Claude MCP Connectors for Workflow Automation: Full Guide

Claude MCP connectors give Claude the ability to reach into external services — reading files, posting messages, creating issues, querying dashboards — without you ever leaving the chat window. The MCP Connectors Directory is a centralized catalog of pre-built integrations built on the Model Context Protocol (MCP), an open standard Anthropic created for connecting AI to external tools and data sources. Once you enable a connector, Claude becomes an active collaborator that can execute multi-step workflows across connected systems on your behalf.

What Is the MCP Connectors Directory?

The directory is a browsable catalog inside claude.ai, Claude Desktop, and Claude mobile apps. Each listing describes what the connector does, what read and write capabilities it exposes, and which plans can use it. Services available include Slack, GitHub, Google Drive, Notion, Stripe, Figma, Canva, and more. Anthropic's official connectors documentation describes the directory as the primary way to discover, review, and enable integrations without writing any code.

Paid plans (Pro, Max, Team, Enterprise) get access to the full catalog of remote connectors. Free users can access at least the Microsoft 365 connector and are limited to one custom connector.

How Do You Set Up a Claude MCP Connector?

Setup takes about two minutes per connector. Here is the exact flow:

1. Open claude.ai (or Claude Desktop or the Claude mobile app).
2. Click the + button in the lower-left corner of the chat input, or type / to open the command menu.
3. Select Connectors to open the directory and see any connectors already configured.
4. Browse the directory, choose a connector, review its capabilities, and click Connect.
5. Complete the OAuth authentication flow — sign in to the service and grant the requested permissions.
6. Once connected, use the toggle next to each connector to enable or disable it for the current conversation.

The toggle is per-conversation, so disabling Slack in one chat does not disconnect it from other chats. This gives you precise control over which tools Claude can access in any given session.

What Workflows Can You Automate With MCP Connectors?

Because Claude can chain calls across multiple connectors in a single prompt, the automation possibilities go well beyond simple lookups. Here are concrete examples drawn from real use cases:

• Document retrieval: Ask Claude to find a specific budget report in Google Drive. Claude searches, locates, and summarizes the file inline — no manual upload required.
• Cross-tool development: Ask Claude to read a JIRA ticket, implement the described feature, and open a pull request on GitHub — all in one conversation.
• Communication automation: Ask Claude to collect action items from a Slack channel over the past week and create a GitHub issue for each one. Claude reads Slack and writes to GitHub automatically.
• Interactive data visualization: Ask Claude to display Stripe revenue trends for the past 30 days with a filterable region breakdown. An interactive connector can render a live dashboard with charts and dropdowns directly in the chat canvas.
• Observability checks: Ask Claude to check Sentry for errors and Statsig for feature flag usage related to a recently shipped feature. Claude queries both services and returns a consolidated report.

How Do You Automate a Multi-Step Workflow? (Worked Example)

The following example chains the Slack and GitHub connectors to convert planning notes into tracked issues — a workflow that normally requires manually reading Slack and then switching to GitHub.

1. Connect both the Slack connector and the GitHub connector from the directory and complete OAuth for each.
2. Enable both connectors for the current conversation via the + menu.
3. Send this prompt:

Summarize the action items from our #product-planning Slack channel
from the past week, then create a GitHub issue for each one
in the 'acme/roadmap' repo.

Claude reads recent messages from #product-planning, identifies action items, and creates GitHub issues with descriptive titles, bodies drawn from the Slack context, and an action-item label — without you switching between tools or copying notes manually.

When Should You Use Directory Connectors vs. Custom MCP Connectors?

The right choice depends on whether your target service is already in the directory and whether you want to manage server infrastructure.

Anthropic's custom connectors guide covers the full setup process for hosting your own remote MCP server, including how to handle OAuth credentials and firewall requirements.

What Are the Common Pitfalls and How Do You Fix Them?

A few issues come up repeatedly when people first start automating workflows with MCP connectors:

• Custom MCP server is unreachable: Remote MCP servers must be publicly accessible over the internet. If your server is behind a corporate firewall, move it to a public endpoint or allowlist Anthropic's IP ranges as described in the custom connectors support article.
• Performance degrades with many connectors: When 10 or more connectors are enabled simultaneously, all their tools load into the context window by default (Auto mode). Switch to On demand mode via + menu → Connectors → Tool access to load tools only when Claude determines it needs them.
• Authentication failed on a previously working connector: OAuth access tokens expire. Re-authenticate by going to Customize → Connectors, finding the affected connector, clicking the gear icon, selecting Reconnect, and completing the OAuth flow again.
• Claude can access more data than intended: Claude inherits the OAuth permissions you grant during connection. During the OAuth flow, review requested scopes carefully and grant only what is needed — for example, read-only for search tasks. You can also disable specific write-action tools from the connector's tool list in settings.
• Team or Enterprise members cannot see org-enabled connectors: An Owner or Primary Owner must first add the connector at the organizational level in Organization Settings → Connectors. After that, individual members must go to their own Connectors settings and click Connect to authenticate with their personal credentials. Org-level enablement does not auto-connect individual accounts.

How Does Enterprise Governance Work for MCP Connectors?

Team and Enterprise plans add organizational governance controls. Administrators can restrict which connectors and which individual tools within a connector are available to different roles. For example, a security administrator can restrict the Jira connector to read-only access for most employees while granting write access only to engineering leads. Claude respects these policy boundaries and informs users when a requested action is blocked by their role's permissions.

This role-based governance was expanded in April 2026, giving Enterprise administrators granular control at the individual tool level — not just the connector level — across custom roles.

Is the MCP Connectors Directory Worth Using for Automation?

If you regularly move data between tools manually — copying Slack notes into GitHub, uploading files to summarize, switching between dashboards — the directory connectors eliminate most of that friction. The no-code setup (OAuth only, no server to host) makes it accessible to non-developers, while the chaining capability means a single prompt can span multiple services. The per-conversation toggle and scope-limited OAuth keep the security model manageable.

The main limitation is the catalog: if your critical internal tool is not listed, you will need to build and host a custom remote MCP server. For teams on Team or Enterprise plans, the governance controls make it practical to roll out connectors organization-wide without losing oversight of what Claude can and cannot do on behalf of each role.

For a full list of available connectors and their capabilities, see the MCP connectors reference in Anthropic's support documentation.