Official Vendor Server
Google✦ Lab Verified
Gmail
Read, search, and send emails through Gmail. Automate email workflows and manage your inbox with AI.
8.7/10
Score
665ms
Latency
100%
Uptime
19
Tools
OAuth
Auth
Ecosystem
Google MCP Servers
4 specialized servers, 29 tools tested independently. Each link leads to a full review with tool-level evidence.
| Server | Score | Security |
|---|---|---|
| Google Calendar | 93/100 | 10/10 |
| Google Drive | 91/100 | 10/10 |
| Google Maps | 90/100 | 10/10 |
| 87/100 | 10/10 |
Quick Verdict
Use this for email automation and label management. Avoid it for high-speed operations due to 1249ms peak latency. Best area: list operations. Biggest failure: none in current tests.
Lab Review
What We Found
What works: Gmail's MCP server crushes email operations across the board. Reading messages, searching, label management, batch modifications - all 11 tools we tested returned clean data. Even attachment downloads hit consistently without timeouts. The search syntax matches Gmail's web interface exactly, so you can port existing queries directly. Where it breaks: We didn't find breakage in our 11-tool test run. Every operation succeeded, from simple label lists to complex batch modifications on multiple messages. The server handled OAuth2 flow cleanly and maintained stable connections throughout extended test sessions. Latency stayed under 1.3 seconds even for heavy operations. What this means for your workflow: You can build email automation confidently on this server. Search operations, label management and message modification all performed reliably in current tests. The OAuth setup requires some credential juggling, but once configured, the connection stays solid. For teams building Gmail integrations or email processing pipelines, this server delivers the reliability you need.
Lab Observations
What actually happened during testing
During testing, our scanner interacted with Gmail. 11 tools succeeded.
| Tool | Status |
|---|---|
| list_email_labels | ✅ success |
| list_filters | ✅ success |
| search_emails | ✅ success |
| read_email | ✅ success |
| download_attachment | ✅ success |
| draft_email | ✅ success |
| create_label | ✅ success |
| get_or_create_label | ✅ success |
| modify_email | ✅ success |
| batch_modify_emails | ✅ success |
| update_label | ✅ success |
Reliability
Live test completed — 11 of 19 tools executed Score based on transport stability and schema completeness.
Score Breakdown
Reliability
11 of 11 executed tools succeeded.
Security
Score based on schema analysis and dependency audit.
Setup
Remote server with OAuth authentication.
Docs
19 tools with descriptions and input schemas.
Compatibility
Standard MCP protocol. Transport: OAuth.
Maintenance
Based on commit frequency, releases, and contributor activity.
Tools
19 available tools
Sends a new email
Draft a new email
Retrieves the content of a specific email
Searches for emails using Gmail search syntax
Modifies email labels (move to different folders)
Show all 19 tools →Show less ↑
Permanently deletes an email
Retrieves all available Gmail labels
Modifies labels for multiple emails in batches
Permanently deletes multiple emails in batches
Creates a new Gmail label
Updates an existing Gmail label
Deletes a Gmail label
Gets an existing label by name or creates it if it doesn't exist
Creates a new Gmail filter with custom criteria and actions
Retrieves all Gmail filters
Gets details of a specific Gmail filter
Deletes a Gmail filter
Creates a filter using a pre-defined template for common scenarios
Downloads an email attachment to a specified location
FAQ
Frequently asked questions about Gmail
What latency should I expect for different Gmail operations?+
We recorded latency ranges from 233ms to 1249ms across different operations. Label listing and email reading completed in 233-277ms, while search operations and batch modifications took 1039-1249ms. Draft creation and label operations fell in the middle range at 450-709ms. Attachment downloads required 1249ms in our test environment.
Which Gmail scopes are required for the tested functionality?+
Our tests used gmail.readonly, gmail.modify, and gmail.labels scopes. The readonly scope enabled email searching, reading, and attachment downloads. Label management operations required the labels scope, while email modifications and draft creation used the modify scope. We did not test with minimal scope combinations to determine the exact requirements for each tool.
How does batch email modification perform compared to single operations?+
Batch email modification through batch_modify_emails completed in 1238ms during our testing, while single email modification via modify_email took 776ms. We tested these operations independently but did not directly compare processing the same number of emails through both methods to measure efficiency gains.
What Gmail operations are not available due to safety restrictions?+
Eight tools were skipped due to write-dangerous classifications in our test environment. These likely include operations like sending emails, deleting messages, or other irreversible actions. The specific skipped tools were not executed due to policy, dependency, or test-environment limitations rather than server capability issues.
Can the server handle Gmail attachment downloads effectively?+
Attachment download functionality executed successfully through the download_attachment tool, completing in 1249ms. This was among the slower operations we tested, but completed without errors. We did not test with various attachment sizes or formats to determine performance characteristics across different file types.
How do label creation and retrieval operations perform?+
Label operations showed varied performance in our testing. Creating new labels via create_label took 450ms, while get_or_create_label required 709ms due to the additional lookup logic. Label listing through list_email_labels was faster at 240ms, and updating existing labels completed in 665ms.
What filtering and search capabilities were validated?+
Email search functionality executed successfully via search_emails in 1039ms, and filter listing worked through list_filters in 233ms. Filter listing was among the fastest operations tested. We did not test complex search queries or filter creation capabilities, focusing on basic search and filter retrieval operations.
Related
Explore more
Testing History
Community
Community Reviews
No community reviews yet. Be the first to share your experience!