MCP Integration

The Model Context Protocol (MCP) is an open standard by Anthropic that lets AI assistants (Claude, Cursor, Windsurf, etc.) connect to external services and call real tools. Datronis exposes an MCP server so any MCP-compatible AI can search jobs, browse news, explore companies, query platform stats — and, with a personal access token, actually submit job applications, list your resumes, and check your application status on your behalf — all without writing a single line of integration code.

The MCP server is a single HTTP endpoint. All three HTTP methods are used by the protocol:

https://api.datronis.com/api/mcp

Add the following to your Claude Desktop configuration file. On macOS this is at ~/Library/Application Support/Claude/claude_desktop_config.json.

{
  "mcpServers": {
    "datronis": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.datronis.com/api/mcp"
      ]
    }
  }
}

These editors support HTTP MCP servers natively. Add the server URL in your editor's MCP settings panel:

{
  "mcpServers": {
    "datronis": {
      "url": "https://api.datronis.com/api/mcp",
      "type": "http"
    }
  }
}

The first 7 tools below are public (no API key required) — the AI can call them automatically based on your request. The remaining 6 require a personal access token (see the next section) since they act on your account: submitting applications, reading your resumes, checking your application history, drafting or revising news articles, and publishing translations of existing articles.

Publishing news through MCP follows a fixed, non-bypassable workflow: draft in English, classify, and only then decide whether it goes live or which other languages to publish it into.

• Step 1 — English draft — draft_news always creates the English version of the article first, regardless of which languages you eventually want it published in. Classification and any review both work from this English version as the source of truth.
• Step 2 — Automatic classification — an AI safety classifier reads the article and returns either "green" (uncontroversial — science, technology, business, sports, entertainment, culture, health, lifestyle) or "flagged" (partisan politics, elections, war or conflict, graphic violence, hate speech, misinformation, or anything likely to read as controversial or divisive to a general audience).
• If green — the article goes live in English immediately, and is also translated and published into any locales you listed in target_locales.
• If flagged — the article is created but stays unpublished. The tool call returns the classifier's reasoning. Nothing you can pass to draft_news forces it live from here — there is no override flag.
• Step 3 — Revise and resubmit (optional) — call resubmit_news with the same news_id and a revised title/body. This runs a brand-new classification against the revision and is logged as its own attempt, separate from the original. If the revision is now green, it publishes; if still flagged, it stays unpublished and can be resubmitted again.
• Ownership — only the account whose api_key originally called draft_news for a given article may call resubmit_news on it. A different (even valid) api_key is rejected.
• Languages are opt-in — omitting target_locales publishes English only. Pass the 2-letter locale codes you want (e.g. ["de", "ru"]) to also translate and publish into those languages in the same call.

apply_to_job, list_my_resumes, and get_my_applications act on your Datronis account, so they need to know who you are. Generate a personal access token from your account settings, then pass it as the api_key argument on any of these tool calls.

• Step 1 — Go to /app/api-keys/ while logged in and click "New Key".
• Step 2 — Copy the generated key (starts with dtk_) — it's shown only once.
• Step 3 — Pass it as api_key in your prompt or tool call, e.g. "apply to job X using api_key dtk_...".
• Revoking — Revoke a key anytime from the same page; it stops working immediately.

The MCP server also exposes a readable resource — the platform overview documentation — which AI assistants can read to understand the platform before calling tools:

platform://docs/overview

The server uses the Streamable HTTP transport (MCP spec 2025-03-26):

• Step 1 — Client sends POST /api/mcp with an initialize message (no session ID header).
• Step 2 — Server creates a session and returns the Mcp-Session-Id header.
• Step 3 — All subsequent tool calls include the Mcp-Session-Id header.
• Step 4 — Client can open a GET /api/mcp SSE stream for server-initiated notifications.
• Step 5 — Client sends DELETE /api/mcp to close the session when done.
• Auto-expiry — Sessions auto-expire after 30 minutes of inactivity.

# Step 1: Initialize a session
curl -X POST https://api.datronis.com/api/mcp \
  -H "Content-Type: application/json" \
  -D - \
  -d '{"jsonrpc":"2.0","method":"initialize","id":1,"params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'

# Note the Mcp-Session-Id in the response headers, then:

# Step 2: List available tools
curl -X POST https://api.datronis.com/api/mcp \
  -H "Content-Type: application/json" \
  -H "Mcp-Session-Id: <your-session-id>" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":2}'

# Step 3: Call search_jobs
curl -X POST https://api.datronis.com/api/mcp \
  -H "Content-Type: application/json" \
  -H "Mcp-Session-Id: <your-session-id>" \
  -d '{"jsonrpc":"2.0","method":"tools/call","id":3,"params":{"name":"search_jobs","arguments":{"q":"React","remote_type":"REMOTE","limit":5}}}'

The locale parameter in get_news and get_categories accepts a number from 1–24. draft_news/resubmit_news use 2-letter codes instead (e.g. "de", "ru") in target_locales — the same codes shown in this table.

Once connected, try these natural language prompts in any MCP-aware AI:

• "Find remote senior React developer jobs in Europe"
• "What are the latest tech news articles in English?"
• "Search for fintech companies actively hiring in London"
• "How many jobs and companies are on the platform?"
• "Get the job details for slug 'senior-frontend-engineer-acme-corp'"
• "List all available news categories"
• "Apply to the senior-frontend-engineer-acme-corp job using my Datronis account (api_key dtk_...)"
• "List my resumes on Datronis and tell me which one is my default"
• "Check the status of my job applications on Datronis"
• "Draft a news article on Datronis about [topic] and publish it in English and German (api_key dtk_...)"
• "My last draft_news call was flagged — here's a revised, neutral version, resubmit it under news_id 123"
• "Which published articles on Datronis are still missing a Finnish translation?"
• "Translate news_id 101 into Finnish and publish it using my api_key"