How to connect Honeyhive to Claude Cowork

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Honeyhive logo
Claude Cowork logo
divider

Introduction

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.

This guide walks you through the easiest and most secure way to connect your Honeyhive account to Cowork via Composio Connect, enabling it to add new datapoints to your evaluation dataset, list all datasets in your Honeyhive project, log a batch of model events for analysis, and more such actions on your behalf without compromising your account security.

Also integrate Honeyhive with

Connecting Honeyhive to Claude Cowork

1. Open Customize

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

Claude Desktop connectors screen with Add custom connector selected

2. Add the Composio MCP server

Click Add custom connector and paste in the Composio MCP server URL:

bash
https://connect.composio.dev/mcp
Add custom connector dialog with Composio MCP server URL

3. Authorize in your browser

Click Connect. You'll be redirected to a browser window where you can authorize Composio to continue.

Composio authorization screen for Claude Cowork

4. Connect your Honeyhive account

Back in Cowork, ask the agent to connect to Honeyhive or give it any Honeyhive-related task.

For example, ask Cowork to:

  • "Add new datapoints to your evaluation dataset"
  • "List all datasets in your Honeyhive project"
  • "Log a batch of model events for analysis"

It will prompt you to authenticate and authorize access.

That's it. Composio's tools are now available in Cowork, and your Honeyhive account is ready to use.

What is Claude Cowork?

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.

With Composio Connect, Cowork can securely access apps like Honeyhive through MCP without you sharing account credentials directly with the agent.

What is the Honeyhive MCP server, and what's possible with it?

The Honeyhive MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Honeyhive account. It provides structured and secure access to your AI observability platform, so your agent can perform actions like managing datasets, logging model and tool events, evaluating runs, and configuring project settings on your behalf.

  • Dataset management and organization: Create, retrieve, and delete datasets for your AI projects, helping you maintain organized and up-to-date evaluation data.
  • Efficient event logging: Log batches of model or external tool events, enabling comprehensive tracking and analysis of AI system interactions in real-time.
  • Data curation and cleanup: Add new datapoints to datasets or remove specific datapoints, ensuring your evaluation data remains accurate and relevant.
  • Streamlined evaluation workflows: Mark evaluation runs as completed and fetch project configuration details, making it easy to track progress and update run statuses automatically.

Supported Tools & Triggers

Tools
Add datapoints to datasetTool to add datapoints to a dataset.
Compare Experiment RunsTool to retrieve experiment comparison between two evaluation runs.
Compare Runs EventsTool to compare events between two experiment runs side-by-side.
Batch Create DatapointsTool to create multiple datapoints in a single batch operation.
Create Batch Model EventsTool to create multiple model events in a single request.
Create Batch Tool EventsTool to log a batch of external API calls as tool events.
Create ConfigurationCreates a new configuration in HoneyHive for managing LLM or pipeline settings.
Create DatapointTool to create a new datapoint with input-output pairs.
Create DatasetTool to create a dataset.
Create EventTool to create a new event in HoneyHive to track execution of different parts of your application.
Create MetricTool to create a new metric in HoneyHive.
Create Model EventTool to create a new model event to log LLM call data.
Create ToolCreates a new tool definition in a HoneyHive project.
Delete DatapointTool to delete a specific datapoint by its ID.
Delete DatasetTool to delete a dataset by ID.
End Evaluation RunTool to update an evaluation run's status and metadata.
Get ConfigurationsTool to retrieve a list of configurations.
Get DatasetsRetrieve datasets from HoneyHive for a specified project.
Get EventsTool to query events with filters and projections from HoneyHive.
Get Events By Session IDTool to retrieve the complete tree of nested events for a specific session.
Get Events ChartTool to retrieve charting and analytics data for events over time.
Get MetricsRetrieves all metrics associated with a HoneyHive project.
Get ProjectsTool to retrieve all projects in the HoneyHive account.
Get Evaluation Run DetailsTool to get details of an evaluation run by its UUID.
Get Run MetricsTool to get event metrics for an experiment run.
Get Evaluation RunsTool to retrieve a list of evaluation runs from HoneyHive.
Get Runs SchemaTool to retrieve the schema for experiment runs in HoneyHive.
Get SessionRetrieve a complete session tree by session ID from HoneyHive.
List ToolsTool to list all available Honeyhive tools.
Retrieve DatapointRetrieve a specific datapoint by its ID from HoneyHive.
Retrieve DatapointsRetrieve datapoints from a HoneyHive project.
Retrieve EventsRetrieve and export events from a HoneyHive project.
Retrieve Experiment ResultTool to retrieve the result of a specific experiment run.
Start Evaluation RunCreates a new evaluation run to group and track multiple session events for analysis.
Start SessionStart a new HoneyHive session for tracing and observability.
Update ConfigurationTool to update an existing HoneyHive configuration.
Update DatapointUpdate an existing datapoint by ID.
Update DatasetTool to update an existing dataset.
Update EventUpdate an existing HoneyHive event by ID.
Update MetricTool to update an existing metric.
Update ProjectUpdates an existing HoneyHive project's name or description.
Update ToolTool to update an existing tool in HoneyHive.

How to build Honeyhive MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Honeyhive MCP?

With a standalone Honeyhive MCP server, the agents and LLMs can only access a fixed set of Honeyhive tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Honeyhive and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Claude Cowork?

Yes, you can. Claude Cowork fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Honeyhive tools.

Can I manage the permissions and scopes for Honeyhive while using Tool Router?

Yes, absolutely. You can configure which Honeyhive scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Honeyhive data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.