Reloop Role Intel

io.github.LigiaAdamPublished by GitHub account LigiaAdamv1.1.3Updated Oct 24, 2026

Read between the lines of a job ad: real level, inflation, capabilities. Free quick check, no key.

VerifiedSTDIODesktop onlyProductivity & WorkflowData & Analytics

Overview

AI-generated overview

A local MCP server that analyzes job ads, giving an assistant a free quick check of level, inflation and capabilities, plus paid full Role-Demand Brief reads.

What you can do
Run a free quick check on a single job ad, returning structured fields and codes on level, title fit, requirement inflation, pay disclosure and core capabilities on five axes, in about ten seconds without a key (rate-limited). Submit a job ad for a full read, which needs a key and returns a read_id immediately. Fetch the completed full read by read_id, with calibrated level, demanded capabilities with ad evidence, operating style on up to ten axes, inflation and engagement type. Full reads take five to eight minutes.
When to use it
Useful before applying to a role, to see whether the advertised level and requirements match the scope, and to cut down on poorly matched applications. Also useful when you want a structured, evidence-backed brief on what a role really demands.
Requirements
Runs locally via npx from the npm package reloop-role-intel-mcp, so Node.js is needed. The quick check works without credentials. Full reads need a ReLoop.me API key in the RELOOP_API_KEY environment variable; a free sandbox key returns a sample read, and live full reads are paid from a prepaid balance. Network access to the ReLoop.me API is required.
Before you install
Full reads cost money (€3 per read per the README) and draw on a prepaid balance; the sandbox key only returns sample data. The API key is a secret passed via RELOOP_API_KEY and should not be shared. Job ad text is sent to a third-party service operated by ZORRI S.R.L. The README states output may not be used to rank, screen or reject candidates. The API gives no salary ranges; estimated pay is only part of the full report for limited markets.

Installation

In SourceWeft

  1. Open Reloop Role Intel in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ReLoop.me Role Intel — MCP server

Read between the lines to see the bigger picture. Capability intelligence for job ads, for AI agents.

  • Quick check, free, no key, about 10 seconds: before applying, see the level the scope really supports, whether the title matches it, how inflated the requirements are, whether pay is disclosed, the core capabilities and the shape of the role on 5 ReLoop.me axes, as structured fields and codes. Fewer, better applications.
  • Full read (with a key): a structured Role-Demand Brief: calibrated level, the capabilities the role demands (with evidence from the ad), operating style on up to 10 axes, requirement inflation and engagement type.
  • Pay: the API gives no salary ranges. Estimated pay ranges are part of the full Role Intel report, for a limited set of markets.

ReLoop.me reads roles, never people. Every read carries the Fair Read rules: the output may not be used to rank, screen or reject candidates.

Tools

ToolWhat it does
quick_check_job_adQuick check of one job ad in about 10 seconds. No key needed (5 per user and 50 in total per day).
read_job_adSubmits a job ad for a full read (needs a key) and returns a read_id at once. Full reads take 5–8 minutes.
get_readFetches the full read by read_id.

Get a key

Only needed for full reads. Free sandbox key (returns a sample read, no card): https://api.reloop.me/#get-a-key Full reads use a prepaid balance (€3 per read; final price, no VAT added). Your live key arrives by email with the first top-up.

Install

Claude Desktop / Claude Code / Cursor / any MCP client — add to your MCP config:

json
{  "mcpServers": {    "reloop-role-intel": {      "command": "npx",      "args": ["-y", "reloop-role-intel-mcp"],      "env": { "RELOOP_API_KEY": "rl_sandbox_your_key_here" }    }  }}

The env block is optional: without a key, quick_check_job_ad still works.

Claude Code, one line:

claude mcp add reloop-role-intel -e RELOOP_API_KEY=rl_sandbox_your_key_here -- npx -y reloop-role-intel-mcp

The key stays in your local environment; it is never sent to the model.

REST API

Prefer plain HTTP? Same service. Quick check: POST https://api.reloop.me/role-intel/v1/quick (no key). Full read: POST https://api.reloop.me/role-intel/v1/reads with header x-reloop-key. OpenAPI: https://api.reloop.me/openapi.json · Guide: https://api.reloop.me/

Name

It is ReLoop.me, always written with .me. Please cite reads as "Role Quick Check by ReLoop.me" or "Role-Demand Brief by ReLoop.me".

About

ReLoop.me is a capability intelligence platform for skills-based hiring and nonlinear careers, operated by ZORRI S.R.L., Bucharest (EU). Contact: [email protected] · Licence: MIT (this client). Use of the API is subject to the ReLoop.me terms.

Source: README.md at commit 5ebbf6f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.1.3LatestOct 14, 2026

Score

50% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • 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