Jobo Job Search

world.joboPublished by jobo.worldOfficial publisherv1.1.0Updated Oct 24, 2026

Search a live index of millions of open jobs from employer career sites and 100+ ATS platforms.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowWeb Search & Scraping

Overview

AI-generated overview

Jobo Job Search gives an assistant a live index of millions of open jobs from employer career sites and ATS platforms, with search, fetch and structured…

What you can do
  • Search the job index with a simple query and fetch a self-contained text version of a listing, in the canonical Deep Research shape.
  • Run structured job searches by location, work model, employment type, experience level, source, skills, industries, salary and date, with facets and paging.
  • Read the full listing for a job, optionally including the raw employer description.
  • List the accepted values for every filter, with live counts.
When to use it
Useful when someone wants an assistant to find open roles, compare listings against criteria such as location, salary or skills, or act as a job-search source inside ChatGPT Deep Research and similar clients.
Requirements
A remote endpoint at jobs-mcp.jobo.world, or a local copy run with npx jobo-job-search-mcp on Node.js, listening on PORT (default 3002). OAuth 2.1 sign-in with a Jobo account and the jobs:read scope; no API key is copied. Self-hosting also needs MCP_RESOURCE_URL set to the host it is served from.
Before you install
Sign-in goes through the Jobo account and every request is validated upstream against the Jobo authorization server, so job queries and account identity reach Jobo. The server is read-only for job data, but it forwards the client's bearer token on each call. Self-hosted copies still require Jobo sign-in and must be configured with the correct resource URL.

Installation

In SourceWeft

  1. Open Jobo Job Search in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/world.jobo%2Fjob-search/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "jobo-job-search": {
      "type": "http",
      "url": "https://jobs-mcp.jobo.world/mcp"
    }
  }
}

README

Jobo Job Search MCP Server

Remote MCP server exposing Jobo's live job index — millions of listings collected from employer career sites and 150+ applicant tracking systems — to LLM clients.

Full client setup (Claude, ChatGPT, Cursor, Codex CLI) and the tool reference: jobo.world/docs/connectors/mcp.

  • Transport: Streamable HTTP, single /mcp endpoint, stateless. Serves MCP spec 2026-07-28 natively and every 2025-era client through the built-in legacy fallback (SDK v2 createMcpHandler, one factory for both eras).
  • Auth: OAuth 2.1. This is a Resource Server; the Authorization Server is the Jobo API. Clients log in with their Jobo account — no API key copy-paste. Required scope: jobs:read.

Self-hosting

The hosted deployment is https://jobs-mcp.jobo.world. To run your own copy instead:

bash
npx jobo-job-search-mcp

Starts the Streamable HTTP server on $PORT (default 3002); point your client at http://localhost:3002/mcp. This changes where the gateway runs, not its auth model — it's still an OAuth resource server gated on Jobo account sign-in, since the upstream API validates every request against the Authorization Server regardless of which copy of the gateway forwarded it. Set MCP_RESOURCE_URL to match whatever host you actually serve it from — see Configuration below.

Why this is a separate server

Jobo.Enterprise/Jobo.Enterprise.Mcp was deliberately re-scoped to analytics-only in v4, which removed search_jobs, get_job_details, list_filters, search and fetch. Adding job tools back there would undo that decision, so this is a second server against the same External API.

The /api/mcp/jobs/* endpoints were never removed — McpController.cs still serves them, and its own comment notes the GET search is "convenient for the canonical ChatGPT search(query) tool". This server is a thin OAuth-forwarding gateway in front of endpoints that were built for it.

The immediate payoff: search + fetch restore Deep Research compatibility. Without that canonical pair a server cannot be used as a ChatGPT Deep Research connector at all.

Tools

ToolPurpose
searchCanonical Deep Research contract: {query} → {results: [{id, title, url}]}.
fetchCanonical Deep Research contract: {id} → {id, title, text, url, metadata}.
search_jobsStructured search — location, work model, employment type, experience level, source, skills, industries, salary, date, facets, paging.
get_job_detailsFull listing for clients not using the Deep Research contract.
list_filtersAccepted values for every filter, with live counts.

search/fetch deliberately take the minimum arguments the contract allows. Anything with structure should go through search_jobs, where filters are real parameters rather than hopeful free text.

What fetch returns

text is self-contained prose, because Deep Research reads it and never opens the URL. It is built from the AI-extracted fields (responsibilities, qualifications, benefits, compensation) in preference to the raw employer HTML, which is boilerplate-heavy and frequently longer than it is useful. The raw description is available via get_job_details with include_description: true.

Auth model

The server is a gateway, not the cryptographic authority. The C# External API validates the JWT with OpenIddict against the same issuer, audience and jobs:read scope; verifying the signature a second time here would only let the two validators drift. So this does the minimum a gateway must:

  1. Require a Bearer token; absent → 401 with the resource-metadata challenge, starting the OAuth flow.
  2. Cheaply reject an already-expired token (decode exp, no signature check) so long-lived clients refresh rather than forwarding a dead token.
  3. Attach the raw current-request token to req.auth, so every tool call forwards the token the client just sent — never one captured at session-initialize.

Stateless by design

No session map. That map lived in process memory, so every restart or redeploy stranded clients with "No active session", and it pinned the deployment to a single replica. Redis cannot back it either: the value is a live transport object holding open streams. Each POST is served by a fresh server and transport with no mcp-session-id issued.

Configuration

VariableDefaultNotes
JOBO_API_URLhttps://connect.jobo.worldUpstream External API.
MCP_RESOURCE_URLhttps://jobs-mcp.jobo.worldOAuth audience. Must differ from the analytics server's mcp.jobo.world.
OAUTH_AUTH_SERVER_URLhttps://enterprise.jobo.worldAuthorization Server.
PORT3002Analytics server uses 3001.

Development

bash
npm install && npm run build && npm test
bash
npm run dev

Verifying without credentials

node --test dist/format.test.js covers the mapping logic, including that search and fetch return exactly the shapes Deep Research requires. For the wire path, point the server at a stub:

bash
JOBO_API_URL=http://localhost:3098 PORT=3097 MCP_RESOURCE_URL=http://localhost:3097 node dist/index.js

Then tools/list and tools/call over HTTP with any JWT-shaped bearer whose exp is in the future — the gateway forwards it and the stub answers. A real token is only needed against the live API.

Registry listing

Published to the official MCP Registry as world.jobo/job-search (the mcpName in package.json; server.json in this directory is the registry manifest). Publishing is automated: the mcp-v* tag workflow publishes npm first, then pushes server.json to the registry under the DNS-TXT-verified world.jobo/* namespace — see ../RELEASING.md. There is no review queue and aggregators poll roughly hourly. Note the official registry has no per-server web page by design — it is a metadata API for aggregators. The downstream surfaces differ: PulseMCP emits a dofollow link, Glama and mcp.so are nofollow. Manual directory submissions (Claude, ChatGPT, aggregator claims) live in ../MCP-DISTRIBUTION.md.

Source: README.md at commit 49966fa

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.1.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts