Skip to content

Kelki in your AI assistant

Ask your AI assistant: "Find me a plumber for a leak under the sink". With the Kelki connector, ChatGPT, Claude or Le Chat prepares your request with you; once you confirm by email, it goes out to tradespeople across the 13 provinces and territories, and a professional calls you back.

Free · No obligation

Your request in 4 steps, without leaving your chat

  1. 01The tradeyour assistant suggests the trades that match your needs, chosen from the trades available on Kelki.
  2. 02Your need and timingyou pick from the same options as the “Call me back” form on kelki.ai (services for that trade, or “Other need” in a few words), then your timeframe. You can also add notes.
  3. 03Your cityyour assistant verifies the city and postal code.
  4. 04Your contact info and consentname, phone number, and email, a recap, and your consent to be called back.

One click in your email, and your request is sent

Right after, you get an email from Kelki with a summary of your request and a “Confirm my request” button. One click, and your request goes out to local pros in that trade: only one pro calls you back to discuss it. The link is valid for 48 hours; unconfirmed requests are automatically deleted, including your contact details.

The service is completely free for you: tradespeople fund Kelki by paying 65 CAD excluding tax for the requests they accept. The quote, appointment and final price are then arranged directly with the professional.

Add Kelki to your assistant

Connector URL: https://kelki.ai/mcp — no account or password required.

  • Claude: Customize › Connectors › “Add a custom connector”, paste the URL, select “no authentication”.
  • ChatGPT: Plugins › “+” › custom MCP server, paste the URL, no authentication (depending on your ChatGPT plan).
  • Le Chat: (Mistral): Connectors › “Add a connector” › “Custom MCP connector”, paste the URL.
https://kelki.ai/mcp

Step‑by‑step guide, plus setup for Claude Code, Cursor, or VS Code: MCP Connector. On kelki.ai, WebMCP‑compatible browsers also offer the “demander_rappel” tool: it fills out the on‑page “Call me back” form, which you submit yourself.

Kelki Agent: it finds the right pro for you

On every page of kelki.ai, the “Kelki Agent” bubble is ready: “I have a leak”, “I’m locked out”, “I need a caterer”. It identifies the trade, offers quick buttons for services, timing, and your city, collects your contact info, and shows a summary: you check the consent box and submit your request, just like the “Call me back” form.

Your own AI agent can also delegate the search via the A2A (Agent2Agent) protocol: it asks the same questions, then you receive the “Confirm my request” email. One click, and your request goes out to local pros in your area.

Your data

The connector only receives what your assistant passes along for your request: the trade, the selected service (or your need in a few words), the timeframe, the city and postal code, your name, your phone number, your email, any notes you added, and the assistant’s name (for instance, “ChatGPT”). Your conversation stays in your assistant: Kelki only receives these fields.

This information is used to send your confirmation email and, once you click, forward your request to local pros in that trade. Any request not confirmed within 48 hours is deleted (retaining only the trade, service, timing, and city, with no personal details). Details, retention periods, and rights: privacy policy.

For developers and platforms

  • Full connector documentation (all 4 tools, schemas, JSON‑RPC examples, installation): MCP Connector.
  • Remote MCP server: https://kelki.ai/mcp, Streamable HTTP transport, JSON responses, stateless, no authentication; protocol versions 2026‑07‑28, 2025‑11‑25, 2025‑06‑18, and 2025‑03‑26.
  • Tools: trouver_service, lister_prestations, verifier_lieu (read‑only), and demander_rappel (creates a request to confirm by email).
  • Resources: kelki://metiers, kelki://accord, kelki://metier/{metier}; prompt trouver_un_professionnel.
  • A2A Agent: https://kelki.ai/a2a, JSON‑RPC 2.0 (versions 1.0 and 0.3: SendMessage / message/send, SSE streams, GetTask, CancelTask), no authentication; task in input‑required state at each question, with data payload (step, choices, expected fields, summary, consent text); after consent, request pending email confirmation (task completed). Agent card: /.well‑known/agent‑card.json.
  • Server card: /mcp/server‑card · ARD manifest: /.well‑known/ard.json · LLM intro: /llms.txt.

Questions?

Email us at contact@kelki.ai: we reply to every message. Kelki is published by D.DESIGN & CONSEIL, based in Paris.

Have a project or a question?
Get a call back.

Free · No obligation · Describe your need in a few clicks
Call me back
What you needEverywhere in CanadaDescribe what you need · Free · No obligationCall me back