Connect Talent and your agent gets 7 tools, among them add_to_shortlist, fetch, get_open_to_work. It answers at https://d.cv/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Talent discovery for AI. Search and read agent-readable candidate profiles; cite by URL.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_to_shortlist | Add a candidate to one of your d.cv shortlists (creates the shortlist if it does not exist). Requires your d.cv API key. Use after search_talent when the user wants to save someone. Inputs: handle, shortlist |
fetch | Fetch a single d.cv profile in full as markdown, by its id (the handle returned from search). Inputs: id |
get_open_to_work | List candidates who are currently open to work, optionally filtered by skills. Best when the user wants people actively looking. Inputs: skills, limit |
get_profile | Read a single candidate profile in full as clean markdown, by handle. Inputs: handle |
save_search | Save a talent search to your d.cv account so you can re-run it later. Requires your d.cv API key. Inputs: query, name, open_to_work |
search | Search d.cv talent profiles by free-text query (name, role, skills, location). Returns lightweight results with an id, title, and url. Use fetch to read one in full. (Standard connector search tool.) Inputs: query |
search_talent | Find published candidate profiles on d.cv by keyword, skill, role, location, and availability. Returns structured candidates with handle, url, headline, skills, and open-to-work status. Inputs: query, skills, open_to_work, limit |
Every block below points at https://d.cv/mcp. Pick your client and copy.
claude mcp add --transport http talent https://d.cv/mcp
{
"mcpServers": {
"talent": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://d.cv/mcp"]
}
}
}{
"mcpServers": {
"talent": {
"url": "https://d.cv/mcp"
}
}
}{
"servers": {
"talent": {
"type": "http",
"url": "https://d.cv/mcp"
}
}
}{
"context_servers": {
"talent": {
"url": "https://d.cv/mcp"
}
}
}{
"mcpServers": {
"talent": {
"serverUrl": "https://d.cv/mcp"
}
}
}{
"mcpServers": {
"talent": {
"url": "https://d.cv/mcp"
}
}
}name: Talent
version: 0.0.1
schema: v1
mcpServers:
- name: Talent
type: streamable-http
url: https://d.cv/mcp{
"mcpServers": {
"talent": {
"httpUrl": "https://d.cv/mcp"
}
}
}{
"mcpServers": {
"talent": {
"type": "http",
"url": "https://d.cv/mcp"
}
}
}{
"mcpServers": {
"talent": {
"url": "https://d.cv/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fd.cv%2Fmcp&type=streamable_http&id=talent&name=Talent
It answered our last check on 19 October 2026 in 707 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by d.cv and served from d.cv, the vendor's own domain: https://d.cv/mcp.
7, as returned by the server's own tools/list on 11 September 2026: add_to_shortlist, fetch, get_open_to_work, get_profile, save_search, search, search_talent.
It answered our last check on 19 October 2026 in 707 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://d.cv/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: cv.d. Endpoint host: d.cv. ARD identifier: urn:air:cv.d:mcp:talent.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.