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 local tradespeople across our 67 districts, and a professional calls you back.
Your request in 4 quick steps, without leaving the chat
- 01The tradeyour assistant suggests the trades that match your needs, chosen from the trades available on Kelki.
- 02Your job and timingpick from the same options as the “Call me back” form on kelki.ai (trade services, or “Other need” in a few words), then select your timing. You can also add extra notes.
- 03Your suburb or cityyour assistant checks your town, suburb, and postcode.
- 04Your contact details and confirmationname, phone number, and email, a quick summary, then your consent to receive a call back.
One click in your email, and your request is sent
Juste après, vous recevez un e‑mail de Kelki avec le récapitulatif de votre demande et un bouton « Confirmer ma demande ». Un clic, et votre demande part vers les professionnels du métier de votre secteur : un seul pro vous rappelle pour en parler avec vous. Not the right pro for you? Ask for another pro in one click. Le lien reste valable 48 heures; une demande non confirmée s’efface d’elle‑même, coordonnées comprises.
The service is completely free for you: tradespeople fund Kelki by paying 75 NZD 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: Customise › Connectors › “Add 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 and setup for Claude Code, Cursor, or VS Code: MCP connector. On kelki.ai, WebMCP‑compatible browsers also offer the “demander_rappel” tool: it fills in the “Call me back” form on the page, which you send yourself.
Agent Kelki: finds the right pro for you
On every kelki.ai page, the “Agent Kelki” chat bubble is ready to help: “I have a leak”, “I’m locked out”, “Looking for a caterer”. It identifies the trade, offers clickable options for services, timing, and your location, collects your details, and presents a summary: tick the consent box and submit your request, just like the “Call me back” form.
Your own AI agent can also run the search via the A2A (Agent2Agent) protocol: it asks the same questions, and you receive the “Confirm my request” email. One click, and your request is dispatched to local trade pros in your area.
Your data
The connector only receives what your assistant passes on for your request: the trade, the selected service (or your brief description), the urgency, the city and postcode, your name, phone number, email, any notes, and the name of the assistant used (e.g. “ChatGPT”). Your full conversation stays in your assistant: Kelki only receives these specific fields.
This information is used strictly to send you the confirmation email and, once confirmed, forward your request to local trade pros in your area. Any request not confirmed within 48 hours is deleted (leaving only the trade, service, timing, and town, with no personal details). Details, retention periods, and rights: privacy policy.
For developers and platforms
- Full connector documentation (the 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 stream, GetTask, CancelTask), no authentication; task marked input‑required on each question, with data payload (step, choices, expected fields, summary, consent text); once consented, creates request to confirm by email (completed task). Agent card: /.well‑known/agent‑card.json.
- Server card: /mcp/server‑card · ARD manifest: /.well‑known/ard.json · LLM intro: /llms.txt.
Got a question?
Email us at contact@kelki.ai: we reply to every message. Kelki is published by D.DESIGN & CONSEIL, Paris.