Connect Pirch and your agent gets 3 tools, among them get_jobs_overview, get_verified_job, search_verified_jobs. It answers at https://pirchjobs.com/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 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Verified job search: every listing confirmed live and accepting applicants within the last 72h.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_jobs_overview | Snapshot of the verified pool: how many jobs are live right now, counts by work mode, and the occupations (role slugs) with jobs today. Good first call to see what's available before searching. |
get_verified_job | Full record for one verified job by `id` (from search_verified_jobs): complete summary, the pirch page `url` to cite, the original posting `apply_url` (applications happen there — pirch never sits between applicant and employer), verificati Inputs: id |
search_verified_jobs | Search pirch's pool of verified-live job listings. Every job returned was opened and confirmed real and accepting applicants by pirch within the last 72 hours — dead and ghost listings are removed automatically, so results can be trusted as Inputs: query, workmode, location, role, limit |
Every block below points at https://pirchjobs.com/mcp. Pick your client and copy.
claude mcp add --transport http pirch https://pirchjobs.com/mcp
{
"mcpServers": {
"pirch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://pirchjobs.com/mcp"]
}
}
}{
"mcpServers": {
"pirch": {
"url": "https://pirchjobs.com/mcp"
}
}
}{
"servers": {
"pirch": {
"type": "http",
"url": "https://pirchjobs.com/mcp"
}
}
}{
"context_servers": {
"pirch": {
"url": "https://pirchjobs.com/mcp"
}
}
}{
"mcpServers": {
"pirch": {
"serverUrl": "https://pirchjobs.com/mcp"
}
}
}{
"mcpServers": {
"pirch": {
"url": "https://pirchjobs.com/mcp"
}
}
}name: pirch
version: 0.0.1
schema: v1
mcpServers:
- name: pirch
type: streamable-http
url: https://pirchjobs.com/mcp{
"mcpServers": {
"pirch": {
"httpUrl": "https://pirchjobs.com/mcp"
}
}
}{
"mcpServers": {
"pirch": {
"type": "http",
"url": "https://pirchjobs.com/mcp"
}
}
}{
"mcpServers": {
"pirch": {
"url": "https://pirchjobs.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fpirchjobs.com%2Fmcp&type=streamable_http&id=pirch&name=pirch
It answered our last check on 18 October 2026 in 574 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by pirchjobs.com and served from pirchjobs.com, the vendor's own domain: https://pirchjobs.com/mcp.
3, as returned by the server's own tools/list on 31 August 2026: get_jobs_overview, get_verified_job, search_verified_jobs.
It answered our last check on 18 October 2026 in 574 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://pirchjobs.com/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: com.pirchjobs. Endpoint host: pirchjobs.com. ARD identifier: urn:air:com.pirchjobs:mcp:pirch.
First indexed 31 August 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.