Hiring Fairness & Selection ROI
ai.saifsPublished by saifs.aiOfficial publisherv1.0.1Updated Oct 24, 2026
Detect hiring adverse impact and estimate whether a selection method is worth its cost.
The publisher's own server: Customer Intelligence & Segmentation
Overview
Remote MCP server that analyses hiring funnel counts and assessment scores for adverse impact, fairness and selection ROI.
- What you can do
- Analyse stage counts by group: selection rates, impact ratios under the EEOC four-fifths rule, chance checks and end-to-end funnel
- Compare jobs like for like to catch Simpson's paradox in selection gaps
- Evaluate anonymous score/outcome pairs: whether a test predicts job success, whether it underrates a group, a fair pass mark and net money value
- Return decision cards such as REVIEW THIS STAGE, TEST PREDICTS, SET CUTOFF or WORTH THE COST
- Get a numpy-only Python script to aggregate large ATS exports locally so candidate rows never reach the server
- When to use it
- Useful when you have hiring funnel counts or assessment results and want a quick statistical read on adverse impact, fair cutoffs or whether a selection method pays for itself, without sending individual candidate records.
- Requirements
- Remote Streamable HTTP endpoint; nothing to install. OAuth 2.1 sign-in (PKCE with dynamic client registration) is required, so the client opens a sign-in page on first use. The analysis tool accepts up to 5,000 rows per call.
Installation
In SourceWeft
- Open Hiring Fairness & Selection ROI in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/ai.saifs%2Fhiring-fairness/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"hiring-fairness-selection-roi": {
"type": "http",
"url": "https://hiring-fairness-mcp.saifs.ai/mcp"
}
}
}README
Hiring Fairness & Selection ROI
Group-level fairness and value analysis of a hiring process. From counts per stage and group it returns selection rates and impact ratios at every stage (EEOC four-fifths rule), whether each gap is larger than chance, the end-to-end funnel, and a like-for-like check across jobs that catches Simpson's paradox. From anonymous score/outcome pairs it tells you whether a test predicts job success, whether it underrates a group, a fair pass mark, and its money value net of cost. It never scores, ranks or selects individuals, and its output is analysis, not legal advice.
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
Claude Code
Any other MCP client
Point it at https://hiring-fairness-mcp.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
Example prompts
- “Here are our applicant and hire counts by stage and gender. Is any stage showing adverse impact?”
- “Is our coding assessment worth what it costs, and what pass mark is fair?”
- “Compare selection rates across departments like for like.”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Source: servers/hiring-fairness/README.md at commit 2b4eab8
Tools
0Version history
2- v1.0.1LatestOct 21, 2026
- v1.0.0Oct 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Saifs integrations
Customer Intelligence & Segmentation
ai.saifsOfficial publisher
Remote MCP server that tiers a customer book into A/B/C/D segments from purchase history and builds a sales call list.
Dynamic Pricing & Overbooking
ai.saifsOfficial publisher
Remote MCP server that gives an assistant revenue-management math: recommended prices, protection levels, overbooking limits and booking-pace alerts.
Statistical Process Control & Anomaly Alerts
ai.saifsOfficial publisher
Remote MCP server that applies statistical process control charts to metric streams and alerts only on genuine out-of-control drift.
Payment Reconciliation & Matching
ai.saifsOfficial publisher
Remote MCP server that matches bank receipts, bank lines and GST 2B rows to open invoices and the ledger, with confidence scores and an exceptions queue.
Optimization Solver (LP / MIP Scheduling)
ai.saifsOfficial publisher
Remote MCP server that solves linear and mixed-integer optimization problems, returning optimal plans, shadow prices and infeasibility diagnostics.