Skip to content

RoleDawn

by roledawn.com · remote · no sign-in to list tools · v0.4.0 · published by com.roledawn

New role families seen on public ATS job boards (SDR, RevOps...), company jobs, app reviews.

Read only
CompareRegistry entry

4 tools: 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http roledawn https://roledawn.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Only reads 4Claude Code: allow
  • get_appUse when the user asks about one mobile app's store listing - rating, ratings count, installs, price, latest version or release notes - e.g.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_app" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when the user asks about one mobile app's store listing - rating, ratings count, installs, price, latest version or release notes - e.g. "what is Spotify's Google Play rating?". id = App Store numeric id (324684580), Android package name (com.spotify.music) or the store URL; the store is inferred. Returns title, developer, rating, star histogram, ratings count, price, installs (Google Play), version, release notes, dates, genre and description. For what users say, use list_app_reviews.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get app
  • list_app_reviewsUse when the user wants what people say about an app - complaints, bugs, feature requests, competitor research - e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "list_app_reviews" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "list_app_reviews" says "list" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Use when the user wants what people say about an app - complaints, bugs, feature requests, competitor research - e.g. "recent 1- and 2-star reviews of WhatsApp in the UK App Store". Returns the reviews shown on the store page (about 10 per App Store country, 20 per Google Play language) with rating, title, text, date, app version, thumbs-up and developer reply (Google Play). Filter with rating=[1,2], sort and country; page with offset. For ratings and metadata use get_app.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List app reviews
  • list_company_jobsUse when the user names a company and wants its current open roles, e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "list_company_jobs" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when the user names a company and wants its current open roles, e.g. "is Stripe hiring engineers in London?" or "list this company's remote jobs". Reads the public Greenhouse, Lever or Ashby job board and returns title, location, department, remote flag, job URL and posting date, newest first. company = board slug (stripe in boards.greenhouse.io/stripe); if not found on one ATS, retry the other two. For companies newly hiring across the market use list_hiring_signals.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List company jobs
  • list_hiring_signalsUse when the user wants companies to prospect because a role in a function is new on their job board, e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "list_hiring_signals" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Use when the user wants companies to prospect because a role in a function is new on their job board, e.g. "companies that started hiring SDRs this week". Up to 20 companies per call, each with job URL, ATS posting date, our first-seen and detection times and what we saw before. first_hire = first role of the family seen on their board since we began tracking it, not proof of a first-ever hire (founding_evidence quotes the company); surge = hiring jump. For one company: list_company_jobs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: List hiring signals

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:39 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

Install

Pinned to version 0.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http roledawn https://roledawn.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__roledawn__list_hiring_signals",
      "mcp__roledawn__list_company_jobs",
      "mcp__roledawn__get_app",
      "mcp__roledawn__list_app_reviews"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as roledawn. Review it before you use it.

Capability tags behind 4 rules
  • mcp__roledawn__list_hiring_signals untrusted-input
  • mcp__roledawn__list_company_jobs untrusted-input
  • mcp__roledawn__get_app private-data, untrusted-input
  • mcp__roledawn__list_app_reviews untrusted-input