Workspace turned third-party connectors on by default. Two screens to check before you decide
Since September 15, 2026, Gemini in Workspace connects to Asana, Salesforce and five other tools over MCP, and the setting ships on by default. Here is how I count what is actually enabled, from both the Admin console and the user side panel.
The Day I Unplugged an MCP Server for the First Time — How I Decide Which Tools Stay On
Keep adding MCP servers and quality degrades well before you hit the API ceiling of 512 function declarations. Here is how I use includeTools and excludeTools in Gemini CLI to decide which tools stay enabled, and how I put the rest away.
The approval rules I had written never matched once — auditing my Gemini CLI policies
A deny rule I trusted for half a year had never matched. The pattern was tested against a JSON string, the folder I kept my rules in is not read, and ask_user turns into deny the moment nobody is watching. Here is the audit, and the script I wrote to keep doing it.
Don't Ingest Gemini Deep Research Reports Blindly — A Citation-Verification Acceptance Gate for MCP-Grounded Research
Now that Deep Research connects to MCP servers and File Search, you can ground research on your own data. This builds an acceptance gate that verifies, before any automated ingest, whether each citation resolves to a trusted source — with an allowlist, a grounding-coverage ratio, and categorized reject reasons, all in working code.
The Day @Canva Moved In With Gemini — A One-Week Field Note on Designing Through Conversation via the MCP Connector
A week of running Gemini's @Canva connector in production. Includes the prompt builder that stops Brand Kit references from going missing, a work-log script that replaces 'it feels faster' with medians, and a colour-difference audit that moves the weekly brand check off human eyes.
Gemini CLI with MCP Servers: A from File I/O to Database Queries
Learn how to connect MCP servers to Gemini CLI for hands-on file operations and database integration. Covers GEMINI.md configuration, filesystem, SQLite, and GitHub MCP with working examples.
Google AI Studio × Gemini API Production Guide — Reduce Input Costs by 90%
Master Gemini API and Google AI Studio. Complete production guide: Gemini 3/3.1 Pro, Context Caching, Batch Mode, MCP, Vertex AI integration, and cost optimization.
Building Custom MCP Servers for Gemini API — Extending AI Agents with TypeScript
Learn how to build custom Model Context Protocol (MCP) servers in TypeScript and integrate them with Gemini API. Covers architecture, authentication, error handling, and production deployment patterns.
Wiring Gemini CLI into Your Shell and CI — Headless Runs and Session Resume
Move past interactive use of Gemini CLI: headless runs, JSON output, session resume, approval modes, and MCP. Includes the five ways headless runs break and a measured pro/flash comparison.