AskMarcel HVAC Technical Knowledge

AskMarcel — HVAC Technical Knowledge MCP Server

Manufacturer-sourced HVAC technical documentation for AI agents: search, diagnostics, error codes, procedures and product sheets across 126 brands and 905 models.

AskMarcel is a remote, hosted MCP server (Streamable HTTP). There is nothing to install or self-host — point your MCP client at the endpoint and authenticate. The server connects AI agents to real manufacturer documentation so answers cite the exact manual and page number instead of hallucinating.

• Endpoint: https://mcp.askmarcel.app
• Registry name: io.github.askmarcel/mcphvac
• Manifest: 1.3.1-beta.1 — 15 tools live in production
• Docs & API key: https://app.askmarcel.app/developers
• Reference: https://app.askmarcel.app/developers/reference
• Marcel Inside (B2B API / MCP): https://askmarcel.app/fr/connecteurs
• Free Developer tier: 250 API calls / month

---

Marcel Inside — branch it behind your bot

Use AskMarcel as Marcel Inside: plug manufacturer-sourced HVAC knowledge behind your existing chatbot, voicebot, or agent — without rebuilding your stack. Compatible with ManyChat, ElevenLabs, Voiceflow, Intercom, Claude, ChatGPT, Gemini, and custom MCP clients.

• Sales & pilot: https://askmarcel.app/fr/connecteurs (490€ pilot, Business 149€/mois HT)
• Developer sandbox: free tier — 250 calls/month at https://app.askmarcel.app/developers

---

Why AskMarcel

General-purpose LLMs guess at HVAC specifics — refrigerant charge, error-code meanings, wiring, fault trees. AskMarcel grounds every response in indexed manufacturer PDFs and returns the source page, so a field technician or an agent can trust and verify the answer. See HVAC-Bench for measured accuracy vs. raw LLM output.

• 126 brands · 905 models · 400,000+ error codes indexed
• Deterministic error-code lookup (not a guess)
• Strict SKU provenance (resolve_model, get_model_coverage, diagnose_v2) — no family substitution
• Sourced one-shot lookups (diagnose) and multi-turn guided troubleshooting for air-to-water heat pumps (diagnose_guided)
• LIVE Beta Harness sessions — stateful diagnostic loop with manufacturer DB lookup at session start (start_diagnostic … get_diagnostic_summary)
• FR / EN, focused on the European HVAC/RACH market

Harness session vs diagnose_guided

Surface	Use when	Quota
Harness session (start_diagnostic …)	Multi-turn field diagnostic on PAC Air/Eau or PAC Air/Air with hypotheses, discriminating next_action, technician journal	Once at session creation
diagnose_guided	Legacy guided loop for PAC Air/Eau only — server-sealed state via continuation	Per turn
diagnose_v2	One-shot strict SKU lookup	Per successful call
diagnose	One-shot lookup without SKU gate	Per successful call

Harness Beta is live in production (DIAGNOSTIC_SESSIONS_PUBLIC=true). At start_diagnostic, the server looks up error codes in technical_error_codes (manufacturer DB) and journals the result — not only pack fallback maps. Active packs: pac_air_eau and pac_air_air at 0.0.1 (mutable during Beta).

---

Tools

The server exposes 15 tools (10 GA + 5 Beta Harness session). Full reference in docs/tools.md.

GA (10)

Tool	What it does
search_technical_docs	Semantic search over technical documentation (≤10 excerpts). Filter by brand, model, error_code.
get_procedure	Retrieve a full procedure by chunk_id.
get_error_code	Deterministic lookup by brand + error_code (optional model).
get_product_sheet	Product sheet: specs, composition, frequent error codes, by brand + model.
get_pdf_page_snapshot	Signed, 5-minute URL to a specific PDF page (document_id + page).
diagnose	One-shot sourced lookup from a symptom or error code (excerpt + steps + citation).
diagnose_v2	Same lookup with strict SKU provenance. Abstains (diagnostic: null) if no approved exact-model manual exists.
resolve_model	Resolve brand + model to a canonical SKU. Exact or alias only — never a series LIKE.
get_model_coverage	Documentary flags for a resolved SKU: exact_manual, error_code_covered, market_verified.
diagnose_guided	Multi-turn guided troubleshooting for air-to-water heat pumps (legacy; quota per turn).

Beta — Harness session (5)

Tool	What it does
start_diagnostic	Open a stateful Harness session. Manufacturer error-code lookup at start. Quota on creation.
get_diagnostic	Read current session projection (hypotheses, next_action, fault code).
respond_to_diagnostic	Append typed observation, measurement, or technician assessment.
close_diagnostic	Close session with optional reason (verification not required).
get_diagnostic_summary	Deterministic exportable summary from the session journal.

Stability: beta · release_channel: beta on responses · qualified HVAC professional required.

---

Quick start

1. Get an API key

Create a free key at https://app.askmarcel.app/developers (250 calls/month on the Developer tier). The server also supports OAuth 2.0 (PKCE + Dynamic Client Registration) for clients that discover auth automatically.

2. Connect your MCP client

Ready-to-use configs live in examples/. The general form for any Streamable HTTP MCP client:

{
  "mcpServers": {
    "askmarcel": {
      "type": "streamable-http",
      "url": "https://mcp.askmarcel.app",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Claude Desktop / Cursor / VS Code: see the matching file in examples/. Replace YOUR_API_KEY with your key.

3. Ask a question

Once connected, prompt naturally, e.g.:

"Daikin Altherma showing error U4 — what does it mean and how do I clear it?"

The agent calls resolve_model / diagnose_v2 (or get_error_code / diagnose) and returns the cause, the fix steps, and the source manual page — or an explicit abstention when no exact manual exists.

For a full field diagnostic loop on a heat pump, use start_diagnostic → respond_to_diagnostic → close_diagnostic (see skill hvac-harnais-session).

---

MCP vs Chat API

AskMarcel exposes two separate integration surfaces — do not mix their protocols:

Surface	Endpoint	Protocol	Use case
MCP server (this repo)	https://mcp.askmarcel.app	JSON-RPC Streamable HTTP (tools/call)	Connect Claude, Cursor, VS Code, or any MCP client to HVAC tools
Chat API (web / mobile / extension)	https://app.askmarcel.app/api/chat	AI SDK v5 SSE (UIMessageStream)	Full conversational UI with streaming, tools, and document blocks

The MCP server does not use the AI SDK chat stream (text-delta, data-* parts). If you build a custom agent with the Vercel AI SDK, use MCP tools via JSON-RPC — not the web chat endpoint.

---

Authentication

Two supported methods (details in docs/authentication.md):

1. API key (Bearer): Authorization: Bearer YOUR_API_KEY
2. OAuth 2.0: discovery via https://mcp.askmarcel.app/.well-known/oauth-protected-resource

---

Claude Skills

The skills/ folder contains ready-to-use Agent Skills that wrap these tools into HVAC workflows:

• hvac-error-lookup — turn a brand + error code into a sourced explanation and fix.
• hvac-diagnostic — one-shot symptom lookup with citations (diagnose).
• hvac-guided-diagnosis — multi-turn guided troubleshooting for air-to-water heat pumps (diagnose_guided).
• hvac-harnais-session — Beta Harness session loop (start_diagnostic … close_diagnostic).

---

REST API SDK

For custom agents that call the REST API directly (not MCP), use the npm package @askmarcel/sdk — includes Harness session methods (startDiagnosticSession, respondToDiagnosticSession, …), guidedTurn() for POST /v1/diagnostic/turn, plus resolveModel() / getModelCoverage() / V2 diagnose.

---

Links

• MCP endpoint — https://mcp.askmarcel.app
• Developer portal & API key — https://app.askmarcel.app/developers
• API reference — https://app.askmarcel.app/developers/reference
• Marcel Inside (B2B) — https://askmarcel.app/fr/connecteurs
• Templates — https://app.askmarcel.app/templates
• Official MCP Registry — io.github.askmarcel/mcphvac
• Website — https://askmarcel.app

---

License

Code and content in this repository (documentation, examples, skills) are released under the MIT License. The AskMarcel hosted service and its underlying data are proprietary and governed by the AskMarcel terms.

---

🇫🇷 En français

AskMarcel est un serveur MCP distant et hébergé (Streamable HTTP) qui connecte les agents IA à la documentation technique HVAC/RACH sourcée constructeur. Rien à installer : on pointe son client MCP sur l'endpoint et on s'authentifie. Chaque réponse cite le manuel et la page exacte plutôt que d'halluciner.

• Endpoint : https://mcp.askmarcel.app
• Nom registre : io.github.askmarcel/mcphvac
• Manifeste : 1.3.1-beta.1 — 15 outils en production
• Doc & clé API : https://app.askmarcel.app/developers
• Marcel Inside (B2B) : https://askmarcel.app/fr/connecteurs
• Tier Developer gratuit : 250 appels / mois
• Couverture : 126 marques · 905 modèles · 400 000+ codes erreur indexés

Marcel Inside — branchez la base AskMarcel derrière votre chatbot, voicebot ou agent existant. Pilote 490€ · Business 149€/mois HT · tier Developer gratuit pour tester.

15 outils : 10 GA (search_technical_docs, get_procedure, get_error_code, get_product_sheet, get_pdf_page_snapshot, diagnose, diagnose_v2, resolve_model, get_model_coverage, diagnose_guided) + 5 session Harnais Beta (start_diagnostic, get_diagnostic, respond_to_diagnostic, close_diagnostic, get_diagnostic_summary).

Harnais Beta LIVE : lookup DB fabricant (technical_error_codes) au start_diagnostic, packs pac_air_eau / pac_air_air 0.0.1, quota à la création de session seulement. Distinct de diagnose_guided (guidé legacy PAC Air/Eau, quota par tour).

Skills : lookup code erreur, diagnostic one-shot, guidé PAC, session Harnais — voir skills/.

SDK REST (npm) : @askmarcel/sdk — sessions Harnais + guidedTurn() + API v2.

Connexion rapide : créez une clé sur https://app.askmarcel.app/developers, puis utilisez une des configs du dossier examples/ (Claude Desktop, Cursor, VS Code). Remplacez YOUR_API_KEY par votre clé.

MCP vs Chat API : ce dépôt documente le serveur MCP (JSON-RPC sur mcp.askmarcel.app). Le chat web/mobile utilise une API distincte (SSE AI SDK v5 sur /api/chat) — les deux protocoles ne sont pas interchangeables.

Détails des outils : docs/tools.md · Authentification : docs/authentication.md.