CV Screening Assistant

Name: CV Screening Assistant
Availability: InStock
Author: Kata Team

Assesses applications requirement by requirement — reasoning first, and never an automatic rejection.

Human Resources Talent Acquisition & Sourcing HR Helpdesk @katateam

Before you connect: what this agent would do

A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.

Tools it can use (5)

get_jobRead-only
Fetch the job with the requirements the assessment must be made against.
Reaches: harvest.greenhouse.io
Uses your Greenhouse Harvest API key.
list_applicationsRead-only
List applications for a job at a given stage.
Reaches: harvest.greenhouse.io
Uses your Greenhouse Harvest API key.
get_applicationRead-only
Fetch one application with its answers and attachments metadata.
Reaches: harvest.greenhouse.io
Uses your Greenhouse Harvest API key.
get_candidateRead-only
Fetch the candidate record associated with an application.
Reaches: harvest.greenhouse.io
Uses your Greenhouse Harvest API key.
add_scorecard_noteCan change data
Attach the requirement-by-requirement assessment to the candidate as a note. Changes no status.
Reaches: harvest.greenhouse.io
Uses your Greenhouse Harvest API key.

Credentials it will ask for (1)

Greenhouse Harvest API key
Only ever sent to: harvest.greenhouse.io
Format: Paste the Base64 encoding of “id:token” (e.g. your email and API token joined by a colon), not the raw token. Many tools show this ready-made as your “Basic auth” value.

Safety rails that guard it

Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no agent can turn off.
These personal details are removed from your input before the agent sees them: Credit card, IBAN, National ID, Phone.
These personal details are stripped from the agent’s results before you see them: Email, Phone.
A request larger than 150,000 characters is rejected before it runs.
get_jobRate limited to 120/hour.Safe to retry automatically if a run is interrupted.
get_candidateRate limited to 600/hour.Safe to retry automatically if a run is interrupted.
get_applicationRate limited to 600/hour.Safe to retry automatically if a run is interrupted.
list_applicationsRate limited to 120/hour.Safe to retry automatically if a run is interrupted.
add_scorecard_noteSensitive — it is flagged and needs an explicit confirmation before it runs.Rate limited to 100/hour.Runs only after get_job has run first.

How FindAgent keeps agents safe

Run locally

This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.

terminal

npx -y @findagent/mcp run

Add it to your MCP client

Paste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.

mcp client config

{
  "mcpServers": {
    "cv-screening-assistant": {
      "command": "npx",
      "args": [
        "-y",
        "@findagent/mcp",
        "run"
      ]
    }
  }
}

What you'll need — and where to get it

This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.

Greenhouse Harvest API key
Base64 of 'YOUR_API_KEY:' (note the trailing colon) — encode it yourself before pasting; the runtime only adds the Basic prefix. Grant it Jobs, Applications, and Candidates read plus Notes write. Do NOT grant application-status or offer permissions — this agent must not be able to advance or reject anyone.
Get this from harvest.greenhouse.io's account or API settings.
Paste the value as a single line.
Only sent to: harvest.greenhouse.io

Requirements

This server requires authentication — see the description for how to get a key.

Get this agent

Free

Add the hosted gateway to Claude, ChatGPT, Cursor or any MCP client. Nothing installs on your machine.

https://mcp.findagent.cloud/agents/cv-screening-assistant

View setup

What we can prove

Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours.
Any key you connect is bound to its destination — it is only ever sent to harvest.greenhouse.io, and is dropped if a request tries to redirect it elsewhere.
Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no listing can turn off.
Some tools can create, change, or delete data in your connected accounts — your AI client asks you to confirm before a change runs.
Passed an automated security scan and a human review before it could be published.

These are facts derived from the manifest, not a score and not a badge.

Agent details