Skip to content

Level 3 · Guide 12

Configure Claude Connectors with least privilege

Before connecting a service, identify the data and tools it can access and whether it may read, write, or delete. Start with least privilege and a read-only test; external sending, deletion, purchase, contract, or permission changes require preview and separate approval.

Product features may change. Check the last verified date and official sources.

Core concepts to know first

Focus on the decisions these terms support in real work rather than memorizing them.

Core concepts

1. A Connector is a controlled data path

A connector inherits both service-side access and Claude-side tool permission. Review identity, accessible resources, action types, storage path, revocation, and logging as one end-to-end data flow. In this guide, the first observable move is to map service identity, resources, actions, and data destinations.

2. Source-service permissions still apply

Reduce access to read-only and a synthetic test resource. Preserve the approved input and the evidence behind the result so a reviewer can distinguish what the source says from what Claude inferred. This directly controls the risk that source-service permissions may be broader than expected.

3. Tool permission defines available actions

Preview every write effect and document revocation and approval. Record the decision and the remaining uncertainty instead of hiding it in polished prose. The review must explicitly test whether write scope can include delete or share actions.

4. Read permissions in three layers

Treat the possibility that revoking one layer may leave another authorization active as a required test case. The intended result is a connector map covering data flow, permission scope, and approval gates, not an unreviewed answer that merely looks complete.

5. Map the complete data flow

For Configure Claude Connectors with least privilege, the final concept joins the earlier checks into an operating boundary: use approved inputs, expose evidence and uncertainty, and stop before a consequential action. Ownership and a reproducible review determine whether a connector map covering data flow, permission scope, and approval gates may move beyond training.

Synthetic work scenario

How this applies at work

This scenario was written for learning and is not a real customer case.

A fictional team evaluates a calendar connector using a test calendar. It grants read-only access, confirms which calendars are visible, verifies revocation, and keeps event creation disabled in the Academy exercise.

The scenario is newly written for this guide and is neither a customer case nor a performance claim. Its specific deliverable is a connector map covering data flow, permission scope, and approval gates. A reviewer can reproduce the work from the synthetic inputs without access to customer, employee, health, contract, or confidential company data.

Try it yourself

Choose one small task and follow the steps. Confirm organizational policy and data boundaries before using sensitive materials.

  1. Step 1. Map service identity, resources, actions, and data destinations

    Map service identity, resources, actions, and data destinations. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  2. Step 2. Reduce access to read-only and a synthetic test resource

    Reduce access to read-only and a synthetic test resource. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  3. Step 3. Preview every write effect and document revocation and approval

    Preview every write effect and document revocation and approval. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

Completion checklist

Check only what you verified yourself. Every item must be checked before saving completion.

Completion checklist

Some items are still unchecked. Review the result again.

What could go wrong?

Plausible language does not guarantee accuracy. Compare the result with originals, calculations, permissions, and current information.

  • Source-service permissions may be broader than expected
  • Write scope can include delete or share actions
  • Revoking one layer may leave another authorization active

Boundaries that require human review

Academy practice stops at draft, preview, or approval pending. Actions with real impact require separate owner approval outside Academy.

What AI can do

  • Step 1. Map service identity, resources, actions, and data destinations
  • Step 2. Reduce access to read-only and a synthetic test resource
  • Step 3. Preview every write effect and document revocation and approval

What a person must approve

  • Applicable law, contract, organizational security policy, and explicit approval boundaries take priority. Stop and ask the responsible owner when they conflict.
  • Academy exercises never send, publish, purchase, delete, execute contracts, or change permissions. A responsible person performs any real action through a separate process.

This guide is educational and does not replace legal, security, or privacy judgment for your organization.

Questions about this guide

When is this guide complete?
It is complete when the stated outcome is ready and another reviewer can retrace the inputs, evidence, boundaries, and decision. The target outcome is “A connector map covering data flow, permission scope, and approval gates.”
May I practice with real company data?
No. Use synthetic material in the Academy. Real data requires a separate review of policy, legal basis, contracts, minimization, retention, deletion, and the approved environment.
What if the product screen differs from this guide?
Product behavior can change. Check the verification date and official sources, then retest the current account and plan with a small, low-risk example.

Official sources and further reading

Recheck the current product and policy status in these primary sources.

  1. Custom connectors using remote MCP · Claude Help Center
  2. Google Workspace connectors · Claude Help Center

Authorship and review

Author
QJC
Last verified
2026-07-23
Update sensitivity
High
Tested product surface
Official documentation and QJC training scenarios using synthetic data
Tested plan
Reconfirm feature and account availability in official sources on the day of use

Save progress

Completion and checklist items are saved only in this browser. They do not sync to other devices or browsers.

Academy does not collect or store work materials, prompts, or outputs. It runs no separate analytics scripts beyond basic server access logs.

QJC Claude Academy is unofficial educational content independently created and operated by QJC. It is not an official course operated, sponsored, certified, or affiliated with Anthropic. Claude and Anthropic are trademarks of Anthropic PBC.