ClearFoxHow ClearFox works
From question to insight in seconds. Here's exactly how ClearFox connects your tools and delivers answers to your team.
System architecture
CEO, CFO, COO, VP's, Team Leads
Ask questions in natural language
Web interface, auth, RBAC, chat history, usage limits
Orchestrates tool calls, builds context, streams answers
30+ isolated Docker containers, one per tool
What happens when you ask a question
The entire process takes 10–30 seconds and is fully transparent. You can watch every step in real time.
You ask a question in plain language
"What are our biggest delivery bottlenecks and what financial risks should I know about this quarter?"
The AI plans its approach
It understands your question, checks which data sources are available for your role, and plans a sequence of tool calls.
Connectors query your tools
Each connector queries its tool via API: Jira for tickets, Stripe for payments, GitLab for code metrics, Salesforce for pipeline — in parallel where possible.
Results are synthesized
The AI gets structured data from each tool, cross-references it, finds patterns, and builds an answer with specific numbers and actionable recommendations.
You get a clear answer
The analysis shows up in your chat — with references to specific data sources. Ask follow-up questions to drill deeper into any finding.
Powered by the Model Context Protocol (MCP)
MCP is an open standard that enables AI models to interact with external tools safely and predictably. Works with any model — Anthropic, OpenAI, or local.
One connector per tool
Each business tool has a dedicated Docker container running its MCP connector. Isolated, secure, independently updatable.
Read and act
Connectors can read data and take actions — create tickets, send messages, open merge requests. You control which actions are allowed per role.
Up to 100 tool calls per query
The AI chains dozens of calls across multiple tools to build a deep, multi-source analysis — automatically.
Trigger agents from anything that speaks HTTP
Every ClearFox agent has its own per-agent webhook URL. Fire it from n8n, Make.com, Zapier, GitHub, alert managers, or your own services — everything is exposed under a stable, versioned /api/public/v1 contract.
Per-agent webhook URL
Each agent gets its own random 32-byte token. A leaked token only authorises that one agent. Rotate or revoke from the admin UI — existing callers stop working immediately.
Sync or async — your choice
Add ?wait=60 and the webhook blocks until the run finishes. Omit it and the agent keeps running server-side; poll the returned statusUrl later.
Idempotent retries
Send Idempotency-Keyon every request — ClearFox de-duplicates retries (n8n execution id, Zapier request id, etc.) so you never trigger the same agent twice.
Structured JSON output
Pin a JSON Schema per agent (Yes/No, Classification, Extraction templates included) and the response becomes a typed object. n8n / Zapier / Make map fields directly — no parsing prose.
One slug for everything
Trigger, polling and the chat URL all share the same conversation slug, so you can DM users a clickable link to the agent's chat in the portal — the same id you used to fire it.
Stable, versioned contract
Everything under /api/public/v1 is backward-compatible. Breaking changes ship as v2while v1 keeps working — safe to embed in long-lived integrations.
Pause for human input
Agents can call ask_human to pause and request a confirmation, missing value, or approval. Polling returns the question + areplyUrl— route it to Slack, a form, or a Teams channel; POST the answer back and the agent continues exactly where it stopped.
POST https://your-portal/api/public/v1/agent/webhook/<agentId>?token=<secret>&wait=60
Content-Type: application/json
Idempotency-Key: <unique-per-event-id>
{ "input": "process this lead", "metadata": { "lead": "acme", "amount": 1500 } }
→ 200 OK
{
"apiVersion": 1, "success": true, "status": "completed",
"slug": "abcd1234ef56",
"conversationUrl": "https://your-portal/c/abcd1234ef56",
"output": { "intent": "lead", "priority": "high", "summary": "..." }
}From access request to team rollout
No ML expertise needed. No public installer. We provision ClearFox on your infrastructure during onboarding.
We deploy on your servers
Our team installs the portal, database, and all connectors on infrastructure you control. Nothing is exposed to us afterwards.
Connect your tools
Add API keys in the admin panel. Set up SSO, create roles, and assign data sources to each team. ClearFox handles the rest.
Start asking questions
Invite your team. Everyone gets role-appropriate access. Ask anything — from quick metrics to deep cross-system analysis.
Stop discovering problems in meetings
Let ClearFox surface risks, explain context, and create actions — every morning, before your first coffee. Any question answered in seconds. Deployed on your servers.