
RoleDawn MCP server
Which MCP servers are RoleDawn's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namecom.roledawn/mcpverified in the MCP registry
The registry name sits under roledawn.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools4
- Server calls itselfcom.roledawn/mcp
- Server version0.4.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 32 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer210 ms
- Space in an agent's context≈ 1,612 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_hiring_signalsUse 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…
list_company_jobsUse 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…
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. "what is Spotify's Google Play rating?". id = App Store numeric id (324684580), Android package…
list_app_reviewsUse 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…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"roledawn": {
"type": "http",
"url": "https://roledawn.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http roledawn https://roledawn.com/mcpclaude.ai, ChatGPT and other clients: add https://roledawn.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.