career-compass-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y career-compass-mcp@2.16.1
Installing a package runs its code. Use a sandbox for anything you have not read.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
explore_opportunity posting, company, role, notes, sourceFitLabel, resume
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 talking points; if the user pastes the job board's own match label, it agrees or disagrees with it explicitly. Use it whenever the user pastes a posting and asks whether to apply. Before anything is saved, pass the résumé they pasted as `resume` and the verdict works from that. Writes nothing.
research_company company, role, applicationId
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 have it, citing sources. Without web search, the brief becomes a checklist of what to look up and where. Use explore_opportunity instead to judge fit for a specific posting.
tailor_resume posting, format, pages, includeProjects, focusAreas, company, resume
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 user wants a résumé for a specific posting. Before anything is saved, pass the résumé they pasted as `resume` and it tailors from that. Use format_for_ats afterwards for a specific applicant system's fields. Writes nothing.
generate_cover_letter posting, company, role, applicationId, hiringManager, tone, angle, resume
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 already in the pipeline (its cached posting, role, and notes), or from just a company and role. Company claims come only from the posting or the user. Before anything is saved, pass the résumé they pasted as `resume`. Writes nothing.
answer_application questions, company, role, posting, resume
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; anything else is a [confirm: ...] placeholder, and a "years with X" the history can't support is flagged, never inflated. Use it whenever the user pastes application or screening questions. Before anything is saved, pass the résumé they pasted as `resume`. Writes nothing.
14 more tools
format_for_ats resumeContent, targetSystem, postingUrl
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 (limits vary by employer). Use it when the user is about to paste a résumé into an application form. Reformats only, never rewrites content; use tailor_resume to change what the résumé says. Writes nothing.
pipeline_view action, id, filterStatus, filterPriority, sortBy, limit
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" fetches one application by id; "calendar" returns upcoming interviews, follow-up dates and offer deadlines as .ics text for the user to save and open in their calendar. Read-only: never modifies anything, and the .ics is returned, not written.
pipeline_add company, role, status, postingUrl, postingText, source, referral, priority, excitement, salaryMin, salaryMax, dateApplied, allowDuplicate
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 role not yet on the board. On the very first application, the result carries Career Compass's one-time offer of a morning briefing; pass it on as one optional line.
pipeline_update id, status, priority, notes, followUpDue, contactName, contactTitle, contactEmail, interviewType, interviewDate, interviewers, roundOutcome, offerBaseSalary, offerBonus, offerEquity, offerCurrency, offerStartDate, offerExpiresDate, offerNotes, tailoredResumeVersion
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 rest untouched. Use after the user confirms the change.
classify_email emailContent, autoUpdatePipeline
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 change it suggests goes through pipeline_update after the user agrees.
prepare_interview applicationId, company, role, interviewType, interviewerInfo, postingText, focusAreas, resume
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 applies. Finds the application by id or company name and uses its posting, rounds, and contacts. For a later round in a process already under way, call interview_arc too so the prep doesn't repeat ground covered. Before anything is saved, pass the résumé they pasted as `resume`. Writes nothing.
interview_arc applicationId, company, role, interviewSoFarNotes, nextRoundType
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 probe and how to prepare without repeating covered ground. Use prepare_interview instead for a first interview. Writes nothing.
evaluate_offer applicationId, company, role, offerDetails, location, currentComp, marketData, priorities, otherOffers
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 exact words. Use it when the user has an offer in hand. Benchmarks come only from data the user gives; the server never fetches salary data. Writes nothing; it ends by offering to record the offer and its deadline with pipeline_update, for the user's OK.
ingest_document content, documentType, associatedRole, associatedCompany, datePeriod
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 reviewed YAML is a separate, explicit save_career_section call.
generate_rejection_response applicationId, company, role, rejectionContent, responseGoal, contactName, hadGoodRapport
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 applicationId out when the user only wants the words.
capture_insight type, summary, detail, applicationId, company, role, signals, sentiment, source, origin
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. Offer it after a debrief, a rejection, or an offer decision, and save only with the user's OK. Set origin to user_said for what they said, or inferred for your own reading, which drafts then treat as a hypothesis.
save_career_section section, data, restoreFrom, replace
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 refused and names them, unless `replace` is true. The previous version is kept as a timestamped .bak next to it. To undo a bad save, pass `restoreFrom` with a backup name that check_setup lists instead of `data`: the current file is backed up first, then that backup is put back. Writes to disk either way; use it only with the user's OK.
harvest_evidence projectPath, since, authorEmail
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, or needs proof of a skill. It reports counts and asks the questions a commit log cannot answer; it never invents achievements and never writes to the Career KB.
check_setup dashboardPort
Health-check this Career Compass install and report everything at once: how it is running (plugin or standalone) and its version, whether your data directory exists and is writable, which Career KB sections are filled in, the recent backups of each section with how to restore one, whether the pipeline file parses, leftover temp files, and whether the dashboard is running. Every finding that needs action comes with the one step that fixes it. Run it when something seems wrong, when the user asks whether it's working, or to find a backup to restore; not on first contact. Writes nothing.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=22.0.0 |
| Source | github.com/benskamps/career-compass-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-iV0eUqVbCVp/k9mKGrzjrNey00vEBMQjbczZrPLT1vO39pgUktJQ1KEVf10zA+n+gnJbo/4KRdDfHOadKNeohw== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/career-compass-mcp)
New version out? Ask for a fresh report.