How to Use the Kibana MCP in Pydantic AI

Q: How do I add Kibana MCP tools to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP URL and assign it to the toolsets array when defining your agent.

Build reliable Kibana workflows with Pydantic AI. This MCP Server provides type-safe validation for saved objects.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kibana MCP to Pydantic AI

Create your Vinkius account to connect Kibana to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kibana with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Kibana MCP Server operations

Silent API failures destroy observability stacks. Pydantic AI fixes this by validating every single response against strict schemas. When your agent calls `get_saved_object`, the framework ensures the returned JSON exactly matches your expected model before the agent takes another step. If Kibana returns an unexpected field format, the agent fails loudly. You won't end up with corrupted dashboards because a hallucinated parameter slipped through a `update_saved_object` request. Correctness takes priority over raw speed.

Deterministic connector management

Alerting connectors require precise configuration to work properly. Your agent uses `list_connectors` to audit existing webhook and email integrations. It parses the results through Pydantic models to guarantee all required authentication fields exist. Creating new integrations is just as strict. The agent executes `create_connector` only after validating the payload structure. You confidently deploy complex alerting pipelines knowing the underlying API contracts are strictly enforced.

Audit and clean up roles

Stale access permissions create massive security vulnerabilities over time. Your agent runs `list_roles` to pull the complete RBAC configuration. It evaluates the active privileges against your internal security policies using whatever LLM backend you prefer. Remediation happens immediately. Unused or overly permissive roles are removed via `delete_role`. Because Pydantic AI is model-agnostic, you swap between Anthropic for complex reasoning and a local model for basic validation without changing your tool setup.

Setup guide

Set up Kibana MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kibana-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kibana tools.",
)

result = await agent.run("List recent Kibana transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kibana. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kibana now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kibana MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP URL and assign it to the `toolsets` array when defining your agent.

Scripts break when APIs change. Pydantic AI enforces runtime validation on operations like `list_data_views`, ensuring your agent never acts on malformed or incomplete data.

The framework supports both SSE and Streamable HTTP transports. You get real-time execution feedback when running heavy tasks like `import_saved_objects`.

The framework is completely model-agnostic. You use GPT-4o for complex `resolve_import_errors` logic, or run a local Llama 3 instance for simple `get_space` queries.

This server accesses your internal RBAC definitions and user roles. Vinkius sandboxes the execution environment completely. The connection is ephemeral, meaning your security configurations vanish from memory the moment the request completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript