job-application-tracker-mcp
An offline MCP server that tracks job and internship applications in a single local JSON file, with no login, network calls or API keys.
Add applications one at a time with company, role, deadline, source, type, status and notes (duplicates are saved with a warning).
Bulk import many applications from CSV text; bad rows are skipped and reported with row numbers.
Update stages between applied, interview, offer and rejected, optionally setting an interview date and appending a note.
Edit details like deadline, notes, role, company, type, source or interview date, or clear a field with an empty string.
Delete applications by id (permanent, ids of others unchanged).
List and filter applications by status, company, text query and deadline range, sorted by deadline, company or id, with per-stage counts.
See upcoming items: deadlines of applied-stage applications and interview dates, earliest first, with reminders like "due tomorrow", configurable look-ahead window and overdue inclusion.
Export reports as CSV or Markdown (optionally filtered by status), with CSV formula-injection protection; nothing is written to disk.
Store data locally at
~/.job-tracker-student-mcp/applications.json, relocatable via theJOB_TRACKER_FILEenvironment variable for backups or syncing.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@job-application-tracker-mcp Add a Software Intern role at Shopify with a deadline of 2026-11-15, found on LinkedIn."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Job Application Tracker MCP
Too many job applications spread across tabs and notes. Track them in one place offline.
npx -y job-tracker-student-mcpTry these prompts:
"Add a Software Intern role at Shopify with a deadline of 2026-11-15, found on LinkedIn."
"Move application 1 to interview on 2026-11-20 at 14:30."
"What deadlines and interviews do I have in the next two weeks?"
A free, open source MCP server named job-tracker-student-mcp on npm. Track internships, jobs, interviews and deadlines, see what is coming up, and export your list as CSV or Markdown. Runs on your computer with Claude Desktop, Claude Code, Cursor, VS Code and Windsurf. No internet, no login, no API keys. Your applications are saved in one JSON file that you can open, back up or delete.
Install
Run it straight from npm with npx. You need Node.js 20 or newer, see Node version for the details. There is nothing else to install and no account to make.
npx -y job-tracker-student-mcpAdd it to your app's MCP config so the app can start it for you. Every app reads its config from its own file, so pick yours:
All of them start the same server the same way. The only difference is where the config goes.
Claude Desktop
Add this to claude_desktop_config.json:
{
"mcpServers": {
"job-tracker": {
"command": "npx",
"args": ["-y", "job-tracker-student-mcp"]
}
}
}Restart Claude Desktop after you save the file.
Claude Code
Run this in a terminal:
claude mcp add job-tracker -- npx -y job-tracker-student-mcpCursor
Cursor reads .cursor/mcp.json from the project folder, or ~/.cursor/mcp.json from your home folder if you want the server in every project.
{
"mcpServers": {
"job-tracker": {
"type": "stdio",
"command": "npx",
"args": ["-y", "job-tracker-student-mcp"]
}
}
}Restart Cursor after you save the file.
VS Code
Put this in .vscode/mcp.json in your project folder, or in the mcp.json file in your user profile:
{
"servers": {
"job-tracker": {
"type": "stdio",
"command": "npx",
"args": ["-y", "job-tracker-student-mcp"]
}
}
}Restart VS Code after you save the file.
Windsurf
Add this to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"job-tracker": {
"command": "npx",
"args": ["-y", "job-tracker-student-mcp"]
}
}
}Refresh the plugins list in Windsurf after you save the file.
After any of these, try one of the prompts below.
Related MCP server: Application Tracker MCP
Try these three prompts
Add an application
"Add a Software Intern role at Shopify with a deadline of 2026-11-15, found on LinkedIn."
The assistant calls
add_applicationwithcompany"Shopify",role"Software Intern",deadline"2026-11-15" andsource"LinkedIn". It is saved as application 1 in the applied stage.Move it along
"Move application 1 to interview on 2026-11-20 at 14:30."
update_statussets the status to interview and keeps the interview date, so it shows up in your reminders.See what is coming
"What deadlines and interviews do I have in the next two weeks?"
list_upcominglists deadlines of open applications and interview dates, earliest first, with a reminder such as "due tomorrow" or "overdue by 2 days".
More things you can ask:
"Export all my applications as a CSV."
"Show only my offers as a Markdown table."
"Which deadlines have already passed?"
"Delete application 3, it was a duplicate."
"Which applications mention a referral?"
"Which applications have a deadline in November 2026?"
Tools
There are eight tools. list_applications, list_upcoming and export_report are read only. add_application, import_applications, update_application, update_status and delete_application write to the local JSON file and nothing else.
Tool | What it does | Parameters | Example prompt |
| Add a job or internship with company, role, deadline and source. |
| "Add a Software Intern role at Shopify with a deadline of 2026-11-15, found on LinkedIn." |
| Add many applications from CSV text, such as a spreadsheet export. Needs company and role columns. Bad rows are skipped and listed, and likely duplicates get a warning. |
| "Import these applications from my spreadsheet: company,role,deadline ..." |
| Move an application between applied, interview, offer and rejected. |
| "Move application 1 to interview on 2026-11-20 at 14:30." |
| Update the deadline, notes, role, company, type, source or interview date of an existing application. |
| "Update application 1 to set the deadline to 2026-11-20 and add a note about the referral." |
| Remove a duplicate or mistaken application for good. |
| "Delete application 3, it was a duplicate." |
| List applications with optional status, company, text query and deadline range filters to see ids. The query searches role, notes and source. The result also has counts per stage in |
| "Show my applications by nearest deadline." |
| Show upcoming deadlines and interviews sorted by date, with reminders. |
| "What deadlines and interviews do I have in the next two weeks?" |
| Export applications as CSV or Markdown. |
| "Export all my applications as a CSV." |
Dates are written as YYYY-MM-DD. An interview can also have a time, written as YYYY-MM-DDTHH:MM.
Where your data lives
Applications are saved in ~/.job-tracker-student-mcp/applications.json. Set the JOB_TRACKER_FILE environment variable to use another path. Add it in the env part of your MCP config:
{
"mcpServers": {
"job-tracker": {
"command": "npx",
"args": ["-y", "job-tracker-student-mcp"],
"env": { "JOB_TRACKER_FILE": "C:\\Users\\you\\Documents\\applications.json" }
}
}
}Comparison
This tracker is built for job applications. Some servers focus on course or learning management systems, and some are general task trackers.
Compared with course focused servers, this one works offline with no login to a learning system and no keys. It is job specific, with statuses for applied, interview, offer and rejected, and it tracks deadlines and interview dates with reminders.
Compared with generic task MCP servers, it is focused on job applications rather than general todos. It keeps applications in a simple local JSON file, has read only and write tools for this specific workflow, and can export as CSV or Markdown. Everything runs locally with no account or network calls.
Privacy
The server makes no network calls and has no API keys, passwords or accounts. It reads and writes the one JSON file above and nothing else. There is no telemetry. What you tell the assistant in a chat is handled by the app you use, not by this server.
FAQ
Does it send reminders on its own? No. MCP servers answer when asked. list_upcoming gives you the reminders when you ask, so a good habit is to start the week with "what is coming up?".
Which applications show up in list_upcoming? Deadlines of applications in the applied stage, and interview dates of applications in the interview stage. Offers and rejected applications are left out.
Can I use it on two computers? Point JOB_TRACKER_FILE at a file in a folder you already sync, and both computers read the same list. Do not use both at the same moment.
Troubleshooting
If npx -y job-tracker-student-mcp fails or hangs:
Check your Node.js version with
node --version. The server needs Node.js 20 or newer, see Node version.Delete the folder where npx keeps its downloads, then try again. On Windows it is
%LocalAppData%\npm-cache\_npx, and on macOS and Linux it is~/.npm/_npx.Make sure your computer can reach
registry.npmjs.org. On a school or work network, npm may need proxy settings from the network's owner.If
nodeornpxis not found on Windows, reinstall Node.js with "Add to PATH" checked, then restart your terminal.
If a tool says the file is not valid JSON, open the file named in the message and fix it, or move it away to start a fresh list.
Node version
There are two floors here, and they are not the same number.
What you are doing | Node.js |
Running the published server | 20 or newer |
Building and testing a clone | 22.12 or newer, on the 22 and 24 release lines or 26 and later |
The server itself is happy on Node.js 20, and that is what engines in package.json says. The test runner wants a newer Node.js, so the development floor lives in devEngines in the same file. npm checks devEngines before install, run and test, so a clone on Node.js 20 stops with a clear message instead of a strange failure part way through the test suite. The 23 and 25 release lines are left out on purpose, because the test runner does not run on them.
Both numbers live in package.json, and a test in tests/node-version.test.ts keeps them in step with the README and with the range the test runner asks for.
Development
npm install
npm run build
npm testThe tests call every tool through a real MCP client and save to a temporary folder, so they need no account or network. They need the newer Node.js from the Node version section above, because of the test runner.
More free student MCP servers
All free, open source and read only where they touch your accounts. Browse the full list at brightspacemcp.com/more-mcps.
Server | What it does |
D2L Brightspace for AI. Due dates with real submission status, grades, a target grade calculator and course files. | |
Canvas LMS for AI, read only. Due dates, missing work, grades and announcements. | |
Moodle for AI, read only. Due dates, overdue work, grades and announcements. | |
Google Classroom for AI, read only. Todos, due dates, missing work and grades. | |
GPA, grade conversion and the grade you need on the final, for AI. Works offline, no account. | |
APA, MLA and Chicago citations from a DOI, an ISBN or typed details. No account. | |
Exam study schedules, spaced repetition dates, pomodoro plans and assignment milestones. Works offline. | |
Search scholarly papers, find open access copies and related work through OpenAlex. No key needed. | |
Clean, convert, dedupe and lint BibTeX, RIS and CSL JSON reference lists, and make cite keys. Works offline. | |
Find free legal copies of textbooks on OpenStax, DOAB and Open Library, look up editions by ISBN and suggest cheaper older ones. | |
Chemistry and physics homework math: molar mass, balancing equations, grams to moles, unit conversion and significant figures. Works offline. | |
Offline writing metrics for essays. Word and page counts, readability scores, passive voice, repeated openers, filler words, long sentences and word limit checks, so students can check their work against assignment requirements. No account, no network. | |
Syllabus to calendar MCP server. Extract dates from syllabus text, build an ics calendar, expand recurring classes and merge calendars. Works offline, no account. |
License
MIT
Available Tools
8 toolsadd_applicationAdd applicationA
Add a job or internship to the tracker. It starts in the applied stage unless you pass another status. Inputs: company and role (both required), an optional deadline as YYYY-MM-DD, an optional source such as LinkedIn or a career fair, an optional type of job or internship, an optional status and optional notes. The tool saves the application on this computer and returns its id, which update_status needs. If an application with the same company, role and deadline already exists, the new one is still saved and the result has a warning field. Example prompt: "Add a Software Intern role at Shopify with a deadline of 2026-11-15, found on LinkedIn."
Inputs: role (required), company (required), type, notes, +3 more. Returns: warning, application
delete_applicationDelete applicationADestructive
Remove an application from the tracker, for example a duplicate or a mistaken entry. Inputs: id of the application (from add_application or list_applications). The application is deleted from the local file and cannot be brought back, and the ids of the other applications do not change. Example prompt: "Delete application 3, it was a duplicate."
Inputs: id (required). Returns: deleted
export_reportExport reportARead-only
Export your applications as CSV or Markdown so you can share them or open them in a spreadsheet. Inputs: format, either csv or markdown (default markdown), and an optional status to export only that stage. The report is returned as text and nothing is written to disk. In CSV, a cell that starts with =, +, - or @ gets a leading apostrophe so spreadsheets do not run it as a formula. Example prompt: "Export all my applications as a CSV."
Inputs: format, status. Returns: count, format, content
import_applicationsImport applicationsA
Add many applications at once from CSV text, for example a list you kept in a spreadsheet. Inputs: csv, the text of the file with a header row. The columns company and role are required; type, status, deadline, interview_date, source and notes are optional, and other columns such as id are ignored. The CSV from export_report works as is. Each valid row is saved as a new application with a new id. A row with a blank company or role, an unknown type or status, or a bad date is skipped and listed with its row number. A row that matches an existing application by company, role and deadline is still saved and gets a warning. Example prompt: "Import these applications from my spreadsheet: company,role,deadline ..."
Inputs: csv (required). Returns: skipped, imported, warnings, applications
list_applicationsList applicationsARead-only
List applications with optional status and company filters, an optional text query and an optional deadline range. Inputs: optional status to filter by stage, an optional company substring to match (case insensitive), an optional query that searches the role, notes and source text (case insensitive), for example referral or LinkedIn, and optional deadline_after and deadline_before as YYYY-MM-DD. Both dates are included, and applications without a deadline are left out when you pass either one. An optional sort orders the list by deadline (nearest first, applications without a deadline last), company (A to Z) or id (the default). Returns all matching applications as a structured list with their ids, so you can see application ids without exporting a full report, plus summary_counts with how many of them are in each stage. Example prompt: "Show my applications by nearest deadline."
Inputs: sort, query, status, company, +2 more. Returns: count, applications, summary_counts
list_upcomingList upcomingARead-only
Show upcoming deadlines and interviews sorted by date, with a reminder for each one. Deadlines come from applications still in the applied stage, and interviews come from applications in the interview stage that have an interview_date. Rejected applications and offers are left out. Inputs: optional days, how far ahead to look (default 14), include_overdue (default true) to also show deadlines that already passed, and an optional today as YYYY-MM-DD to ask as if it were another day. Example prompt: "What deadlines and interviews do I have in the next two weeks?"
Inputs: days, today, include_overdue. Returns: items, today
update_applicationUpdate applicationA
Update the deadline, notes, role, company, type, source or interview date of an existing application. Inputs: id of the application (from add_application or list_applications), and any of company, role, deadline as YYYY-MM-DD, notes, type (job or internship), source and interview_date as YYYY-MM-DD or YYYY-MM-DDTHH:MM. Only the fields you pass are changed; the rest stay the same. Pass an empty deadline, source or interview_date to clear it. Example prompt: "Update application 1 to set the deadline to 2026-11-20 and add a note about the referral."
Inputs: id (required), role, type, notes, +4 more. Returns: application
update_statusUpdate statusA
Move an application to another stage: applied, interview, offer or rejected. Inputs: id of the application (from add_application or list_applications), the new status, an optional interview_date as YYYY-MM-DD or YYYY-MM-DDTHH:MM, and an optional note that is added to the notes. When the status is interview, pass interview_date so list_upcoming can remind you. Example prompt: "Move application 1 to interview on 2026-11-20 at 14:30."
Inputs: id (required), status (required), note, interview_date. Returns: application, previous_status
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool maps to a distinct resource+action (add, import, export, delete, list, upcoming), so most are easy to tell apart. The only mild overlap is update_status vs update_application, which touch related fields (interview_date appears in both) and require two calls to change status plus other fields, but the descriptions clarify the boundary.
All tools follow a consistent verb_noun snake_case pattern: add_, import_, export_, update_, delete_, list_. update_status and update_application both use the update_ prefix predictably, and there is no style mixing.
Eight tools is well-scoped for a job application tracker, with each tool earning its place (create, bulk import, export, delete, list, upcoming reminders, and two update variants). No redundant or filler tools.
The CRUD lifecycle is well covered: add/import for creation, update_application and update_status for edits, delete_application, list_applications with rich filtering, plus export_report and list_upcoming. Minor gaps like fetching a single application by id exist but are workable via list_applications filters.
Maintenance
Related MCP Connectors
Track job applications: find the ones to follow up on, add jobs, update status, notes and steps.
Job search tracker for Claude and ChatGPT: applications, interviews, follow-ups, company watch.
Track job applications on a board: let Claude or ChatGPT read and update jobs, interviews, notes.
Analyze job listings against your resume, track applications, and generate cover letters.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceManages job applications, companies, roles, statuses, deadlines, and reminders through natural language queries.-
- AlicenseAqualityDmaintenanceA privacy-first MCP server for locally managing job, fellowship, and graduate-school applications. It offers tools for tracking application status, analyzing role fit, generating LaTeX CV/cover letters, interview prep, and discovering public jobs from ATS APIs.81MIT
- AlicenseNot gradedqualityCmaintenanceEnables tracking of job applications and freelance leads through an MCP interface, with tools to add and update items, list and summarize the pipeline, flag stale entries, and draft follow-up messages grounded in each item's logged notes using locally stored JSON data.MIT
- AlicenseAqualityCmaintenanceEnables Claude to organize a job search by registering openings, advancing applications through a status funnel, measuring conversion rates between stages, and flagging applications that have gone quiet and need follow-up. Data is kept locally in SQLite, so no external account or server is required.5MIT