AI Agents & MCP Server

Ask your observability data anything. In plain English.

Kloudfuse MCP Server gives AI agents governed, natural-language access to your production metrics, traces, logs, and dependencies. Deployed in your VPC. Authenticated against your platform's access controls. Audit-logged every time.

Governed access for AI agents, not another side door.

Natural language to production queries.

Type a question in plain English. The MCP Server translates it into FuseQL, PromQL, or LogQL, executes against your data lake, and returns correlated results. No query language required.

Query Safety Mode blocks runaway queries.

Built-in query guardrails keep agent-generated queries bounded, and every AI-generated query is validated before it runs. The AI operates with the requesting user's permissions, never higher.

Works with Claude, Codex, Gemini, ChatGPT.

OAuth-based one-click install for Claude Desktop, Claude Code, OpenAI Codex, Gemini CLI, and ChatGPT. Authenticate once, connect instantly — one service account token, three parameters, minutes to deploy.


One question. A full investigation.

A platform deep dive: structured investigations, three layers of dependencies, hard safety rails, AI-assisted root cause, and the toolsets underneath.

One question. A full investigation.

Ask "Why is checkout-service slow?" and the MCP Server runs a structured sequence — entity identification, metric fetch, trace retrieval, log search, dependency check — and returns a correlated response with root cause candidates, not raw query output.

  • Language translation — plain English into FuseQL, PromQL or LogQL
  • Signal correlation — metrics, traces and logs in one pass
  • Conversation context — follow-ups like "now show me the last hour" work as expected
  • Ranked root causes — returned with confidence scores
A structured MCP investigation The agent identifies the entity, fetches metrics, retrieves traces and searches logs, then reports a root cause candidate: p99 latency rose 3.2 times after deploy v2.4.1, pod checkout-7f9 on saturated node-7. AI INVESTIGATION · CHECKOUT-SVC · LIVE identify entity · checkout-service40ms fetch metrics · p99 latency, error rate120ms retrieve traces · 1,204 spans310ms search logs · error fingerprints ROOT CAUSE CANDIDATE p99 latency rose 3.2× after deploy v2.4.1 pod checkout-7f9 · saturated node node-7



From the engineering team.

Quickstart: MCP Server in 15 minutes

Connect your AI client, authenticate with a service-account token, and ask your first natural-language question against production data. Guides for Claude Desktop, Codex, and Gemini CLI included.

Read the guide

MCP for observability: what enterprise deployments actually require

Query safety, access controls, audit logging, and what it takes to connect AI agents to production observability data without compromising governance.

Read the blog

Kloudfuse MCP vs Datadog MCP

VPC deployment, query safety controls, audit logging, OAuth integration, and AI client support. A side-by-side breakdown for teams evaluating both.

See the comparison


Bring an incident. We'll bring the platform.

Thirty minutes on your telemetry. The cause, before the call ends.