Honeycomb MCP Server for Pydantic AI 12 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Honeycomb through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Honeycomb "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in Honeycomb?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Honeycomb MCP Server
Connect your Honeycomb.io observability platform to any AI agent and take full control of your telemetry data, query specifications, and incident markers through natural conversation.
Pydantic AI validates every Honeycomb tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Dataset Oversight — List all event sources, retrieve detailed metadata, and monitor last access times for your datasets.
- Query Management — Define new query specifications and execute them to retrieve granular performance insights.
- Marker Automation — Create timeline annotations (e.g., for deployments or outages) to contextualize your data visualization.
- Schema Insights — List and inspect columns within specific datasets to understand your event structure.
- Team Collaboration — Access shared boards and retrieve information about your Honeycomb team configuration.
- Incident Analysis — Use AI to run complex queries and retrieve results for rapid troubleshooting and RCA.
The Honeycomb MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Honeycomb to Pydantic AI via MCP
Follow these steps to integrate the Honeycomb MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Honeycomb with type-safe schemas
Why Use Pydantic AI with the Honeycomb MCP Server
Pydantic AI provides unique advantages when paired with Honeycomb through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Honeycomb integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Honeycomb connection logic from agent behavior for testable, maintainable code
Honeycomb + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Honeycomb MCP Server delivers measurable value.
Type-safe data pipelines: query Honeycomb with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Honeycomb tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Honeycomb and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Honeycomb responses and write comprehensive agent tests
Honeycomb MCP Tools for Pydantic AI (12)
These 12 tools become available when you connect Honeycomb to Pydantic AI via MCP:
create_marker
Pass details as a JSON string in "body_json" (requires message). Use "__all__" for team-wide markers. Create a new marker (e.g., deploy, maintenance) on a dataset timeline
create_query_specification
Pass the specification as a JSON string in "query_json". Returns a query ID for execution. Create a new query specification for a dataset
get_dataset_details
Get metadata for a specific dataset
get_query_result
Retrieve the results of an executed query
get_team_details
Retrieve information about the Honeycomb team
list_dataset_columns
List all columns (fields) defined in a specific dataset
list_datasets
Use this to find the "slug" required for markers and queries. List all datasets in your Honeycomb team
list_honeycomb_boards
List all boards (dashboards) shared with the team
list_markers
List markers (annotations) for a dataset
list_queries
List query specifications for a specific dataset
list_triggers
List triggers (alerts) defined for a dataset
run_query
Poll for results using "get_query_result" with the returned result ID. Execute a query specification and return a result ID
Example Prompts for Honeycomb in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Honeycomb immediately.
"List all datasets and find one related to 'payment-gateway'."
"Create a marker on all datasets: 'Deploy v2.4.0 started'."
"Execute query ID 'q_99283' for the 'main-api' dataset."
Troubleshooting Honeycomb MCP Server with Pydantic AI
Common issues when connecting Honeycomb to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiHoneycomb + Pydantic AI FAQ
Common questions about integrating Honeycomb MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Honeycomb with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Honeycomb to Pydantic AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.