
PM Career Desk MCP server
Which MCP servers are PM Career Desk'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 2026-10-29
- Registry namecom.pmcareerdesk/interview-coachverified in the MCP registry
The registry name sits under pmcareerdesk.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Statedid not answerchecked 2026-10-29
On 2026-10-29 nothing answered at this address. We will ask again on the next pass.
- Answered on only 1 of 7 daily checks.
- Its tools do check resume lines against what hiring managers question; prepare interview answers from your own work record, but not track recruiter emails and job postings in one place.
Once connected
- For "check resume lines against what hiring managers question", the likely first call is check_resume_line.
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 score63 of 100answers 13 · does the job 67 · definitions 100 · context 67 · connects 100
- What an agent can do with it2 of 3 use cases
- Answered14% of days1 of 7 daily checks
- Median first answer1439 ms
- Space in an agent's context≈ 10,189 tokensthe definitions of all its tools (19), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 19 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · check resume lines against what hiring managers question
- can do · prepare interview answers from your own work record
- cannot · track recruiter emails and job postings in one place
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
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 →
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"interview-coach": {
"type": "http",
"url": "https://app.pmcareerdesk.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http pmcareerdesk https://app.pmcareerdesk.com/mcpclaude.ai, ChatGPT and other clients: add https://app.pmcareerdesk.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.
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.