Gravity AI UI MCP server
tech.ydb-qdrant/gravity-ai-uiydb-qdrant.techstreamable-httpv1.0.0Scanned
Search public Gravity AI UI drafts and generate Gravity UI interface payloads.
4 tools: 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.
What the Gravity AI UI MCP server can do
The Gravity AI UI MCP server is published by ydb-qdrant.tech, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: generate_interface and refine_interface), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (get_interface, generate_interface and refine_interface).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 2Claude Code: ask
generate_interfaceUse to generate a new Gravity AI UI composed interface from a prompt.Reads text others writeNo findings
Why it is in this group
- The name "generate_interface" says "generate": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use to generate a new Gravity AI UI composed interface from a prompt. This calls the public generator with the server OpenAI configuration and does not save or publish the result.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
refine_interfaceUse to refine a previously generated Gravity AI UI composed payload with a natural-language instruction.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use to refine a previously generated Gravity AI UI composed payload with a natural-language instruction. This does not save or publish the result.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
get_interfaceUse when you already have a public Gravity AI UI gallery id and need the sanitized public interface metadata, composed payload, thumbnail URLs, page URL, and copyable React code.Reads text others writeNo findings
Why it is in this group
- The name "get_interface" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Use when you already have a public Gravity AI UI gallery id and need the sanitized public interface metadata, composed payload, thumbnail URLs, page URL, and copyable React code.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_interfacesUse to discover public liked Gravity AI UI interface drafts by title, summary, or id.No findings
Why it is in this group
- The name "search_interfaces" says "search": a word for reading.
Description, as the server wrote it Use to discover public liked Gravity AI UI interface drafts by title, summary, or id. This returns public gallery metadata only. Use get_interface when you need the full payload or React code for a known id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:19 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://gravity-ai.ydb-qdrant.tech/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://gravity-ai.ydb-qdrant.tech
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://gravity-ai.ydb-qdrant.tech/mcp: tools/list returned 4 tools to an anonymous client, including generate_interface (write), refine_interface (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http gravity-ai-ui https://gravity-ai.ydb-qdrant.tech/mcpclaude mcp add --transport http gravity-ai-ui https://gravity-ai.ydb-qdrant.tech/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__gravity-ai-ui__search_interfaces",
"mcp__gravity-ai-ui__get_interface"
],
"ask": [
"mcp__gravity-ai-ui__generate_interface",
"mcp__gravity-ai-ui__refine_interface"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as gravity-ai-ui. Review it before you use it.
Capability tags behind 3 rules
- mcp__gravity-ai-ui__get_interface untrusted-input
- mcp__gravity-ai-ui__generate_interface untrusted-input
- mcp__gravity-ai-ui__refine_interface untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/tech.ydb-qdrant/gravity-ai-ui/verify?hash=f2aef7bc7ebeb82648031ee543eff2143bd1a5d3053c16d152659ed20e3f852c" | jq -e '.changed == false'Pinned hash f2aef7bc7ebe, from Nov 19, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/tech.ydb-qdrant/gravity-ai-ui/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/tech.ydb-qdrant/gravity-ai-ui)Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.
Gravity AI UI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Gravity AI UI MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Gravity AI UI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Gravity AI UI MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Gravity AI UI MCP server have?
- 4 tools: 2 write, 2 read. generate_interface, refine_interface, search_interfaces and get_interface.
Does the Gravity AI UI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Gravity AI UI MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Gravity AI UI MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.