Application Tracker MCP
Fetches job postings from public Greenhouse job boards, optionally filtered by location, to support application tracking and analysis.
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., "@Application Tracker MCP Save this job description and create a new application for it."
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.
Application Tracker MCP
A privacy-first Model Context Protocol server for managing job, fellowship, and graduate-school applications locally.
It gives an MCP client a durable local workspace for:
saving a job description and application status;
comparing a private factual profile to a role without inventing experience;
creating editable LaTeX CV and cover-letter starters;
producing an interview-prep scaffold;
discovering roles from opt-in public Greenhouse, Lever, and Ashby job-board APIs.
It does not submit applications, scrape logged-in sites, bypass CAPTCHAs/rate limits, or send data to a hosted service.
Why an MCP server?
An LLM is useful for interpreting a job description and drafting language. It should not be the database of record or silently decide facts about a candidate. This server keeps the repeatable operations local and explicit:
Private profile + job description
↓
MCP tools: save / analyse / scaffold / track
↓
Agent drafts wording from factual evidence
↓
Human reviews, edits, and submitsThe server owns tracking and document scaffolding. The MCP client owns conversational reasoning. The user owns the final claims and submission.
Related MCP server: jobjourney-claude-plugin
Privacy model
The public repository contains no applicant data. It includes only fictional examples.
Configure
APPLICATION_TRACKER_ROOTto a private local directory.Keep profiles, real application records, PDFs, job descriptions, and notes outside the repository or in ignored directories.
The server accepts only paths relative to
APPLICATION_TRACKER_ROOT; it rejects absolute paths and path traversal.Do not commit the configured data workspace. The included
.gitignoreignoresdata/,applications/,private/, PDFs, and LaTeX build output.
Read SECURITY.md before using the server with sensitive information.
Quick start
Requires Python 3.10+ and the official Python MCP SDK.
git clone https://github.com/YOUR_GITHUB_USERNAME/application-tracker-mcp.git
cd application-tracker-mcp
python -m venv .venv
. .venv/bin/activate
pip install -e .
# Pick a private directory that is NOT inside the Git checkout.
export APPLICATION_TRACKER_ROOT="$HOME/.local/share/application-tracker"
application-tracker-mcpThe server uses MCP's standard stdio transport. The client launches it as a subprocess and communicates using JSON-RPC over standard input/output. See the MCP transport specification.
Example client configuration
Use a client configuration equivalent to the following (adapt the absolute paths):
{
"mcpServers": {
"application-tracker": {
"command": "/absolute/path/to/application-tracker-mcp/.venv/bin/application-tracker-mcp",
"env": {
"APPLICATION_TRACKER_ROOT": "/absolute/private/path/application-tracker-data"
}
}
}
}MCP tools
Tool | Purpose |
| Saves a private application record and its job description. |
| Lists records, optionally by status. |
| Tracks drafting, applied, interview, offer, rejected, and closed states. |
| Matches only declared private profile skills/evidence against the saved JD. |
| Writes editable LaTeX CV and cover-letter starters plus a tailoring brief. |
| Creates a factual interview-practice scaffold. |
| Runs Tectonic on a generated |
| Fetches roles from public Greenhouse, Lever, or Ashby APIs. |
Example workflow
Copy the fictional profile example into your private data workspace and replace it with your own verified facts.
Ask an MCP client to call
create_applicationwith the job description.Call
analyse_application_fitwith a relative profile path such asprivate/profile.json.Ask the agent to write a factual tailoring brief using the returned evidence.
Call
render_application_draftsto create local, editable.texfiles.Review and edit the files. If Tectonic is installed, call
compile_application_tex.Use
update_application_statusas the process progresses.Before an interview, call
create_interview_prepwith only truthful highlights.
The examples/ directory is documentation only. It is deliberately fictional and does not demonstrate a real applicant.
Public job discovery
The repository has a small safe subset of the larger job-discovery concept. It supports only public APIs:
discover_public_jobs(provider="greenhouse", board="example-board", location_contains="Berlin")
discover_public_jobs(provider="lever", board="example-company")
discover_public_jobs(provider="ashby", board="example-company")It intentionally does not scrape LinkedIn, StepStone, Xing, authenticated pages, or sites with CAPTCHAs. It does not apply to jobs.
LaTeX notes
render_application_drafts creates generic, editable LaTeX starters. The server never writes a real applicant's data into this repository; it only writes into your private workspace at runtime.
If Tectonic is on PATH, compile_application_tex can compile an artifact safely using argument lists, not a shell. Otherwise, compile the .tex file with your preferred local LaTeX workflow.
Development
python -m unittest discover -s tests -v
python -m compileall src testsThe server targets the official Python MCP SDK v2 (mcp>=2,<3), whose high-level server class is MCPServer. SDK migration notes
Project status
This is an early local-first foundation. Good next additions are encrypted-at-rest user storage, a richer document-template system, more public ATS connectors, and client-specific installation guides.
Available Tools
8 toolsanalyse_application_fitA
Compare a private JSON profile to the saved job description without inventing claims.
Inputs: application_id (required), profile_json_path (required).
compile_application_texB
Compile a generated local .tex artifact with Tectonic; no shell command is used.
Inputs: tex_filename (required), application_id (required).
create_applicationA
Create a private application record and save its job description locally.
Inputs: company (required), role_title (required), job_description (required), tags, +3 more.
create_interview_prepA
Create a private interview-preparation scaffold from factual highlights.
Inputs: application_id (required), factual_highlights (required).
discover_public_jobsA
Discover listed jobs from a public Greenhouse, Lever, or Ashby API board.
This does not log in, bypass restrictions, scrape LinkedIn, or auto-apply.
Inputs: board (required), provider (required), limit, location_contains. Returns: result
list_applicationsA
List private application records, optionally filtered by their status.
Inputs: status. Returns: result
render_application_draftsC
Write editable LaTeX CV/cover-letter starters and a factual tailoring brief locally.
Inputs: application_id (required), tailoring_brief (required), profile_json_path (required).
update_application_statusC
Update one application status and optional private notes.
Inputs: status (required), application_id (required), notes.
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 targets a distinct action and resource: create/list/update applications, analyse fit, render drafts, create interview prep, compile TeX, and discover jobs. There is no overlap or ambiguity between tool purposes.
All tools follow a consistent verb_noun snake_case pattern (create_application, list_applications, update_application_status, analyse_application_fit, etc.). The only minor deviation is the British spelling 'analyse' vs 'analyze', but the pattern is uniform.
Eight tools is well within the ideal 3-15 range and each tool serves a clearly defined function in the application tracking workflow. The count feels appropriate for the domain and not excessive or thin.
The toolset covers the core lifecycle: create, list, update, analyse, render, compile, and prepare for interviews. A delete application tool is missing, and there is no explicit single-application getter, but list_applications can serve that need, so the gaps are minor.
Related MCP Connectors
Public MCP server for discovering open jobs. Search, filter, and get application links.
Job application tracker for developers - AI agents write over MCP, you review in a dashboard.
Analyze job listings against your resume, track applications, and generate cover letters.
GetJobzi MCP server for job search, application tracking, and career forecasting.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn intelligent, zero-cost MCP server that securely parses local resumes and compares them against live job postings for ATS scoring, skill gap analysis, and interview prep.MIT
- AlicenseCqualityCmaintenanceAn MCP server that enables AI-assisted job search workflows including job discovery, application tracking, resume evaluation, and cover letter generation, with support for multiple job sources and scheduled scraping.8356 npm1AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceA local-first, open-source MCP server that analyzes jobs, matches your CV, tailors documents, and tracks applications — all on your machine with no data uploaded.AGPL 3.0
- AlicenseAqualityBmaintenanceLocal MCP server that manages a job search using Markdown files, enabling skills tracking, gap analysis, and offer pipeline management via Claude.866 npmMIT