antigravity-mcp
Integrates Google Antigravity's agy agent into MCP, enabling asynchronous delegation of complex tasks like code analysis and file management with job polling.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
TurkerYakup
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
use_antigravityDelegate a task to Antigravity (Gemini). Returns a jobId IMMEDIATELY; poll antigravity_result until done. Good for web search, large-codebase analysis, file/folder creation, viewing images/PDFs. add_dirs grants agy access to specific folders; auto_approve (default true) lets it create/edit files wit…
antigravity_continueContinue the latest agy conversation, or a specific conversation ID.
antigravity_resultGet the result of an Antigravity job by jobId. status is running | done | error | not_found. When done, the 'output' field holds agy's full response.
antigravity_jobsList recent Antigravity jobs and their statuses (most recent first).
antigravity_cancelCancel a running Antigravity job (kills the agy process) by jobId.
antigravity_cleanupDelete old job JSON files from agy_jobs directory.
antigravity_create_folderCreate a folder (recursively) on disk. Instant, done by the server directly (no agy, no permission prompt).
antigravity_create_fileCreate/write a text file on disk (creates parent folders). Set overwrite=false to avoid replacing an existing file.
antigravity_create_treeCreate a whole folder/file structure from a JSON spec. In spec: a string value = file with that content, null = empty folder, a nested object = subfolder.
antigravity_list_dirList entries in a folder on disk.
antigravity_modelsList available Antigravity/Gemini models (runs `agy models`).
antigravity_read_fileRead a UTF-8 text file from disk (server-side, instant, no agy). Optionally cap bytes returned.
antigravity_agentsList available agy agent profiles (runs `agy agents`). Use the name with the `agent` param of use_antigravity.
antigravity_healthCheck that the agy CLI is reachable (version) and report the server's effective defaults and live job count. Run this first when something isn't working.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Zod denial of service vulnerability
AGY_AUTO_APPROVE"": "true"AGY_CLEANUP_HOURSAGY_HEARTBEAT_MS15000 Interval for the "job running" progress notification. 0 disables.AGY_MODEL"": "Gemini 3.5 Flash (Medium)",AGY_MODEL_TTL_MS300000 How long the cached agy models list is trusted.AGY_PATHWhere it lands (remember this — you may need it for below):AGY_PRINT_TIMEOUT10m agy's --print-timeout.AGY_SANDBOXfalse Run every job with --sandbox (terminal-restricted). Cheap; safer for untrusted prompts. Per-call sandbox overrides.AGY_WATCHDOG_MSTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
14/14 tools missing one or more hints — use_antigravity (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); antigravity_continue (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); antigravity_result (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — antigravity_cleanup deletes at line 181 (fs.unlinkSync(fp))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — antigravity_models (line 682: execSync('"' + AGY_BIN + '" models', { encoding: "utf8", timeout: 30000 })); antigravity_agents (line 719: execSync('"' + AGY_BIN + '" agents', { encoding: "utf8", timeout: 30000, windowsHide: true }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
10/14 tool handlers declare input schemas (71%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
13/14 tool handlers wrap calls in try/catch (93%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Tool description accuracy
antigravity_models: description implies read-only but handler writes/deletes/executes; antigravity_agents: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/turkeryakup/mcp-server-google-antigravity)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check