MCP Server

What is MCP?

Model Context Protocol (MCP) is an open-source standard for securely connecting AI applications to external systems and tools. Honeydew provides an MCP server that connects your AI coding assistant to the Honeydew Semantic Layer.

When to use

Discover and explore your warehouse tables, schemas, and semantic model definitions
Build and maintain your semantic model through natural conversation
Query your data with natural language from any MCP-compatible assistant

Installation

Server URL

Honeydew exposes the MCP Server API at https://api.honeydew.cloud/mcp/

If your organization uses a custom Honeydew hostname, replace the default URL with your tenant hostname. You can find the hostname in the Honeydew UI under Settings > MCP Server.

Authentication

There are two ways to authenticate with the Honeydew MCP Server: OAuth or HTTP Basic authentication. OAuth Authentication (recommended) Most clients support OAuth authentication. When you first connect, you’ll be prompted to:

Log in with your Honeydew account
Accept the OAuth authorization

The client then securely provides an access token for subsequent requests. HTTP Basic Authentication The MCP Server in HTTP Basic authentication mode requires an API Key for authentication. You need to provide a Base64-encoded string of your API Key and API Secret in the format API_KEY:API_SECRET.

If creating a new API Key for MCP Server access, you can copy the Base64-encoded string from the Honeydew Studio UI at the time of creation.

You can use the following command to generate the Base64-encoded string:

MacOS
Windows

echo -n '<API_KEY>:<API_SECRET>' | base64

Use PowerShell:

[Convert]::ToBase64String(
  [Text.Encoding]::UTF8.GetBytes(
    "<API_KEY>:<API_SECRET>"
  )
)

Provide the encoded string in the Authorization header as follows: Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>

Configuration

Each MCP Server request must include additional headers to specify the Honeydew workspace and branch to use.

Workspace: Set the Honeydew workspace
Branch: Set the Honeydew branch to use, such as prod or dev
Honeydew-Client: Provide a client identifier for tracking purposes (optional)
ReadonlyToolsOnly: Set to true to expose only read-only tools (optional)

Supported Clients

Claude Code

Setup instructions

Command line
JSON configuration
.mcp.json

Run the following command to add the Honeydew MCP server:

OAuth (recommended)
API Key

claude mcp add --transport http honeydew \
    https://api.honeydew.cloud/mcp/ \
    --header "Workspace: <your_workspace>" \
    --header "Branch: <branch>" \
    --header "Honeydew-Client: Claude-Code"

Launch Claude Code with claude. You’ll be prompted to authenticate with OAuth to Honeydew.

claude mcp add --transport http honeydew \
    https://api.honeydew.cloud/mcp/ \
    --header "Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>" \
    --header "Workspace: <your_workspace>" \
    --header "Branch: <branch>" \
    --header "Honeydew-Client: Claude-Code"

Save the following to honeydew-mcp.json:

OAuth (recommended)
API Key

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Claude-Code"
  }
}

Then register it with:

claude mcp add honeydew ./honeydew-mcp.json

Launch Claude Code with claude. You’ll be prompted to authenticate with OAuth to Honeydew.

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Claude-Code"
  }
}

Then register it with:

claude mcp add honeydew ./honeydew-mcp.json

Add the following to your .mcp.json file:

OAuth (recommended)
API Key

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Claude-Code"
      }
    }
  }
}

Launch Claude Code with claude. You’ll be prompted to authenticate with OAuth to Honeydew.

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Claude-Code"
      }
    }
  }
}

Using environment variablesTo avoid storing sensitive values directly in configuration files, Claude Code supports environment variable expansion using the ${VAR_NAME} syntax.Set the following environment variables:

HONEYDEW_WORKSPACE
HONEYDEW_BRANCH
HONEYDEW_API_KEY (API Key authentication only)

Then reference them in your configuration:

Command line
JSON configuration
.mcp.json

OAuth (recommended)
API Key

claude mcp add --transport http honeydew \
    https://api.honeydew.cloud/mcp/ \
    --header "Workspace: ${HONEYDEW_WORKSPACE}" \
    --header "Branch: ${HONEYDEW_BRANCH}" \
    --header "Honeydew-Client: Claude-Code"

claude mcp add --transport http honeydew \
    https://api.honeydew.cloud/mcp/ \
    --header "Authorization: Basic ${HONEYDEW_API_KEY}" \
    --header "Workspace: ${HONEYDEW_WORKSPACE}" \
    --header "Branch: ${HONEYDEW_BRANCH}" \
    --header "Honeydew-Client: Claude-Code"

OAuth (recommended)
API Key

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "${HONEYDEW_WORKSPACE}",
    "Branch": "${HONEYDEW_BRANCH}",
    "Honeydew-Client": "Claude-Code"
  }
}

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic ${HONEYDEW_API_KEY}",
    "Workspace": "${HONEYDEW_WORKSPACE}",
    "Branch": "${HONEYDEW_BRANCH}",
    "Honeydew-Client": "Claude-Code"
  }
}

OAuth (recommended)
API Key

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Workspace": "${HONEYDEW_WORKSPACE}",
        "Branch": "${HONEYDEW_BRANCH}",
        "Honeydew-Client": "Claude-Code"
      }
    }
  }
}

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Authorization": "Basic ${HONEYDEW_API_KEY}",
        "Workspace": "${HONEYDEW_WORKSPACE}",
        "Branch": "${HONEYDEW_BRANCH}",
        "Honeydew-Client": "Claude-Code"
      }
    }
  }
}

Claude Code resolves ${VAR_NAME} references at runtime from your environment.

AI Coding Agent Plugins

Honeydew provides a plugins repository with skills and tools for building semantic models and analyzing data through natural conversation.Add the marketplace to Claude Code:

/plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins

Then install the Honeydew plugins from the marketplace:

/plugin install semantic-modeling-tools@honeydew-ai
/plugin install data-analysis-tools@honeydew-ai

Honeydew Documentation MCP

Give Claude Code access to the Honeydew documentation through a separate MCP server. No authentication is required.

claude mcp add --transport http honeydew-docs \
    https://honeydew.ai/docs/mcp

Claude Desktop

Setup instructions

MCP Server

Open Claude Desktop
Go to Settings -> Developer
Click Edit Config
Add the following to claude_desktop_config.json:

OAuth (recommended)
API Key

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Claude-Desktop"
      }
    }
  }
}

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Claude-Desktop"
      }
    }
  }
}

AI Coding Agent Plugins

Honeydew provides a plugins repository with skills and tools for building semantic models and analyzing data through natural conversation.

Go to Settings -> Customize
Click Browse Plugins
Go to the Personal tab
Click the + icon and choose Add marketplace from GitHub
Enter honeydew-ai/honeydew-ai-claude-plugins in the input box
Two plugins appear: Semantic modeling tools and Data analysis tools. Install both.

Honeydew Documentation MCP

Give Claude Desktop access to the Honeydew documentation through a separate MCP server. No authentication is required.Add the following to claude_desktop_config.json alongside the main Honeydew MCP server:

{
  "mcpServers": {
    "honeydew-docs": {
      "type": "http",
      "url": "https://honeydew.ai/docs/mcp"
    }
  }
}

Cortex Code CLI

Setup instructions

MCP Server

Command line
JSON configuration
mcp.json

Run the following command to add the Honeydew MCP server:

OAuth (recommended)
API Key

cortex mcp add honeydew \
    https://api.honeydew.cloud/mcp/ \
    --type http \
    -H "Workspace: <your_workspace>" \
    -H "Branch: <branch>" \
    -H "Honeydew-Client: Cortex-Code"

Launch Cortex Code CLI with cortex. You’ll be prompted to authenticate with OAuth to Honeydew.

cortex mcp add honeydew \
    https://api.honeydew.cloud/mcp/ \
    --type http \
    -H "Authorization: Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>" \
    -H "Workspace: <your_workspace>" \
    -H "Branch: <branch>" \
    -H "Honeydew-Client: Cortex-Code"

Save the following to honeydew-mcp.json:

OAuth (recommended)
API Key

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Cortex-Code"
  }
}

Then register it with:

cortex mcp add honeydew ./honeydew-mcp.json --type http

Launch Cortex Code CLI with cortex. You’ll be prompted to authenticate with OAuth to Honeydew.

{
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Cortex-Code"
  }
}

Then register it with:

cortex mcp add honeydew ./honeydew-mcp.json --type http

Add the following to ~/.snowflake/cortex/mcp.json:

OAuth (recommended)
API Key

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Cortex-Code"
      }
    }
  }
}

Launch Cortex Code CLI with cortex. You’ll be prompted to authenticate with OAuth to Honeydew.

{
  "mcpServers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "Cortex-Code"
      }
    }
  }
}

Honeydew Documentation MCP

Give Cortex Code CLI access to the Honeydew documentation through a separate MCP server. No authentication is required.

cortex mcp add honeydew-docs \
    https://honeydew.ai/docs/mcp \
    --type http

Cursor

Setup instructions

MCP Server

Open the Cursor application
Go to Settings -> Cursor Settings -> Tools & MCP
Click New MCP Server

Add the following configuration:

OAuth (recommended)
API Key

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Cursor"
  }
}

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Cursor"
  }
}

Click Save

AI Coding Agent Plugins

Honeydew provides a plugins repository with skills and tools for building semantic models and analyzing data through natural conversation.

Go to Cursor Settings > Rules, Skills, Subagents
Click the +New button next to Rules
Select Add from GitHub
Enter the repository URL: https://github.com/honeydew-ai/honeydew-ai-coding-agents-plugins.git

Honeydew Documentation MCP

Give Cursor access to the Honeydew documentation through a separate MCP server. No authentication is required.

Go to Settings -> Cursor Settings -> Tools & MCP
Click New MCP Server

Add the following configuration:

{
  "name": "honeydew-docs",
  "type": "http",
  "url": "https://honeydew.ai/docs/mcp"
}

Click Save

GitHub Copilot CLI

Setup instructions

MCP Server

Launch GitHub Copilot CLI with copilot
Type /mcp add to open the server configuration form

Fill in the following fields:

Name: honeydew
Type: http
URL: https://api.honeydew.cloud/mcp/
HTTP Headers:

OAuth (recommended)
API Key

{
  "Workspace": "<your_workspace>",
  "Branch": "<branch>",
  "Honeydew-Client": "Copilot-CLI"
}

{
  "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
  "Workspace": "<your_workspace>",
  "Branch": "<branch>",
  "Honeydew-Client": "Copilot-CLI"
}

Press Ctrl+S to save

Use /mcp show to verify the server is connected.

AI Coding Agent Plugins

Honeydew provides a plugins repository with skills and tools for building semantic models and analyzing data through natural conversation.Add the marketplace to Copilot CLI:

/plugin marketplace add honeydew-ai/honeydew-ai-coding-agents-plugins

Then install the Honeydew plugins from the marketplace:

/plugin install semantic-modeling-tools@honeydew-ai-github-copilot-plugins
/plugin install data-analysis-tools@honeydew-ai-github-copilot-plugins

Honeydew Documentation MCP

Give Copilot CLI access to the Honeydew documentation through a separate MCP server. No authentication is required.

Launch GitHub Copilot CLI with copilot
Type /mcp add to open the server configuration form
Fill in the following fields:
- Name: honeydew-docs
- Type: http
- URL: https://honeydew.ai/docs/mcp
Press Ctrl+S to save

VS Code and GitHub Copilot

Setup instructions

MCP Server

Open the Command Palette with CMD+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux)
Select MCP: Add Server…
Choose HTTP (HTTP or Server-Sent Events)
Enter the Honeydew MCP server URL: https://api.honeydew.cloud/mcp/
Enter honeydew as the server name

This adds the server to your .vscode/mcp.json file. Open the file and add the required headers:

OAuth (recommended)
API Key

{
  "servers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "VSCode"
      }
    }
  }
}

{
  "servers": {
    "honeydew": {
      "type": "http",
      "url": "https://api.honeydew.cloud/mcp/",
      "headers": {
        "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
        "Workspace": "<your_workspace>",
        "Branch": "<branch>",
        "Honeydew-Client": "VSCode"
      }
    }
  }
}

Honeydew Documentation MCP

Give VS Code access to the Honeydew documentation through a separate MCP server. No authentication is required.Add the following to your .vscode/mcp.json:

{
  "servers": {
    "honeydew-docs": {
      "type": "http",
      "url": "https://honeydew.ai/docs/mcp"
    }
  }
}

Codex CLI

Setup instructions

MCP Server

Command line

codex mcp add honeydew \
    --url https://api.honeydew.cloud/mcp/

Then launch Codex with codex. You’ll be prompted to authenticate with OAuth to Honeydew.After adding the server, open the configuration file at ~/.codex/config.toml and add the required headers to the [mcp_servers.honeydew] section.TOML configurationAdd the following to ~/.codex/config.toml (or .codex/config.toml in a trusted project):

[mcp_servers.honeydew]
url = "https://api.honeydew.cloud/mcp/"

[mcp_servers.honeydew.http_headers]
Workspace = "<your_workspace>"
Branch = "<branch>"
Honeydew-Client = "Codex-CLI"

[mcp_servers.honeydew.env_http_headers]
Authorization = "HONEYDEW_AUTH"

Set the HONEYDEW_AUTH environment variable to Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET> (see Authentication).

Honeydew Documentation MCP

Give Codex CLI access to the Honeydew documentation through a separate MCP server. No authentication is required.

codex mcp add honeydew-docs \
    --url https://honeydew.ai/docs/mcp

Codex (Desktop)

Setup instructions

MCP Server

Open the Codex application
Go to Settings -> MCP Servers
Under Custom servers, click Add Server
Set the server name to honeydew
Choose Streamable HTTP as the transport type
Set the URL to https://api.honeydew.cloud/mcp/
Leave the Bearer token environment variable field empty
Add the following headers:
- Workspace: <workspace name>
- Branch: <branch name, e.g. prod or dev>
- Honeydew-Client: Codex
Configure authentication as follows: OAuth authentication Codex redirects you to authenticate with Honeydew when connecting. No additional configuration is needed. HTTP Basic authentication Add an Authorization header to the headers list above with the value Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET> (see Authentication).

Honeydew Documentation MCP

Give Codex access to the Honeydew documentation through a separate MCP server. No authentication is required.

Go to Settings -> MCP Servers
Under Custom servers, click Add Server
Set the server name to honeydew-docs
Choose Streamable HTTP as the transport type
Set the URL to https://honeydew.ai/docs/mcp

Antigravity

Setup instructions

MCP Server

Open the Antigravity editor
Click the … dropdown at the top of the agent panel
Click Manage MCP Servers
Click View raw config

Add the following to mcp_config.json:

OAuth (recommended)
API Key

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Antigravity"
  }
}

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "Antigravity"
  }
}

Save the file

Honeydew Documentation MCP

Give Antigravity access to the Honeydew documentation through a separate MCP server. No authentication is required.

Open the Antigravity editor
Click the … dropdown at the top of the agent panel
Click Manage MCP Servers
Click View raw config

Add the following to mcp_config.json:

{
  "name": "honeydew-docs",
  "type": "http",
  "url": "https://honeydew.ai/docs/mcp"
}

Save the file

Other Clients

Any MCP-compatible client can connect to the Honeydew MCP Server using the standard HTTP transport. Use the following JSON configuration as a starting point:

OAuth (recommended)
API Key

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "My-MCP-Client"
  }
}

{
  "name": "honeydew",
  "type": "http",
  "url": "https://api.honeydew.cloud/mcp/",
  "headers": {
    "Authorization": "Basic <YOUR_BASE64_ENCODED_API_KEY_AND_SECRET>",
    "Workspace": "<your_workspace>",
    "Branch": "<branch>",
    "Honeydew-Client": "My-MCP-Client"
  }
}

See Server URL, Authentication, and Configuration for details on each parameter.

Example Usage

Once connected, you can prompt your AI assistant with questions like:

“What entities are available in the semantic model?”
“Show me the attributes and metrics for the orders entity”
“What tables are in the analytics schema?”
“How many orders were placed last month?”
“Create a new metric for total revenue on the orders entity”
“What is the average order value by region for the last quarter?”

Troubleshooting

OAuth Authentication Problems

Verify your client supports OAuth, ensure you have the necessary Honeydew workspace permissions, and attempt re-authentication through your client’s MCP management interface. Re-authenticating in Claude Code Type /mcp, select the Honeydew MCP from the list, choose “Clear authentication” or “Authenticate”, then follow the browser OAuth prompts to reconnect to Honeydew.

Connection Issues

Confirm the MCP server URL matches https://api.honeydew.cloud/mcp/ and verify your client’s MCP configuration syntax is correct. If your organization uses a custom hostname, check that the URL matches your tenant hostname that appears in Settings > MCP Server in Honeydew Studio.

Missing Tools

Verify authentication succeeded, check your Honeydew workspace access permissions, and review your client’s console for error messages. For additional support, contact Honeydew support at support@honeydew.ai.

Tools Available

Tools marked as read-only do not modify the semantic model or the data warehouse.

To expose only read-only tools, set the ReadonlyToolsOnly: true header in your MCP server configuration. When enabled, the server returns only tools that do not modify the semantic model or the data warehouse.

Question & Analysis

`ask_question_get_data`

read-only Ask a data question in natural language and get the data results.

question

string

required

The natural language question to ask.

max_rows

number

Maximum number of rows to return.

domain

string

The domain to query against.

`ask_question_get_sql`

read-only Ask a data question in natural language and get the SQL query. You can then run the query in your data warehouse to get the results.

question

string

required

The natural language question to ask.

domain

string

The domain to query against.

`ask_deep_analysis_question`

read-only Ask a data question that performs a multi-step analysis. Supports follow-up questions using a conversation_id.

question

string

required

The natural language question to ask.

domain

string

required

The domain to query against.

conversation_id

string

ID of a previous conversation for follow-up questions.

Browse & Discovery

`list_entities`

read-only List all entities in the semantic model with their names, descriptions, and keys.

`get_entity`

read-only Get detailed information about an entity, including its attributes, metrics, datasets, relations, and YAML definition.

entity_name

string

required

The name of the entity.

`get_field`

read-only Get detailed information about a specific field (attribute or metric) within an entity, including its YAML definition.

entity_name

string

required

The name of the entity containing the field.

field_name

string

required

The name of the field.

`search_model`

read-only Search the semantic model for entities, attributes, metrics, datasets, dynamic datasets and domains, matching a query string.

query

string

required

The search query string.

full_match

boolean

default:"false"

Whether to require a full match.

Warehouse Discovery

`list_databases`

read-only List all databases available in the connected data warehouse.

`list_schemas`

read-only List all schemas in a specific database in the connected data warehouse.

database

string

required

The database name.

`list_tables`

read-only List tables/views in a specific database and schema in the connected data warehouse.

database

string

required

The database name.

schema

string

required

The schema name.

`get_table_info`

read-only Get detailed information about a warehouse table/view, including its columns and metadata.

database

string

required

The database name.

schema

string

required

The schema name.

table

string

required

The table name.

Semantic Model

`import_tables`

Import tables from the connected data warehouse into the semantic model. Each table becomes an entity with its columns as attributes.

tables

string[]

required

List of fully qualified table names in the format database.schema.table.

`create_entity`

Create a new entity in the semantic model from YAML definitions.

entity_yaml

string

required

The YAML definition for the entity.

dataset_yaml

string

required

The YAML definition for the dataset.

`create_object`

Create a new semantic model object from a YAML definition. Supported types: attribute, metric, dynamic dataset, domain, and global parameter.

yaml_text

string

required

The YAML definition of the object.

force_with_error

boolean

Create the object even if validation produces errors.

`update_object`

Update an existing semantic model object from a YAML definition. Supported types: entity, attribute, metric, dataset, dynamic dataset, domain, and global parameter.

yaml_text

string

required

The YAML definition of the object.

object_key

string

The key of the object to update.

force_with_error

boolean

Update the object even if validation produces errors.

`validate_object`

read-only Validate a semantic model object YAML definition without creating or updating it. Supported types: entity, attribute, metric, dataset, dynamic dataset, domain, and global parameter.

yaml_text

string

required

The YAML definition to validate.

object_key

string

The key of the object to validate against.

`delete_object`

Delete a semantic model object by its key.

object_key

string

required

The key of the object to delete.

force_with_error

boolean

Delete the object even if validation produces errors.

Query & Preview

`get_sql_from_fields`

read-only Generate the SQL query for a semantic layer query defined by attributes, metrics, and filters. Returns the SQL without executing it.

attributes

string[]

List of attribute names to include.

metrics

string[]

List of metric names to include.

filters

string[]

List of filter expressions.

order_by

string[]

List of fields to order by.

domain

string

The domain to query against.

`get_data_from_fields`

read-only Execute a semantic layer query defined by attributes, metrics, and filters, and return the resulting data.

attributes

string[]

List of attribute names to include.

metrics

string[]

List of metric names to include.

filters

string[]

List of filter expressions.

order_by

string[]

List of fields to order by.

domain

string

The domain to query against.

limit

number

default:"100"

Maximum number of rows to return.

offset

number

default:"0"

Number of rows to skip for pagination.

Quick Start

Migration Guides

Reference

Integrations

Security

Release Notes

​What is MCP?

​When to use

​Installation

​Server URL

​Authentication

​Configuration

​Supported Clients

​Claude Code

​MCP Server

​AI Coding Agent Plugins

​Honeydew Documentation MCP

​Claude Desktop

​MCP Server

​AI Coding Agent Plugins

​Honeydew Documentation MCP

​Cortex Code CLI

​MCP Server

​Honeydew Documentation MCP

​Cursor

​MCP Server

​AI Coding Agent Plugins

​Honeydew Documentation MCP

​GitHub Copilot CLI

​MCP Server

​AI Coding Agent Plugins

​Honeydew Documentation MCP

​VS Code and GitHub Copilot

​MCP Server

​Honeydew Documentation MCP

​Codex CLI

​MCP Server

​Honeydew Documentation MCP

​Codex (Desktop)

​MCP Server

​Honeydew Documentation MCP

​Antigravity

​MCP Server

​Honeydew Documentation MCP

​Other Clients

​Example Usage

​Troubleshooting

​OAuth Authentication Problems

​Connection Issues

​Missing Tools

​Tools Available

​Question & Analysis

​ask_question_get_data

​ask_question_get_sql

​ask_deep_analysis_question

​Browse & Discovery

​list_entities

​get_entity

​get_field

​search_model

​Warehouse Discovery

​list_databases

​list_schemas

​list_tables

​get_table_info

​Semantic Model

​import_tables

​create_entity

​create_object

​update_object

​validate_object

​delete_object

​Query & Preview

​get_sql_from_fields

​get_data_from_fields

What is MCP?

When to use

Installation

Server URL

Authentication

Configuration

Supported Clients

Claude Code

MCP Server

AI Coding Agent Plugins

Honeydew Documentation MCP

Claude Desktop

MCP Server

AI Coding Agent Plugins

Honeydew Documentation MCP

Cortex Code CLI

MCP Server

Honeydew Documentation MCP

Cursor

MCP Server

AI Coding Agent Plugins

Honeydew Documentation MCP

GitHub Copilot CLI

MCP Server

AI Coding Agent Plugins

Honeydew Documentation MCP

VS Code and GitHub Copilot

MCP Server

Honeydew Documentation MCP

Codex CLI

MCP Server

Honeydew Documentation MCP

Codex (Desktop)

MCP Server

Honeydew Documentation MCP

Antigravity

MCP Server

Honeydew Documentation MCP

Other Clients

Example Usage

Troubleshooting

OAuth Authentication Problems

Connection Issues

Missing Tools

Tools Available

Question & Analysis

`ask_question_get_data`

`ask_question_get_sql`

`ask_deep_analysis_question`

Browse & Discovery

`list_entities`

`get_entity`

`get_field`

`search_model`

Warehouse Discovery

`list_databases`

`list_schemas`

`list_tables`

`get_table_info`

Semantic Model

`import_tables`

`create_entity`

`create_object`

`update_object`

`validate_object`

`delete_object`

Query & Preview

`get_sql_from_fields`

`get_data_from_fields`