_ registry / mcp streamable-http · checked 1h ago

com.roledawn/mcp

https://roledawn.com

Registry code: 864d5a8c08ec1616

api record

RoleDawn: public hiring and app-store data, read-only, no sign-up. Pick the tool by the question: "which companies started hiring for X" (sales triggers, prospect lists) -> list_hiring_signals; "what jobs does <company> have open" -> list_company_jobs; "rating / installs / version of <app>" -> get_app; "what do users complain about in <app>" -> list_app_reviews. Every result starts with a one-line summary, then the full JSON. Free use: 50 tool calls per IP per day. For list_hiring_signals a free personal key (roledawn.com/api/key; X-RoleDawn-Key header or ?key= on the server URL) gives 50…

endpoint
https://roledawn.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is com.roledawn/mcp live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is com.roledawn/mcp free to use?
Yes — the hub reached it with no key and no payment.
What tools does com.roledawn/mcp have?
4 tools: get_app, list_app_reviews, list_company_jobs, list_hiring_signals.
Is com.roledawn/mcp safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
400ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 190 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 4 tools
4 never probed 0 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_app unknown 4h ago

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "examples": [
            "com.spotify.music",
            "324684580"
          ],
          "maxLength": 300,
          "description": "App Store id (e.g. 324684580), package name (e.g. com.spotify.music) or store URL."
        },
        "lang": {
          "type": "string",
          "description": "Google Play language, e.g. en, de, pt-BR. Default en."
        },
        "store": {
          "enum": [
            "apple",
            "google"
          ],
          "type": "string",
          "description": "Optional; inferred from id (numeric = apple, package name = google)."
        },
        "country": {
          "type": "string",
          "pattern": "^[a-z]{2}$",
          "description": "Two-letter store country, default us."
        }
      },
      "additionalProperties": false
    }
    arguments 35 lines
  • list_app_reviews unknown 4h ago

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "maxLength": 300,
          "description": "App Store id, package name or store URL."
        },
        "lang": {
          "type": "string",
          "description": "Google Play language, default en."
        },
        "sort": {
          "enum": [
            "newest",
            "oldest",
            "rating_asc",
            "rating_desc",
            "relevant"
          ],
          "type": "string",
          "description": "Default newest."
        },
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1,
          "description": "Reviews per page (1-50). Default 20."
        },
        "store": {
          "enum": [
            "apple",
            "google"
          ],
          "type": "string",
          "description": "Optional; inferred from id."
        },
        "offset": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 0,
          "description": "Reviews to skip; use next_offset."
        },
        "rating": {
          "type": "array",
          "items": {
            "type": "integer",
            "maximum": 5,
            "minimum": 1
          },
          "maxItems": 5,
          "description": "Only these star ratings, e.g. [1,2]."
        },
        "country": {
          "type": "string",
          "pattern": "^[a-z]{2}$",
          "description": "Two-letter store country, default us."
        }
      },
      "additionalProperties": false
    }
    arguments 64 lines
  • list_company_jobs unknown 4h ago

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "ats",
        "company"
      ],
      "properties": {
        "q": {
          "type": "string",
          "maxLength": 100,
          "description": "Text that must appear in the job title, e.g. engineer."
        },
        "ats": {
          "enum": [
            "greenhouse",
            "lever",
            "ashby"
          ],
          "type": "string",
          "description": "Applicant tracking system that hosts the job board. Unknown? Try greenhouse, then lever, then ashby."
        },
        "limit": {
          "type": "integer",
          "maximum": 500,
          "minimum": 1,
          "description": "Jobs per page (1-500). Default 25."
        },
        "offset": {
          "type": "integer",
          "maximum": 100000,
          "minimum": 0,
          "description": "Jobs to skip; use next_offset from the previous result."
        },
        "remote": {
          "type": "boolean",
          "description": "true = only remote jobs, false = only non-remote jobs. Omit for all."
        },
        "company": {
          "type": "string",
          "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,79}$",
          "examples": [
            "stripe"
          ],
          "description": "Job-board slug from the careers URL, e.g. stripe."
        },
        "location": {
          "type": "string",
          "maxLength": 100,
          "description": "Text that must appear in the location, e.g. London."
        }
      },
      "additionalProperties": false
    }
    arguments 53 lines
  • list_hiring_signals unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "family"
      ],
      "properties": {
        "type": {
          "enum": [
            "first_hire",
            "surge",
            "all"
          ],
          "type": "string",
          "description": "first_hire (default) = first role of the family RoleDawn has observed on the board since tracking it (observed) or inferred on its first read (inferred), not the company's first hire ever; surge = hiring jump; all = both."
        },
        "limit": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "Companies per page (1-20). Default 20."
        },
        "since": {
          "enum": [
            "7d",
            "14d",
            "30d"
          ],
          "type": "string",
          "description": "Detected in the last 7, 14 or 30 days. Default 7d."
        },
        "family": {
          "type": "array",
          "items": {
            "type": "string",
            "pattern": "^[a-z-]+$"
          },
          "examples": [
            [
              "sdr"
            ],
            [
              "revops",
              "sales-enablement"
            ]
          ],
          "maxItems": 5,
          "minItems": 1,
          "description": "Role family ids (1-5). Common: sdr (SDR/BDR), sales (AEs), revops, customer-success, marketing, security, data-engineering, ml-ai. All ids: sdr, sales, revops, sales-enablement, marketing-ops, sales-engineering, partnerships, customer-success, account-management, support, professional-services, marketing, product-marketing, growth-marketing, content, devrel, community, software-engineering, frontend, mobile, platform-sre, security, compliance, qa, engineering-management, hardware, it, data-engineering, data-analytics, ml-ai, product-management, design, ux-research, technical-writing, finance, legal, people, recruiting, bizops, workplace, executive, clinical, supply-chain."
        },
        "offset": {
          "type": "integer",
          "maximum": 19,
          "minimum": 0,
          "description": "Companies to skip; use next_offset from the previous result."
        },
        "include_closed": {
          "type": "boolean",
          "description": "true = also return signals whose job post has since closed (still_open=false). Default false."
        }
      },
      "additionalProperties": false
    }
    arguments 62 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 864d5a8c08ec1616.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/864d5a8c08ec1616/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/864d5a8c08ec1616/badge.svg)](https://brick.blue/agent/864d5a8c08ec1616?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.