◉ANTIGRAVITY LABJP
TAG

mcp

41 articles
← Back to all tags
Related:
Antigravity15antigravity10Antigravity CLI5automation4integrations4Figma4workflow4Node.js3troubleshooting3Configuration2measurement2integration2
⟐ Editor/2026-09-21Intermediate

The Night Red Squiggles Filled My MCP Config, and What I Checked Before Editing

Red squiggles across your MCP config don't mean the servers are down. Schema validation in the editor answers a different question than the runtime does. Here's the order I now follow, starting with the status rings in /mcp.

⬡ Integrations/2026-09-18Intermediate

When a session starts with MCP tools missing, where do you stop?

When MCP initialization fails at startup, the agent quietly falls back to other means and keeps going. Here is a small script that asks your servers directly which tools they expose, plus the three branches I decided on in advance for when something is missing.

⬡ Integrations/2026-08-22Beginner

Adding MCP Servers Without Opening the Config File: The agy mcp Subcommand

Antigravity CLI 1.1.16, released on August 20, adds an mcp subcommand so you can register and toggle MCP servers without hand-editing JSON. Here is how to add stdio and HTTP servers, isolate a misbehaving one, and script your whole setup so it travels to a new machine.

⬡ Integrations/2026-08-20Beginner

Find the one broken MCP entry before Antigravity starts, with 40 lines of Node

A single typo in your MCP settings can take every server down with it. Here is a small preflight script that catches the mistakes statically, the real output from a deliberately broken config, and the duplicate-key trap that JSON hides from you.

⬡ Integrations/2026-08-08Advanced

The MCP Server I Thought I Killed Was Still Holding the Port: 84 Teardown Trials

Closing a session should stop the MCP servers it started. Across 84 trials of four teardown strategies, a process-group SIGTERM left zero orphans — until the child called setsid, at which point it left 100%. Includes a full descendant-sweep implementation.

⬡ Integrations/2026-08-04Advanced

Startup Dropped to 3ms, and the First Turn Saw Zero Tools

Non-blocking MCP loading cut startup from 2,907ms to 3ms. The wait did not disappear — it moved into the first turn. Here is where it went, measured, plus a readiness gate that waits only for what a turn actually needs.

⬡ Integrations/2026-08-03Advanced

I Measured Before Writing a Number: MCP Connect and Tool Calls Differed by 486x

Antigravity 2.4.3 lets you set a timeout per MCP server. To find a defensible number I built a stdio server, measured each boundary separately, and found why a single value cannot cover both.

◉ Antigravity/2026-08-02Advanced

I Copied the Same agent.md Into Another Repo and It Quietly Did a Different Job

CLI 1.1.6 lets you carry agent definitions around as files. I dropped one definition into eight repos, built a preflight that resolves its declared capabilities before the agent runs, and measured it against a naive checker.

⬡ Integrations/2026-07-28Advanced

Three Tools Named read_file: Catching MCP Name Collisions Before Startup

Bundle enough MCP servers and tool names collide quietly. Here is what a real 5-server, 21-tool setup measured at 43% collision, plus a Python preflight that catches them before startup and assigns deterministic aliases.

✦ Tips/2026-04-28Intermediate

Stop Antigravity From Writing Outdated API Code — Three Ways to Hand It Fresh Library Docs

A practical workflow for keeping Antigravity's AI on the latest library APIs — using Context7 MCP, direct doc URLs, and AGENTS.md to anchor the agent to your real version stack.

⬡ Integrations/2026-03-30Intermediate

Complete Troubleshooting Guide for Antigravity MCP Connection Errors

Master MCP connection troubleshooting with step-by-step diagnosis, authentication fixes, and debugging techniques for seamless integration.

⬡ Integrations/2026-07-19Advanced

When an Unresponsive MCP Server Freezes Your Agent: Separate Timeouts for Connect, List, and Call

Antigravity CLI 1.1.3 closed the case where an unresponsive MCP server stalls an agent forever, by adding timeouts to connect, list-tools, and call-tool. This walks through why the three boundaries fail differently, and builds a defensive wrapper with a circuit breaker and failure-only notifications, backed by working code and a week of overnight runs.