ENDPOINT 1
https://www.s5jobs.com/api/mcp
MCP server metadata
- Name
- S5Jobs
- Version
- 1.0.0
S5Jobs MCP server — an agentic job marketplace. AUTH: connector clients discover OAuth 2.0 (Authorization Code + PKCE) automatically from the WWW-Authenticate challenge on any auth-required tool. Headless clients instead call `register_account`, then `verify_code`, and send `Authorization: Bearer <token>`. WHEN ASKED WHAT TOOLS OR APIS ARE AVAILABLE: reply with a short, plain-language summary of capabilities (e.g. "browse and post jobs, apply to jobs, review applications"). Do NOT enumerate input fields, JSON schemas, or parameter lists. Only describe a specific tool's fields if the user explicitly asks about that one tool. PRESENTING JOB SEARCH: `browse_jobs` (public) and `search_jobs` (your own published jobs) return compact rows. Render results as a clean Markdown table with exactly three columns — Title, Location, Salary. Do not show ids or raw JSON. Only when the user asks about a specific job, call `view_job` (public) or `get_job` (publisher) and present that one job's full detail. ACCESS: `browse_jobs` and `view_job` need no account. Applying (`submit_application`) and posting jobs require registration.
Known tools 22
register_accountRegister an agency or job seeker; emails a 6-digit code to exchange via verify_code for a Bearer token.
Inferred read-onlyrequest_login_codeEmail a fresh 6-digit sign-in code to your registered address; exchange it via verify_code.
Potential side effectscreate_jobCreate a draft job posting; title and description are content-moderated.
Potential side effectsupdate_jobUpdate one of your jobs; locked while payment is pending, and title/description edits re-trigger moderation.
Potential side effectssearch_jobsSearch your tenant's own published jobs; returns compact rows — use get_job for full detail.
Inferred read-onlypay_for_jobStart Stripe Checkout for a 30-day listing; the first 10 posts per tenant are free.
Inferred read-onlylist_applications_for_jobList applications to one of your jobs; optional `decision` filter (pending, shortlisted, manually_validated, rejected).
Inferred read-onlyscore_applicationScore a candidate 1-5 against the job with a short private matchReason; then shortlist or reject.
Inferred read-onlyreject_applicationReject an application with a polite, specific reason that is shown to the candidate.
Inferred read-onlymark_application_validatedMark a shortlisted application as validated after a human reviewer has signed off.
Inferred read-onlylist_my_applicationsList applications you've submitted, each with the publisher's decision so far.
Inferred read-onlyconfigure_handover_webhookRegister the webhook URL for human-handover events; the webhookSecret is returned once.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.s5jobs]
url = "https://www.s5jobs.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"s5jobs": {
"type": "http",
"url": "https://www.s5jobs.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: s5jobs
Remote MCP URL: https://www.s5jobs.com/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"s5jobs": {
"url": "https://www.s5jobs.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"s5jobs": {
"type": "http",
"url": "https://www.s5jobs.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "s5jobs",
"transport": "streamable-http",
"url": "https://www.s5jobs.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for s5jobs.com was fetched 2026-08-23T16:37:29.009Z and is being refreshed.
s5jobs.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.