Skip to main content

MCP integration: setup and scope

Model Context Protocol, or MCP, allows Claude Code to use approved tools and data sources beyond its built-in capabilities.

An MCP server can provide controlled access to systems such as:

  • Issue trackers
  • Source-control platforms
  • Documentation systems
  • Monitoring tools
  • Databases
  • Internal APIs
  • Design platforms
  • Approved enterprise services

How MCP works​

  1. Connect — Register an approved local or hosted MCP server with Claude Code.
  2. Discover — Claude identifies the tools and resources exposed by the server.
  3. Approve — Review requests, permissions, parameters, and the data involved.
  4. Execute — Claude invokes the approved tool and uses the returned result.
Enterprise approval required

Connect only MCP servers approved for enterprise use. Verify ownership, authentication, permissions, data handling, network access, and logging before enabling a server.

Add an approved HTTP server​

Run MCP configuration commands in the terminal, outside the interactive Claude Code session.

General structure:

claude mcp add --transport http <server-name> <server-url>

Example using the public Claude Code documentation server:

claude mcp add --transport http claude-code-docs https://code.claude.com/docs/mcp

The server name is a local label. Use a clear name that identifies the system or purpose.

Verify the connection​

List configured servers:

claude mcp list

Check a specific server:

claude mcp get claude-code-docs

Start Claude Code:

claude

Inside the session, inspect MCP availability:

/mcp

Then test with a read-only request:

Use the Claude Code documentation MCP server to find the official guidance for plan mode.

Summarise the result and identify the source used.
Do not perform any write actions.

Remove a server​

claude mcp remove claude-code-docs

Select the correct scope​

MCP configuration may be applied at different scopes:

  • Local: Available to the current user in the current project
  • Project: Shared through project configuration
  • User: Available to the current user across projects
  • Managed: Controlled centrally by the enterprise

Use the narrowest scope that meets the requirement.

Start with local and read-only access

For evaluation, begin with local scope and read-only capabilities. Expand access only after the integration, permissions, and business need have been reviewed.

MCP security checklist​

Before using any MCP server, verify:

  • The server comes from an approved and trusted source
  • Authentication follows enterprise standards
  • Only required permissions are granted
  • Secrets are stored outside source control
  • Tool descriptions and parameters are reviewed
  • Write and destructive actions require approval
  • External content is treated as untrusted input
  • Logs do not expose credentials or restricted information
  • Customer and proprietary data remain within approved boundaries
  • The server can be disabled or removed safely

Prompt-injection risk​

MCP servers that retrieve external content may expose Claude to malicious or misleading instructions embedded in that content.

Reduce risk by:

  1. Using approved servers and trusted data sources
  2. Starting with read-only access
  3. Reviewing tool requests before approval
  4. Separating retrieved data from trusted project instructions
  5. Preventing uncontrolled access to credentials and production systems
  6. Requiring human approval for write, delete, deploy, or communication actions
MCP integration checkpoint

Continue after connecting an approved server, verifying its scope and permissions, completing a read-only test, reviewing the returned source, and confirming that the server can be removed safely.