How to connect Dock certs to Claude Cowork

Trusted by teams atAWSGleanZoomAirtable

30 min · no commitment · see it on your stack

Dock certs 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 Dock certs account to Cowork via Composio Connect, enabling it to list all credentials issued this month, delete a credential by its ID, create a webhook for credential updates, and more such actions on your behalf without compromising your account security.

Also integrate Dock certs with

Connecting Dock certs 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 Dock certs account

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

For example, ask Cowork to:

  • "List all credentials issued this month"
  • "Delete a credential by its ID"
  • "Create a webhook for credential updates"

It will prompt you to authenticate and authorize access.

That's it. Composio's tools are now available in Cowork, and your Dock certs 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 Dock certs through MCP without you sharing account credentials directly with the agent.

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

The Dock certs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Dock certs account. It provides structured and secure access to your verifiable credentials and decentralized identity management, so your agent can perform actions like issuing credentials, managing API keys, retrieving credential details, and automating webhook notifications on your behalf.

  • Instant credential issuance and management: Easily have your agent issue new verifiable credentials, retrieve detailed credential metadata, or delete outdated credentials as needed.
  • Secure API key lifecycle management: Direct your agent to create, list, retrieve, or delete API keys, ensuring secure programmatic access for your organization.
  • Automated webhook setup and oversight: Let your agent create or delete webhook endpoints, so you can receive real-time event notifications from Dock certs to your own systems.
  • Credential retrieval and decryption: Ask your agent to fetch specific credentials by ID, with options for full retrieval if protected by a password, ensuring secure and flexible access.
  • Tag and metadata cleanup: Enable your agent to delete obsolete tags or credential metadata, keeping your Dock certs environment organized and up to date.

Supported Tools & Triggers

Tools
Create API KeyTool to create an API key.
Create WebhookTool to create a webhook endpoint.
Delete API KeyTool to delete a specific API key.
Delete CredentialTool to delete a verifiable credential.
Delete TagTool to delete a specific tag.
Delete WebhookTool to delete a specific webhook.
Retrieve API KeyTool to retrieve details of an API key.
Retrieve API KeysTool to list all API keys.
Retrieve CredentialTool to retrieve a verifiable credential by its unique ID.
Retrieve CredentialsTool to retrieve a list of credential metadata.
Retrieve DID DocumentTool to retrieve a DID Document by its DID.
Retrieve Revocation RegistriesTool to retrieve a list of revocation registries.
Retrieve WebhookTool to retrieve a specific webhook's details.
Retrieve WebhooksTool to list configured webhooks.
Verify Credential or PresentationTool to verify a verifiable credential or presentation.

How to build Dock certs MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Dock certs MCP?

With a standalone Dock certs MCP server, the agents and LLMs can only access a fixed set of Dock certs tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Dock certs 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 Dock certs tools.

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

Yes, absolutely. You can configure which Dock certs 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 Dock certs 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.