MCP.Market

HR MCP server

by Autostackup·io.github.Autostackup/hr·v0.1.1
No reviews yet

Candidate screening, offer letters, onboarding, interview kits & performance reviews for Claude.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

0 stars28 downloads/wk

Reviews

Write one

Nobody has reviewed HR yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

HR tools (5, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • build_interview_kit

    Generate a complete interview kit for any role — structured questions by competency, STAR follow-up probes, 'what good looks like' benchmarks, red flags, a scorecard template, legal reminders, and a debrief guide. Covers screening, technical, behavioural, case, panel, and final interviews.

  • create_onboarding_planwrite action

    Build a complete 30/60/90-day onboarding plan for a new hire. Includes Day 1 checklist, weekly themes, milestone goals, manager action list, red flag warnings, and a success definition. Adapts for IC, manager, and executive roles.

  • draft_offer_letter

    Generate a professional, ready-to-send offer letter with compensation summary, equity and bonus clauses, expiry date, negotiation notes, and a follow-up call script. Supports formal, warm, and startup tones.

  • screen_candidate

    Score a candidate against a job's required skills, experience, and must-haves. Returns a tier (A/B/C/D), skill gap analysis, salary fit, and exact recommended next step. Built on structured competency scoring used by top People teams.

  • write_performance_reviewwrite action

    Write a structured performance review with achievements narrative, development sections, next-period goals, compensation recommendation, and a manager meeting guide. Adapts to exceeds/meets/partially meets/does not meet ratings and supports coaching, direct, and formal tones.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan25 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 111 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How HR compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
5
the typical server has 7
Tools that change things
40%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
28
more than 15% of 12,191 servers with a package

What its tools let an agent do: 3 read · 2 create

Install HR in Claude Code, Cursor or VS Code

Runs npx -y @autostackup/hr on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add hr -- npx -y @autostackup/hr
Add to Cursor

What the publisher says

From the HR repository's README, as published. We do not edit it. Read it on GitHub

Autostackup MCP Suite

The AI operating system for founders — plug Claude directly into your sales pipeline, marketing strategy, and business operations. No new apps. No new dashboards. Just ask Claude and get expert-grade output instantly.

What is this?

Most MCP servers connect Claude to APIs — they let you read and write data. Autostackup does something different: it gives Claude business intelligence frameworks — the strategic thinking tools that consultants, growth teams, and sales leaders use every day.

Ask Claude to qualify a lead using BANT and MEDDIC. Ask it to build a full IMC campaign across Meta and Google. Ask it to audit your marketing strategy against Kotler's 9-element framework. It does it — structured, scored, and actionable — in seconds.

Packages

Quick Setup (Claude Desktop)

Add to your Claude Desktop config file:

Mac: ~/Library/Application Support/Claude/claudedesktopconfig.json Windows: %APPDATA%\Claude\claudedesktopconfig.json

{
  "mcpServers": {
    "autostackup-sales": {
      "command": "npx",
      "args": ["-y", "@autostackup/sales"],
      "env": {
        "HUNTER_API_KEY": "your-hunter-key-optional",
        "APOLLO_API_KEY": "your-apollo-key-optional"
      }
    },
    "autostackup-marketing": {
      "command": "npx",
      "args": ["-y", "@autostackup/marketing"]
    }
  }
}

Restart Claude Desktop. Done. Every tool below is now available.

@autostackup/sales

Turn Claude into a senior sales strategist. Qualify leads, score fit, write outreach, and track your pipeline — all from a conversation.

qualify_lead — BANT + MEDDIC Dual Qualification

Most teams use BANT or MEDDIC. This tool runs both simultaneously and gives you a combined score, tier, and action plan.

What it does:

  • Scores your lead on Budget, Authority, Need, and Timeline (BANT)
  • Cross-validates using Metrics, Economic Buyer, Decision Criteria, Decision Process, Identify Pain, and Champion (MEDDIC)
  • Returns a tier (A = close now / B = develop / C = nurture / D = deprioritize)
  • Lists specific strengths in this deal ("Decision maker is at VP level", "Timeline is defined")
  • Lists specific gaps ("Budget not established", "Competing against 2 vendors")
  • Recommends the exact next step ("Schedule executive alignment call and begin proposal draft")

Example prompt:

"Qualify this lead: Acme Corp, 200 employees, SaaS company. Decision maker is the VP of Operations. They need to reduce manual reporting time by 80%. Budget is ~$50k/year. They want to decide by end of quarter."

score_icp — Ideal Customer Profile Fit Scoring

Before you spend time on a lead, know if they actually fit. Define your ICP once and score every prospect against it automatically.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

HR: common questions

Is HR MCP server safe?
Mostly: it is graded B (82/100). Read the HR safety report
How do I install HR?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does HR need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is HR maintained?
The last commit was 149 days ago (2026-06-08). The latest release is v0.1.1.
How does HR compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 5 (the typical server has 7); tools that change things 40% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from Autostackup →