mcpField
I
indeeddata

indeeddata

Local
github.com/CloudCorpRecordsBusiness & Marketing0Updated 2d ago

About indeeddata

indeeddata is a local bridge that returns Indeed job listings and full posting details as JSON. It is aimed at clients searching public jobs by keyword and location or retrieving a posting by URL, and relays requests to HasData without maintaining its own listings.

Key features

  1. 01Search listings by keyword and location
  2. 02Filter and page through search results
  3. 03Retrieve full job posting details
  4. 04Return salary, type, description, and benefits
  5. 05Read-only forwarding to HasData

Use cases

  1. 01Find jobs matching a role and location
  2. 02Narrow listings by posting date or remote type
  3. 03Review compensation and benefits for a job

MCP support

Exposes two read-only Indeed job lookup tools to MCP clients. It forwards calls to the hosted HasData Indeed MCP server and passes successful results through.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cloudcorprecords-indeeddata": {
"command": "npx",
"args": [
"-y",
"@reneturcios/indeeddata"
]
}
}
}
Run commandnpx -y @reneturcios/indeeddata

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/indeeddata0.1.0
ocighcr.io/cloudcorprecords/indeeddata:0.1.0

Tools

2

Saved tool list · updated 2d ago

ParameterTypeRequiredDescription
urlstringYesThe URL of the job vacancy to retrieve details for.

Details

From the project README

indeeddata

indeeddata is a small local bridge to the hosted HasData Indeed MCP server, which returns Indeed job data as JSON. It covers the two everyday questions about public postings: which jobs match a keyword in a place right now, and what a single posting actually says once you have its URL. A listing search returns a page of jobs with their titles, companies, locations, salaries, posted dates, URLs, sponsored flags and stable jobKey identifiers; a details fetch returns one posting in full, with its compensation, employment type, complete description and benefits.

The bridge keeps no postings of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface is two read-only fetches over public postings only: there is no application submission, no employer or candidate contact data, and no messaging or payment tool in it.

Tools

  • hasdata_indeed_listing_getJobListings — search Indeed listings. Required: keyword and location. Optional: sort (relevance / date), domain (the country site to search, for example au.indeed.com), sponsoredOnly, datePosted (1 / 3 / 7 / 14 days), remoteType (remote / hybrid), and start (result offset for paging). For remote roles in the US, use a country-wide location such as United States: Indeed ties fully remote jobs to the country rather than a city.
  • hasdata_indeed_job_getJobDetails — fetch one posting in full. Required: url (the posting's viewjob URL, typically taken from a listing search result). Returns title, company, location, salary/compensation, employment type, full description and benefits.

Configuration

  • HASDATA_INDEED_MCP_URL (optional) — override the upstream endpoint. Defaults to https://mcp.hasdata.com/mcp?apis=indeed. (The override hook is this rebuild's own labelled reconstruction.)
  • HASDATA_API_KEY (optional) — when set, every upstream request carries an x-api-key: <key> header, for the caller's own HasData API key. When it is not set, no key header is sent. (The header name and the env name are pinned by the original's registry record; forwarding the key from this env var is a labelled reconstruction — the original surface was captured keyless.)
Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name indeeddata), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with indeeddata error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string:

npx @reneturcios/indeeddata hasdata_indeed_listing_getJobListings '{"keyword":"nurse","location":"Austin, Texas","sort":"date"}'
npx @reneturcios/indeeddata hasdata_indeed_job_getJobDetails '{"url":"https://www.indeed.com/viewjob?jk=example"}'
npx @reneturcios/indeeddata --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

npx -y @reneturcios/indeeddata mcp

MCP client config:

{
  "mcpServers": {
    "indeeddata": {
      "command": "npx",
      "args": ["-y", "@reneturcios/indeeddata", "mcp"]
    }
  }
}

Docker

docker run -i ghcr.io/cloudcorprecords/indeeddata
docker run --rm ghcr.io/cloudcorprecords/indeeddata --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

npm install
npm run build
npm test
npm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.