How to Connect Claude to External Tools: MCP Connectors Guide

Connect Claude to external tools through the MCP Connectors Directory — a centralized catalog built on the Model Context Protocol (MCP), an open standard for linking AI applications to third-party services. In a few clicks, you can give Claude live access to Slack, GitHub, Google Drive, Notion, Stripe, and more, letting it retrieve information and take actions on your behalf without you ever leaving the conversation.

What Is the MCP Connectors Directory?

The MCP Connectors Directory is a curated catalog of integrations available 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. Once you enable a connector, Claude can independently call that service's tools to retrieve information, take actions, or render interactive interfaces — without you needing to copy-paste data or switch tabs.

This turns Claude from a conversational assistant into an active collaborator that can execute multi-step workflows across connected systems on your behalf. For example, you can ask Claude to read a JIRA ticket, implement the described feature, and open a pull request on GitHub — all in a single prompt, across two connectors, without leaving the chat.

The directory is accessible on Pro, Max, Team, and Enterprise plans. Free users can access at least the Microsoft 365 connector and are limited to one custom connector. For the full picture of what's available, see Anthropic's guide to using connectors to extend Claude's capabilities.

How Do You Connect Claude to an External Tool Step by Step?

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' from the menu to see the directory and any connectors already configured.
4. Browse the directory, choose a connector, review its capabilities, and click 'Connect'.
5. Complete the OAuth authentication flow for that service — sign in and grant the requested permissions.
6. Use the toggle next to each connector to enable or disable it for the current conversation.

That's the core flow for any pre-built directory connector. The toggle in step 6 is per-conversation, so disabling a connector in one chat does not affect other chats or disconnect the integration globally — a useful detail for keeping work and personal contexts separate.

How Do You Add a Custom Connector to Claude?

If the service you need isn't in the directory, you can connect Claude to any tool that exposes a remote MCP server. The process differs slightly by plan:

On Pro or Max

1. Go to Customize > Connectors and click '+'.
2. Enter a name and the remote MCP server URL.
3. Optionally add OAuth credentials.
4. Click 'Add'.

On Team or Enterprise

1. An Owner or Primary Owner navigates to Organization Settings > Connectors and clicks 'Add'.
2. Enter the remote MCP server URL and optional OAuth credentials.
3. Each user then individually authenticates their own account — org-level enablement does not auto-connect individual accounts.

One important constraint: remote MCP servers must be publicly accessible over the internet. If your server is behind a corporate firewall or private network, you'll need to move it to a public endpoint or allowlist Anthropic's IP ranges. See Anthropic's custom connectors setup guide for the specifics.

What Can You Actually Do Once Claude Is Connected?

Here are concrete examples of what becomes possible when connectors are active:

• File and document retrieval: Ask Claude to find a specific budget report in Google Drive. It searches, locates, and summarizes the document in-line — no manual upload required.
• Cross-tool project management: A developer asks Claude to read a JIRA ticket, implement the described feature, and open a pull request on GitHub. Claude chains calls across both connectors in one conversation.
• Team communication automation: A project manager asks 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: An analyst asks Claude to display revenue trends from Stripe with a filterable region breakdown. An interactive connector renders a live dashboard with charts and dropdowns directly in the chat canvas.
• Monitoring and observability: An engineer asks 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.

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

The short version: use the directory for no-code or low-code integration in the claude.ai chat interface. Reach for custom connectors or the API when you're building something the directory doesn't cover.

What Are the Most Common Pitfalls When Connecting Claude to Tools?

Too many active connectors slow things down

When many connectors are enabled simultaneously, all their tools load into the context window by default. If you notice degraded response quality or speed, switch from 'Auto' to 'On demand' mode: hover over 'Connectors' in the '+' menu, select 'Tool access', and change the setting. In 'On demand' mode, tools are only loaded when Claude determines it needs them.

OAuth tokens expire

A previously working connector may return an authentication error after its access token expires. 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 than you intended

Claude inherits the OAuth permissions you grant during connection. During the OAuth flow, review the requested scopes carefully and grant only what is needed — for example, read-only access for search tasks. You can also disable specific write-action tools from the connector's tool list in settings. Enterprise deployments can enforce least-privilege access through role-based tool restrictions.

Team members can't see org-enabled connectors

On Team or Enterprise, an Owner must add the connector at the organizational level first. After that, each individual member must still go to their own Connectors settings and click 'Connect' to authenticate with their personal credentials. Org-level enablement does not auto-connect individual accounts.

Is the MCP Connectors Directory Worth Using for Teams?

For teams that already live in tools like Slack, GitHub, Notion, and Google Drive, the connectors directory removes a significant amount of manual context-switching. Instead of reading Slack, copying notes, opening GitHub, and creating issues by hand, a project manager can describe the workflow once and let Claude execute it across both systems.

Team and Enterprise plans add organizational governance controls, including role-based restrictions on which connectors and individual tools are available to different members. A security administrator can, for example, restrict the Jira connector to read-only access for most employees while granting write access only to engineering leads — and Claude will respect those policy boundaries, informing users when a requested action is blocked.

For a deeper look at what's available and how connectors are structured, the MCP connectors reference on Anthropic's support site covers the full catalog and capability details.