jobfinder-mcp
Allows opening tailored LaTeX resumes in Overleaf by submitting the resume as a data URI, enabling PDF compilation without a local LaTeX installation.
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., "@jobfinder-mcp search for remote Python developer jobs"
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.
jobfinder-mcp
A local MCP server for searching job listings and tracking applications. Runs entirely on your machine over stdio; saved jobs live in a local SQLite file.
Install
python3 -m venv .venv
.venv/bin/pip install -e .Requires Python 3.10+. The SDK is pinned to mcp>=1.2,<2: mcp 2.x removed
mcp.server.fastmcp, which this server is built on.
Related MCP server: Job Board MCP Server
Run
.venv/bin/jobfinder-mcp # or: .venv/bin/python -m jobfinder_mcpThe server speaks MCP over stdio, so running it by hand just blocks waiting for a client. To inspect it interactively:
.venv/bin/mcp dev src/jobfinder_mcp/server.pyWeb UI
.venv/bin/jobfinder-web # http://127.0.0.1:8765, opens a browser
.venv/bin/jobfinder-web --port 0 --no-browserTwo panes: tracked jobs on the left (search box, status filters, a badge showing
the tailored resume's file type), the selected job on the right with tabs for the
full Description and its Tailored resume — copy it, download the file, or
take it as a self-contained data:application/x-tex;base64,… link (shown under
the buttons, with copy data URI next to it). The whole document lives inside
that link, so it can be pasted anywhere and downloaded with this server stopped.
For .tex output there is also Open in Overleaf, which POSTs that data URI to
overleaf.com/docs as snip_uri and opens the compiled CV in a new tab — the way
to get a PDF without a local TeX install. It uploads the resume to Overleaf, so it
only fires when you click it. Note that Chrome refuses data: URIs typed into the
address bar; only the in-page controls work.
The status dropdown writes straight back to the tracker, so the MCP tools and the
UI stay in sync; hit refresh after Claude saves something new.
It reads the same SQLite file and tailored directory as the MCP server, and binds
to loopback only — it serves your resume and application notes, so do not expose
it on a LAN interface. The MCP tool open_web_ui(port) starts the same UI on a
background thread inside the running server.
Register with Claude Code
claude mcp add jobfinder -- /Users/juansalzar/Documents/git/jobfinder/.venv/bin/jobfinder-mcpOr add it to ~/.claude.json / .mcp.json manually:
{
"mcpServers": {
"jobfinder": {
"command": "/Users/juansalzar/Documents/git/jobfinder/.venv/bin/jobfinder-mcp"
}
}
}For Claude Desktop, the same block goes in
~/Library/Application Support/Claude/claude_desktop_config.json.
Tools
Tool | Purpose |
| Search listings across all sources, ranked by where the terms hit |
| Full listing text for an id from a search or the tracker |
| Save a listing from the last search into the tracker |
| Add a job found elsewhere by pasting its details |
| Replace a saved job's description with pasted text |
| List tracked jobs, newest first |
| Move a job through the pipeline |
| Remove a tracked job |
| Counts by status |
| Store a resume from pasted text or a |
| Stored resumes, with the default marked |
| Show a resume; |
| Pick the resume used when a call names none |
| Remove a resume and its original file |
| Build the tailoring brief for a job |
| Store the tailored CV as LaTeX |
| Read back the tailored CV |
| The tailored CV as a base64 |
| Every tailored CV written so far |
| Start the local browser UI and return its URL |
Resource jobfinder://saved returns every tracked job as JSON.
Prompt tailor_application(job_id, resume_summary) drafts a cover letter; with no
resume_summary it uses the default stored resume.
Statuses: saved, applied, interviewing, offer, rejected, archived.
Tailoring a resume
The server does not call an LLM. tailor_resume returns a brief — the listing's
must-have terms, its most frequent terms, and which of them the resume already
evidences — and the model driving the client writes the CV from it. Nothing is
sent anywhere, and there is no API key or per-call cost.
add_resume(name="main", path="~/Documents/cv.pdf")
search_jobs(query="python backend", location="remote")
save_job(job_id="remoteok:123456")
tailor_resume(job_id="remoteok:123456") # -> brief; the model writes the CV
save_tailored_resume(job_id="remoteok:123456", content="\\documentclass...")PDF, DOCX and LaTeX files are converted to text for matching, and the original is
kept next to it. A scanned, image-only PDF extracts to nothing; paste the text
with add_resume(name, text=...) instead.
LaTeX output
Tailored resumes are always written as .tex. tailor_resume ends its brief
with the LaTeX to write into:
the stored resume is a
.texfile → its source is included, to be rewritten in place with the preamble, macros and layout left alone;otherwise → a plain
article-class template is included for the model to fill.
save_tailored_resume rejects content with no \documentclass or
\begin{document}; pass an explicit extension to store another format anyway.
There is no LaTeX toolchain in this project — compile the result with
pdflatex/tectonic, or upload it to Overleaf.
To use your own layout instead of the built-in template, drop a .tex file at
~/.jobfinder/resume_template.tex or point JOBFINDER_LATEX_TEMPLATE at one.
Term matching is deterministic string work: known multi-word phrases plus
non-stopword tokens, normalized through an alias table so k8s in a listing
matches Kubernetes in a resume. It surfaces gaps; it does not judge fit.
Sources
remoteok — RemoteOK's public JSON feed. No API key. Cached 15 minutes.
local — set
JOBFINDER_FEED=/path/to/jobs.jsonto read your own listings. The file is a JSON list of objects with at leastid,titleandcompany;location,url,salary,tags,descriptionare optional.
Add another source by writing a fetch_* function in sources.py that returns
normalized job dicts, then registering it in the SOURCES map.
Configuration
Env var | Default | Meaning |
|
| SQLite file for saved jobs |
| unset | JSON file for the |
|
| Base directory for resumes and tailored output |
|
| Where stored resumes live |
|
| Where tailored resumes are written |
| built-in template |
|
Available Tools
20 toolsadd_jobA
Add a job you found elsewhere (LinkedIn, a referral, an email) to the tracker.
Use this to paste a full job description for a listing that did not come from search_jobs. Reusing an existing job_id overwrites that listing's fields while keeping its application status.
Args: title: role title. company: hiring company. description: full job description text. location: e.g. "Remote", "Berlin". url: link to the original posting. salary: free-form, e.g. "$150,000 - $180,000". tags: comma-separated, e.g. "python, backend". notes: your own notes about the role. job_id: optional explicit id; defaults to a generated "manual:" id.
Inputs: title (required), company (required), url, tags, +5 more. Returns: result
add_resumeA
Store a resume so it can be tailored against job listings.
Give either text (pasted resume) or path (a file to read). Accepted
files: .md, .txt, .pdf, .docx, .tex. Non-text files are converted to text
for matching and the original is kept so a rewrite can stay in that format.
Re-using a name replaces that resume.
Args: name: label for this resume, e.g. "main" or "backend". text: full resume text, if pasting. path: path to a resume file, if uploading.
Inputs: name, path, text. Returns: result
delete_resumeA
Delete a stored resume and its original file.
Inputs: name (required). Returns: result
delete_saved_jobB
Remove a job from the local tracker.
Inputs: job_id (required). Returns: result
get_job_detailsA
Show the full listing for a job id returned by search_jobs or list_saved_jobs.
Inputs: job_id (required). Returns: result
get_resumeB
Show a stored resume. raw returns the original LaTeX source when there is one.
Inputs: raw, name. Returns: result
get_tailored_resumeB
Return the tailored resume stored for a job.
Inputs: job_id (required). Returns: result
list_resumesA
List stored resumes, marking which one is used when none is named.
Inputs: no named parameters. Returns: result
list_saved_jobsA
List saved jobs, newest first, optionally filtered by application status.
Inputs: limit, status. Returns: result
list_tailored_resumesA
List every tailored resume written so far.
Inputs: no named parameters. Returns: result
open_web_uiA
Start the local web UI for browsing saved jobs and their tailored resumes.
Runs on a background thread inside this server, on 127.0.0.1 only, and stops when the MCP client disconnects. Calling it again returns the running URL.
Inputs: port. Returns: result
pipeline_summaryA
Count saved jobs by application status.
Inputs: no named parameters. Returns: result
save_jobB
Save a job from the latest search results to the local tracker.
Inputs: job_id (required), notes. Returns: result
save_tailored_resumeA
Store a tailored resume for a job as LaTeX. Replaces any previous version for that job.
Args: job_id: the job this version targets. content: the full tailored resume, a complete LaTeX document. extension: output file type; leave as "tex" unless you have a reason not to.
Inputs: job_id (required), content (required), extension. Returns: result
search_jobsA
Search job listings.
Args: query: keywords matched against title, tags, company and description. location: substring filter on the listing location (e.g. "remote", "berlin"). tags: comma-separated tags that must all be present on the listing. source: restrict to one source ("remoteok" or "local"); empty means all. limit: maximum listings to return.
Inputs: tags, limit, query, source, +1 more. Returns: result
set_default_resumeA
Choose which resume is used when a tailoring call does not name one.
Inputs: name (required). Returns: result
set_job_descriptionA
Replace the description of a saved job with pasted text.
Useful when the listing was saved from a feed with a truncated or empty description and you have the full text.
Inputs: job_id (required), description (required). Returns: result
tailored_resume_linkA
Return the tailored resume for a job as a base64 data: URI.
The whole document travels inside the link, so it can be pasted anywhere that renders a URL and downloaded without this server running.
Inputs: job_id (required). Returns: result
tailor_resumeA
Build a tailoring brief: the listing's requirements matched against a stored resume.
Returns the job's must-have and frequent terms split into what the resume already evidences and what it does not, then the resume text, then the LaTeX to write into. Tailored output is always LaTeX: when the stored resume is a .tex file its source is included to rewrite in place, otherwise a template is included to fill. Write the CV, then store it with save_tailored_resume.
Args: job_id: id from search_jobs, add_job or list_saved_jobs. resume: stored resume name; empty uses the default resume.
Inputs: job_id (required), resume. Returns: result
update_job_statusA
Update the application status and/or notes of a saved job.
Valid statuses: saved, applied, interviewing, offer, rejected, archived.
Inputs: job_id (required), notes, status. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Most tools have distinct purposes, but save_job and add_job both create a saved job, which could cause confusion. The descriptions clarify the source, so an agent can differentiate with careful reading.
Most tools follow verb_noun naming (search_jobs, get_job_details, save_job). However, pipeline_summary and tailored_resume_link are noun-phrase names, breaking the pattern slightly.
At 20 tools, this is on the heavier side. The dual purpose (job tracking and resume tailoring) justifies many tools, but it borders on overwhelming for an agent.
The job lifecycle (search, save, update, delete, summaries) and resume tailoring workflow (add, tailor, save, retrieve) are well covered. Missing a dedicated delete for tailored resumes is a minor gap.
Maintenance
Related MCP Connectors
Search jobs, prepare resumes and cover letters, retrieve PDFs, and track your applications.
Public MCP server for discovering open jobs. Search, filter, and get application links.
GetJobzi MCP server for job search, application tracking, and career forecasting.
Analyze job listings against your resume, track applications, and generate cover letters.
Related MCP Servers
- FlicenseAqualityDmaintenanceA local job-hunting MCP server for discovering jobs across pluggable web sources, tracking applications through a status lifecycle, and managing profiles/resumes, with geo/map-region search.12-
- AlicenseAqualityBmaintenanceEnables searching and retrieving job listings from multiple platforms through MCP.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables an MCP-capable coding agent to run a local-first job search: recording verified opportunities in a private SQLite tracker, tracking follow-ups and outcomes, and preparing evidence-based resumes, application answers, and outreach drafts. It keeps all personal data on the user's machine and stops before submitting applications, uploading documents, or contacting anyone.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables any MCP-capable AI app to act as a personal job-search assistant by storing resumes and job postings, matching skills, tracking applications, and analyzing market skill demand.MIT