’t see application toolsReconnect the server and ask the client to refresh its tools.
The client creates duplicatesAsk it to list applications first and match on company and role before creating one.
A stage change to rejected or an archive request failsThose no longer exist. Use the closed stage with a reason.
Attaching a document failsOnly PDFs up to 10 MB are accepted. Attach from the app if your client can’t read the file.
Scoring, tailoring or drafting failsCheck that a default AI provider is set up and tested. For scoring and tailoring, also check that the application has a job description and a linked resume.