Antigravity MCP Server

Overview Schema Source Related Servers Discussions Admin

digest-antigravity

Read-only

Ingest multiple files or directories to answer a focused question from content beyond your context window, returning a concentrated brief.

Instructions

Ingest many files at once and answer a focused question. Uses Antigravity's large model context (Gemini ~1M tokens) to swallow whole modules / docs that don't fit in the caller's context. Walks directories (symlinks are not followed), filters by extension, withholds credential files (.env, .npmrc, keys…), truncates oversized files, caps total payload. Returns a concentrated brief.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "<question>",
      "paths": "<paths>"
    },
    "name": "digest-antigravity"
  }
}

Input Schema

Name	Required	Description	Default
`model`	No
`paths`	Yes	Files or directories to ingest, inside workingDir (symlinks are resolved; anything outside is skipped). Directories are walked. Globs are NOT expanded — pass concrete paths.
`shape`	No	summary: 1-paragraph; detailed: structured deep-dive; qa: focused answer to the question.	qa
`effort`	No	Reasoning effort (--effort). Supported levels depend on the model — see list-models. Use with a base model ID (e.g. gemini-4-hydrogen); not supported by Orchestrator.
`exclude`	No	Substrings to exclude from paths (matched against relative path). Default: node_modules, .git, dist, build.
`timeout`	No	Maximum execution time in milliseconds (default 600000)
`question`	Yes	Focused question to answer using the provided files (e.g., "explain auth flow", "find dead code").
`recursive`	No	Walk into subdirectories. Default: true.
`extensions`	No	Filter by extensions when walking dirs (e.g., [".ts", ".tsx"]). Default: all text-like files.
`workingDir`	No
`maxTotalBytes`	No	Stop adding files once the total payload exceeds this. Gemini models have ~1M-token contexts; 8 MB default leaves headroom.
`maxBytesPerFile`	No	Truncate any single file above this size. Default: 200 KB.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 14, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; beyond that the description adds genuinely useful behavior — credential files (.env, .npmrc, keys) are withheld, oversized files are truncated, and total payload is capped. One defect: it says 'symlinks are not followed,' while the paths schema says 'symlinks are resolved,' an internal inconsistency an agent may trip over. Return format is covered by 'Returns a concentrated brief.'

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and the answer it produces, then a tight run of behavioral facts in one sentence. Dense and largely waste-free, though the parenthetical 'Gemini ~1M tokens' is more flavor than guidance and the symlink sentence is factually muddled.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with no output schema, the definition covers the important ground: what gets read, what gets skipped, what gets truncated, and roughly what comes back. It stops short of explaining how 'shape' and 'effort' change the result or how the model parameter interacts with the rest, which leaves some selection risk on a fairly complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 83%, so most parameters are already documented in structured data and the baseline of 3 applies. The description reinforces directory walking, extension filtering, credential omission, truncation and payload capping — all of which map to existing schema descriptions rather than adding new semantics — and never mentions 'shape' or 'effort,' the two parameters most likely to change output.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource combination: ingest many files and answer a focused question, with the mechanism (large-context model) and the payoff (a concentrated brief) spelled out. What's missing is sibling differentiation — with both 'ask-antigravity' and 'batch-antigravity' present, an agent must infer on its own that this is the many-files variant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'swallow whole modules / docs that don't fit in the caller's context' implies when this tool is the right pick, but usage is only implied, never stated as a rule. There is no explicit when-not guidance and no alternative tool is named, which is a real gap given several similarly named siblings that could plausibly handle the same request.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server