AskHR Policy Agent

Name: AskHR Policy Agent
Availability: InStock
Author: Kata Team

Answers HR policy questions in Slack with the page, the link, and the right form.

Human Resources Onboarding & Training 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 (8)

search_hr_policiesRead-only
Search an approved Confluence HR space for pages matching an employee's question.
Reaches: {confluence_site}.atlassian.net
Uses your Confluence Cloud token.
get_policy_pageRead-only
Fetch the full body and version metadata of one HR page, including when it was last updated.
Reaches: {confluence_site}.atlassian.net
Uses your Confluence Cloud token.
find_request_formRead-only
Find the form or request page for a process, from pages labelled as HR forms in an approved space.
Reaches: {confluence_site}.atlassian.net
Uses your Confluence Cloud token.
compose_hr_answerRead-only
Turn a retrieved HR page into a cited answer with its form link, or refuse when the page does not cover the question.
post_cited_answerCan change data
Post the cited policy answer as a reply in the Slack thread where the question was asked.
Reaches: slack.com
Uses your Slack bot token.
post_private_noticeCan change data
Reply visibly only to the person who asked, for a sensitive matter that must not appear in a public thread.
Reaches: slack.com
Uses your Slack bot token.
escalate_questionCan change data
Send an unanswered general or individual-case question to the people team's channel with the search already run.
Reaches: slack.com
Uses your Slack bot token.
flag_sensitive_to_hrCan change data
Notify the people team that someone raised a sensitive matter, passing only who and where — never what was said.
Reaches: slack.com
Uses your Slack bot token.

Credentials it will ask for (2)

Confluence Cloud token
Only ever sent to: atlassian.net
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.
Slack bot token
Only ever sent to: slack.com

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, Email, Phone.
A request larger than 30,000 characters is rejected before it runs.
get_policy_pageRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
compose_hr_answerRate limited to 200/hour.Safe to retry automatically if a run is interrupted.
escalate_questionRate limited to 100/hour.
find_request_formRate limited to 200/hour.Safe to retry automatically if a run is interrupted.
post_cited_answerRate limited to 100/hour.Runs only after get_policy_page has run first.
search_hr_policiesRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
post_private_noticeRate limited to 60/hour.
flag_sensitive_to_hrRate limited to 60/hour.

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": {
    "askhr-policy-agent": {
      "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.

Confluence Cloud token
Base64 of 'your-email:your-api-token' — encode it yourself before pasting; the runtime only adds the Basic prefix. Create the token at id.atlassian.com/manage-profile/security/api-tokens. Use an account whose Confluence access covers only the spaces this agent should answer from — it can read whatever this account can read.
Get this from atlassian.net's account or API settings.
Paste the value as a single line.
Only sent to: atlassian.net
Slack bot token
A bot token starting with xoxb- from your Slack app. Needs chat:write, and the bot must be invited to every channel it answers or escalates in.
Create a Slack app (api.slack.com/apps), add the scopes the agent needs, install it to your workspace, and copy the bot/user token.
Paste the value as a single line.
Only sent to: slack.com

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/askhr-policy-agent

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 atlassian.net, slack.com, 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