Connect
Optimize
Secure
Honeycomb MCP Server
for AI Agents
Production-ready Honeycomb MCP server with 68 extensible actions — plus built-in authentication, security, and optimized execution.
Honeycomb MCP Server
Built by 
StackOne
StackOne 
Coverage
68 Agent Actions
Create, read, update, and delete across Honeycomb — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Honeycomb MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Honeycomb tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Honeycomb call.
Tools Discovery →What is the Honeycomb MCP Server?
A Honeycomb MCP server lets AI agents read and write Honeycomb data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Honeycomb MCP server ships with 68 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Honeycomb MCP Tools and Actions
Every action from Honeycomb's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Boards
- Create Board
Create a new Board with query panels, SLO panels, or text panels.
- List Boards
List all dashboards (boards) for monitoring and visualizing observability data.
- Get Board
Get a single Board by its unique identifier.
- Update Board
Update a Board by specifying its ID and full details.
- Delete Board
Delete a public Board by specifying its ID.
Board Views
- Create Board View
Create a new view for a board with specified filters.
- List Board Views
Retrieve a list of all views for a board.
- Get Board View
Retrieve a single Board View by ID.
- Update Board View
Update a Board View by specifying its ID and full details.
- Delete Board View
Delete a Board View by specifying its ID.
Calculated Fields
- Create Calculated Field
Create a new calculated field (derived column) in a dataset.
- List Calculated Fields
List all calculated fields (derived columns) in a dataset.
- Get Calculated Field
Get a single calculated field by ID.
- Update Calculated Field
Update a calculated field's expression or metadata.
- Delete Calculated Field
Delete a calculated field from a dataset.
Columns
- Create Column
Create a new column in a dataset.
- List Columns
List all columns (fields/attributes/schema) in a dataset - shows available fields to query.
- Get Column
Get a single column by ID from a dataset.
- Update Column
Update a column's metadata in a dataset.
- Delete Column
Delete a column from a dataset.
Datasets
- Create Dataset
Create a Dataset in the environment associated with your API key.
- List Datasets
List all observability datasets and environments - shows available data containers in Honeycomb.
- Get Dataset
Get detailed information about a specific dataset by its slug identifier.
- Update Dataset
Update a Dataset's settings.
- Delete Dataset
Deletes a Dataset. This is an irreversible operation.
Dataset Definitions
- Get Dataset Definition
Get the dataset definition describing fields with special meaning.
- Update Dataset Definition
Update the dataset definition with fields having special meaning.
Events
- Create Event
Send/log a single event to a Honeycomb dataset - record telemetry, deployment events, or custom data.
- Create Batch Events
Send multiple events to a Honeycomb dataset in a single request.
Markers
- Create Marker
Create a marker to indicate a point in time on graphs.
- List Markers
List deployment markers, release annotations, and event markers on observability graphs.
- Update Marker
Update an existing marker.
- Delete Marker
Delete a marker from a dataset.
Marker Settings
- Create Marker Setting
Create a marker setting to define a group of similar markers.
- List Marker Settings
List all marker settings in a dataset.
- Update Marker Setting
Update an existing marker setting.
- Delete Marker Setting
Delete a marker setting from a dataset.
Annotations
- Create Query Annotation
Create a query annotation to associate a name and description to a query.
- List Query Annotations
List all query annotations in a dataset.
- Get Query Annotation
Get a single query annotation by ID.
- Update Query Annotation
Update an existing query annotation.
- Delete Query Annotation
Delete a query annotation.
Results
- Create Query Result
Run a query asynchronously and create a result. Enterprise feature.
- Get Query Result
Retrieve query results by result ID. Enterprise feature.
Recipients
- Create Recipient
Create a new notification recipient.
- List Recipients
List all notification recipients.
- Get Recipient
Get a single recipient by ID.
- Update Recipient
Update an existing notification recipient.
- Delete Recipient
Delete a notification recipient.
SLOs
- Create SLO
Create a new Service Level Objective.
- List SLOs
List all Service Level Objectives.
- Get SLO
Get a single SLO by ID.
- Update SLO
Update an existing SLO.
- Delete SLO
Delete an SLO.
Burn Alerts
- Create Burn Alert
Create a new burn alert for an SLO.
- List Burn Alerts
List all burn alerts for an SLO.
- Get Burn Alert
Get a single burn alert by ID.
- Update Burn Alert
Update an existing burn alert.
- Delete Burn Alert
Delete a burn alert from an SLO.
Triggers
- Create Trigger
Create a new trigger in a dataset.
- List Triggers
List all alerts and monitoring triggers configured in a dataset for notifications.
- Get Trigger
Get a single trigger by ID.
- Update Trigger
Update an existing trigger.
- Delete Trigger
Delete a trigger from a dataset.
Other
- Create Query
Create a query to analyze data - calculate latency, count events, aggregate metrics, analyze performance.
- Get Auth (Configuration Key)
Check Configuration API key permissions and authentication status.
- Get Auth (Ingest Key)
Check Ingest API key permissions and authentication status.
- Get Query
Retrieve a query specification by its ID.
Set Up Your Honeycomb MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Honeycomb in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Honeycomb MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Honeycomb MCP Server FAQ
Honeycomb MCP server vs direct API integration — what's the difference?
A Honeycomb MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Honeycomb. A Honeycomb MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Honeycomb at runtime. StackOne provides both.
How does Honeycomb authentication work for AI agents?
Honeycomb authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Honeycomb account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Honeycomb MCP tools vulnerable to prompt injection?
Yes — Honeycomb MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Honeycomb agent and how do I avoid it?
Context bloat happens when Honeycomb tool schemas and API responses eat your Honeycomb agent's memory, preventing it from reasoning effectively. A single Honeycomb query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Honeycomb agent can access?
Yes — you can limit which actions your Honeycomb agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Honeycomb MCP server?
Yes — you can create custom agent actions for your Honeycomb MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Honeycomb's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Honeycomb MCP server?
Skip a Honeycomb MCP server if your integration is purely software-to-software — direct Honeycomb API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Honeycomb actions at runtime.
What AI frameworks and AI clients does the StackOne Honeycomb MCP server support?
The StackOne Honeycomb MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.