Connecting Odds

How to use Connecting Odds AI job search

Step-by-step guide to connecting ChatGPT, Claude, Gemini or any MCP client to Connecting Odds, what search_jobs and get_job return, and which data is never exposed.

1. The endpoint

One MCP server serves every client. Paste this URL into your assistant's connector settings.

https://connectingodds.com/mcp

2. Setup, step by step

  1. 1
    Add the Connecting Odds MCP server

    In your AI client's connector or MCP settings, add a remote MCP server and paste the Connecting Odds endpoint. No API key, no database credential — the endpoint URL is the only value you enter.

  2. 2
    Authorise the connection

    Your client opens Connecting Odds in a browser so you can approve the connection. Approval issues a scoped token to that client only, and you can revoke it at any time by removing the connector.

  3. 3
    Ask for jobs in plain language

    Ask the way you would ask a person: "remote Python jobs in Europe paying over 90k" or "cybersecurity roles in Washington DC with a clearance". The assistant calls search_jobs with the filters it parsed from your sentence.

  4. 4
    Open a specific listing

    When you want the full posting, the assistant calls get_job with the job id from the search results and reads back the public detail plus the canonical Connecting Odds URL to apply through.

3. The two job tools

search_jobs

Search the active Connecting Odds catalogue in natural language or with structured filters. Runs the same intent-aware ranked engine as the website.

Input
query (free text), plus optional location, country, remote type, employment type, experience level, company, category, salary floor/ceiling, skills, visa sponsorship, citizenship, security clearance, posted-within-days, limit.
Output
Ranked job records: title, company, location, workplace type, salary when the posting states it, skills, eligibility signals, posted date and canonical job URL — plus an explanation of how the request was interpreted.
get_job

Fetch the full public detail of a single posting by its job id.

Input
job_id (UUID).
Output
The public job record: description, requirements, company, location, salary, eligibility, employment type and apply URL. Private, moderation and recruiter-internal fields are never included.

4. What a reply looks like

Found 18 matching Connecting Odds jobs.

1. Senior Python Engineer
   Company: Example Company
   Location: Remote — US
   Salary: $150K–$180K
   Skills: Python, AWS, PostgreSQL
   Visa: Sponsorship available
   View job: https://connectingodds.com/jobs/…

2. Staff Backend Engineer
   Company: Example Company Two
   Location: Austin, TX (Hybrid)
   Salary: not stated by the employer
   Skills: Python, Django, Kubernetes
   View job: https://connectingodds.com/jobs/…

5. What is never exposed

Only public job data leaves the server

MCP job tools return the same fields a signed-out visitor sees on a job page. There is no raw table access and no query passthrough — the AI client calls a named tool with validated arguments.

Fields that are never exposed

Owner user ids, recruiter-private notes, applicant and application data, moderation state, scraper diagnostics, internal processing metadata and database credentials are excluded at the query layer, not filtered client-side.

You authorise the connection

Connecting Odds MCP uses OAuth 2.1 with dynamic client registration. Your AI client is redirected to Connecting Odds, you approve it, and it receives a scoped access token. You can revoke it at any time by removing the connector in your client.

Tools act as you, with your permissions

Account-scoped tools (your profile, saved jobs, notifications) run under your identity with row-level security applied. Another member's private data is unreachable, whatever the assistant asks for.

Never paste secrets

Connecting Odds will never ask you to paste a database credential, service key or private token into an AI client. The only value you enter is the public MCP endpoint URL.

Frequently asked questions

Do I need a Connecting Odds account to search jobs from an AI client?

No. Job search and job detail are public tools. An account is only needed for tools that act on your behalf, such as saved jobs or your profile.

Which AI clients work with Connecting Odds?

Any client that speaks the Model Context Protocol. Verified compatibility for individual clients — ChatGPT, Claude, Gemini, Copilot, Perplexity and others — is listed on the AI job search hub with the date each was last checked.

Can the assistant invent a salary or visa status?

The tools only return values the posting actually contains. When a posting states no salary, no salary is returned rather than an estimate, and the same rule applies to visa sponsorship, citizenship and clearance.

How fresh are the results?

Every job carries a posted date and a last-verified timestamp. Listings that disappear from the employer's careers page are deactivated and drop out of search, the feeds and the sitemaps.

Is there a plain HTTP feed instead of MCP?

Yes. /api/public/jobs.json returns paginated public job data as JSON and /jobs/feed.xml is an RSS feed of the most recently verified listings. Both are documented in the developer reference.

Next steps