Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent Read More

Honeycomb MCP Server
for AI Agents

Production-ready Honeycomb MCP server with 79 extensible actions — plus built-in authentication, security, and optimized execution.

Honeycomb logo
Honeycomb MCP Server
Built by StackOne StackOne

Coverage

79 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 79 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. Call create_query to get a query_id for query panels, and list_slos to get an slo_id for SLO panels.

  • List Boards

    List all dashboards (boards) for monitoring and visualizing observability data.

  • Get Board

    Get a single Board by its unique identifier. Call list_boards first to retrieve the boardId.

  • Update Board

    Update a Board by specifying its ID and full details. Call list_boards first to retrieve the boardId.

  • Delete Board

    Delete a public Board by specifying its ID. Call list_boards first to retrieve the boardId.

Board Views

  • Create Board View

    Create a new view for a board with specified filters. Call list_boards first to retrieve the boardId.

  • List Board Views

    Retrieve a list of all views for a board. Call list_boards first to retrieve the boardId.

  • Get Board View

    Retrieve a single Board View by ID. Call list_boards first to retrieve the boardId, then list_board_views to retrieve the viewId.

  • Update Board View

    Update a Board View by specifying its ID and full details. Call list_boards first to retrieve the boardId, then list_board_views to retrieve the viewId.

  • Delete Board View

    Delete a Board View by specifying its ID. Call list_boards first to retrieve the boardId, then list_board_views to retrieve the viewId.

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. Call list_calculated_fields first to retrieve the derivedColumnId.

  • Update Calculated Field

    Update a calculated field's expression or metadata. Call list_calculated_fields first to retrieve the derivedColumnId.

  • Delete Calculated Field

    Delete a calculated field from a dataset. Call list_calculated_fields first to retrieve the derivedColumnId.

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. Call list_columns first to retrieve the columnId.

  • Update Column

    Update a column's metadata in a dataset. Call list_columns first to retrieve the columnId.

  • Delete Column

    Delete a column from a dataset. Call list_columns first to retrieve the columnId.

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. Call list_datasets first to retrieve the datasetSlug.

  • Update Dataset

    Update a Dataset's settings. Call list_datasets first to retrieve the datasetSlug.

  • Delete Dataset

    Deletes a Dataset. This is an irreversible operation. Call list_datasets first to retrieve the datasetSlug.

Dataset Definitions

  • Get Dataset Definition

    Get the dataset definition describing fields with special meaning. Call list_datasets first to retrieve the datasetSlug.

  • Update Dataset Definition

    Update the dataset definition with fields having special meaning. Call list_datasets first to retrieve the datasetSlug.

Markers

  • Create Marker

    Create a marker to indicate a point in time on graphs. Call list_marker_settings to find valid type values that match existing marker settings.

  • List Markers

    List deployment markers, release annotations, and event markers on observability graphs.

  • Update Marker

    Update an existing marker's message, type, URL, or time range. Call list_markers first to retrieve the markerId.

  • Delete Marker

    Permanently delete a marker from a dataset. Call list_markers first to retrieve the markerId.

Marker Settings

  • Create Marker Setting

    Create a marker setting to define a group of similar markers with a shared color.

  • List Marker Settings

    List all marker settings in a dataset.

  • Update Marker Setting

    Update an existing marker setting's color. Call list_marker_settings first to retrieve the markerSettingId.

  • Delete Marker Setting

    Permanently delete a marker setting from a dataset. Call list_marker_settings first to retrieve the markerSettingId.

Annotations

  • Create Query Annotation

    Create a query annotation to associate a name and description to a query. Call create_query first to retrieve the query_id.

  • List Query Annotations

    List all query annotations in a dataset.

  • Get Query Annotation

    Get a single query annotation by ID. Call list_query_annotations first to retrieve the queryAnnotationId.

  • Update Query Annotation

    Update an existing query annotation's name or description. Note that query_id is required but cannot be changed. Call list_query_annotations first to retrieve the queryAnnotationId.

  • Delete Query Annotation

    Permanently delete a query annotation. Call list_query_annotations first to retrieve the queryAnnotationId.

Results

  • Create Query Result

    Execute a query asynchronously and get a result ID to poll. Requires Honeycomb Enterprise plan. Call create_query first to retrieve the query_id.

  • Get Query Result

    Retrieve query execution results by result ID. Requires Honeycomb Enterprise plan. Call create_query_result first to execute a query and retrieve the queryResultId.

Recipients

  • List Recipients

    List all notification recipients for the team.

  • Get Recipient

    Get a single recipient by ID. Call list_recipients first to retrieve the recipientId.

  • Delete Recipient

    Permanently delete a notification recipient. Call list_recipients first to retrieve the recipientId, and get_triggers_for_recipient to verify it is not in use.

Recipient (type Email)s

  • Create Recipient (type Email)

    Create an email notification recipient.

  • Update Recipient (type Email)

    Update an existing email notification recipient. Call list_recipients first to retrieve the recipientId.

Recipient (type PagerDuty)s

  • Create Recipient (type PagerDuty)

    Create a PagerDuty notification recipient.

  • Update Recipient (type PagerDuty)

    Update an existing PagerDuty notification recipient. Call list_recipients first to retrieve the recipientId.

Recipient (type Slack)s

  • Create Recipient (type Slack)

    Create a Slack notification recipient. Requires Slack OAuth flow completed in Honeycomb Integration Center.

  • Update Recipient (type Slack)

    Update an existing Slack notification recipient. Requires Slack OAuth flow completed in Honeycomb Integration Center. Call list_recipients first to retrieve the recipientId.

Recipient (type Webhook)s

  • Create Recipient (type Webhook)

    Create a webhook notification recipient.

  • Update Recipient (type Webhook)

    Update an existing webhook notification recipient. Call list_recipients first to retrieve the recipientId.

Recipient (type MSTeams Workflow)s

  • Create Recipient (type MSTeams Workflow)

    Create a Microsoft Teams workflow notification recipient.

  • Update Recipient (type MSTeams Workflow)

    Update an existing Microsoft Teams workflow notification recipient. Call list_recipients first to retrieve the recipientId.

SLOs

  • Create SLO

    Create a new Service Level Objective on a dataset. Call list_calculated_fields first to find a valid alias for the sli field.

  • List SLOs

    List all Service Level Objectives for a dataset or environment.

  • Get SLO

    Get a single SLO by ID. Call list_slos first to retrieve the sloId.

  • Update SLO

    Update an existing SLO by specifying its full details. Call list_slos first to retrieve the sloId, and list_calculated_fields to find a valid alias for the sli field.

  • Delete SLO

    Permanently delete an SLO and all its associated burn alerts. Call list_slos first to retrieve the sloId.

Burn Alerts

  • Create Burn Alert

    Create a new burn alert for an SLO. Call list_slos to get a valid slo ID, and list_recipients to get recipient IDs.

  • List Burn Alerts

    List all burn alerts for a specific SLO. Call list_slos to find the SLO to scope burn alert retrieval.

  • Get Burn Alert

    Get a single burn alert by ID. Call list_burn_alerts first to retrieve the burnAlertId.

  • Update Burn Alert

    Update an existing burn alert by specifying its full details. Call list_burn_alerts to retrieve the burnAlertId, list_slos to get the SLO ID, and list_recipients for recipient IDs.

  • Delete Burn Alert

    Permanently delete a burn alert from an SLO. Call list_burn_alerts first to retrieve the burnAlertId.

Triggers

  • Create Trigger

    Create a new trigger on a dataset or environment. Call list_recipients first to get recipient IDs to include in the recipients field.

  • List Triggers

    List all triggers configured in a dataset or environment.

  • Get Trigger

    Get a single trigger by ID. Call list_triggers first to retrieve available trigger IDs.

  • Update Trigger

    Update an existing trigger by specifying its full details. Call list_triggers first to get the triggerId, and call list_recipients to get any recipient IDs needed.

  • Delete Trigger

    Permanently delete a trigger from a dataset. Call list_triggers first to get the triggerId.

Other (9)

  • Create Event

    Send a single event to a Honeycomb dataset. Requires Ingest API Key authentication. Discouraged for production use — prefer create_batch_events for efficiency.

  • Create Batch Events (by JSON)

    Send multiple events to a Honeycomb dataset in a single request. Requires Ingest API Key authentication. Preferred over create_event for production use.

  • Create Query

    Create a query specification to analyze observability data. Does not execute — use create_query_result to run it.

  • 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. Call create_query first to create a query and retrieve the queryId.

  • Get Triggers For Recipient

    List all triggers associated with a specific recipient across the team. Call list_recipients first to retrieve the recipientId.

  • Get SLO Realtime Counts

    Get per-minute success and failure event counts for an SLO. Enterprise plan only. Call list_slos first to retrieve the sloId.

  • Get SLO Hourly Counts History

    Get hourly-bucketed historical event counts for an SLO. Enterprise plan only. Call list_slos first to retrieve the sloId.

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

Claude Desktop
{
  "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>"
      ]
    }
  }
}

More Data Infrastructure MCP Servers

Supabase

128+ actions

Grafana

89+ actions

Render

81+ actions

Snowflake

80+ actions

Sentry

74+ actions

Talend

52+ actions

Algolia

41+ actions

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.