A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Career Compass is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
332
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
AI-native career co-pilot for Claude — Career KB, resume tailoring, job pipeline, interview prep, and offer evaluation via MCP
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user career-compass-mcp '--' npx -y career-compass-mcp
# 2 — ask your agent for something these tools do
# explore_opportunity, research_company, tailor_resume and 16 more
Career Compass costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Career Compass as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user career-compass-mcp '--' npx -y career-compass-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Judge how well the user fits one job posting, using their saved Career KB and stated preferences (salary floor, remote or relocation, notice period). Returns a verdict (Strong fit, Stretch, or Long shot) with a score, requirement-by-requirement evidence, the top gaps and how to address them, and…
No parameter schema on file.
Set up a research brief on a company the user is applying to or interviewing with: what it does, stage, culture, interview process, and how it fits the user's target roles. The server does not browse; it returns the brief's outline plus the user's targets, and you fill it from web search when you…
No parameter schema on file.
Write a résumé tailored to one job posting from the user's saved Career KB: the posting's vocabulary, the most relevant real achievements first, nothing invented, and [confirm: ...] placeholders where a fact is missing. Returns the résumé text first, then a keyword match report. Use it when the…
No parameter schema on file.
Draft a cover letter in the user's voice from their saved Career KB, built on real achievements that match the role and quoting their saved narrative (why they're looking, a gap, a switch) word for word. Use it when the user asks for a letter. Works from a pasted posting, from an application…
No parameter schema on file.
Answer the questions on a job application form (why this company, years of experience with X, work authorization, salary expectation, start date, short essays) from the user's saved Career KB, each within its character or word limit. Eligibility answers come only from what the user saved or said;…
No parameter schema on file.
Reformat résumé text the user already has into clean, parse-safe plain text for an applicant tracking system (Workday, Greenhouse, Lever, LinkedIn, iCIMS, Taleo, SmartRecruiters, or generic): standard headings, consistent dates, sections ready to paste field by field, and long sections flagged…
No parameter schema on file.
Read the job application pipeline. action "next_actions" answers "what should I work on?" with a ranked digest led by one start-here move; "list" shows applications (filter by status or priority); "stats" gives funnel and response rates, plus any pattern the user's own numbers support; "get"…
No parameter schema on file.
Add one job application to the pipeline. Writes one new record; never modifies an existing one. If the same company and role are already tracked, it writes nothing and returns the existing id instead (use pipeline_update to change that one). Use this when the user applies to, or wants to track, a…
No parameter schema on file.
Update one application already in the pipeline: change its status, add a note, set a follow-up date, record a contact, log an interview round and its outcome, record an offer and its answer deadline, or note which résumé version was sent. Writes: overwrites the fields you supply and leaves the…
No parameter schema on file.
Read a job-search email the user pasted (recruiter outreach, interview invite, assessment, rejection, offer) and extract its type, company, role, contact, dates, urgency, and next action, matched against applications already in the pipeline, with a short reply draft. Writes nothing: any pipeline…
No parameter schema on file.
Prep the user for one upcoming interview: an opening pitch, STAR stories (saved ones from their story bank first, skipping any this company or interviewer already heard), likely questions for that round, questions to ask, and the concerns to get ahead of, quoting their saved narrative where it…
No parameter schema on file.
For a user already partway through one company's interviews: reconstruct the process so far (rounds done, what each surfaced, threads left open, which saved stories each round already heard) from the pipeline, the journal, the story bank, and their notes, then project what the next round will…
No parameter schema on file.
Analyze a job offer the user has received: total compensation year one and fully vested, how it compares to their current pay, stated targets, other offers (including live offers already recorded in their pipeline, side by side), and any market data they supply, then what to negotiate and the…
No parameter schema on file.
Extract achievements, skills, and quotes from a career document the user pasted (performance review, award email, project summary, recommendation) as Career KB YAML for them to review, copying only what the document states and marking missing metrics [confirm: ...]. Extraction only: writing the…
No parameter schema on file.
Draft a short reply to a rejection the user received: keep the door open, ask for feedback, or decline politely, plus an alternative and a LinkedIn note. If you pass applicationId, this also sets that application's status to rejected in your pipeline — it does not only write a draft. Leave…
No parameter schema on file.
Append one lasting takeaway to the user's career journal: what an interview surfaced, why an offer felt right or wrong, the pattern behind a rejection, or fresh proof of a skill. Later fit checks, interview prep, and résumés read these back. Writes one new entry and never changes existing ones.…
No parameter schema on file.
Write one section of the Career KB to disk. This is how the Career KB gets populated — ingest_document and the resume tools only read and extract. Replaces the whole section, so send the complete list you want stored, not just new entries. A save that would drop stored entries or achievements is…
No parameter schema on file.
Read a local project's git history and report what you measurably did there — months active, files and file types touched, your share of commits, test ratio — each with the command that produced it. Use it when the user cannot remember what they shipped, is writing a résumé bullet for a project,…
No parameter schema on file.
Health-check this Career Compass install and report everything at once: how it is running (plugin or standalone) and its version, whether a newer version has shipped, whether your data directory exists and is writable, which Career KB sections are filled in, the recent backups of each section with…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Career Compass or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 2.13.1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings5 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest0eb6bf6c542b6bcf66b1e14d15b1f572ff7240ba8af4ef8bb12788ff97311302
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| ingest_document | no tags | |
| generate_rejection_response | no tags | |
| capture_insight | no tags | |
| save_career_section | no tags | |
| check_setup | no tags | |
| harvest_evidence | no tags | |
| prepare_interview | no tags | |
| interview_arc | no tags | |
| evaluate_offer | no tags | |
| explore_opportunity | no tags | |
| research_company | untrusted-input | untrusted-input: keyword "web_search" |
| pipeline_view | no tags | |
| pipeline_add | no tags | |
| pipeline_update | no tags | |
| classify_email | no tags | |
| tailor_resume | no tags | |
| generate_cover_letter | no tags | |
| answer_application | no tags | |
| format_for_ats | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest0eb6bf6c542b6bcf
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.13.1. Pin a release below and the command asks for exactly that one.
2.13.1
14 Oct 2026
latestNo release note was published with this version.
2.11.2
10 Oct 2026
No release note was published with this version.
2.11.1
9 Oct 2026
No release note was published with this version.
2.9.9
7 Oct 2026
No release note was published with this version.
2.9.6
5 Oct 2026
No release note was published with this version.
2.9.5
4 Oct 2026
No release note was published with this version.
2.9.4
3 Oct 2026
No release note was published with this version.
2.9.3
26 Sep 2026
No release note was published with this version.
2.9.2
16 Sep 2026
No release note was published with this version.
2.9.1
6 Sep 2026
No release note was published with this version.
2.6.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Career Compass can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.