Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.kaiv/can-i-use

REMOTE · API.KAIV.AI · SCANNED SEP 20

Browser support for web features, live from caniuse. From which version, and is it safe to ship?

Available components

+4 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability83
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 338 tokens (~112/item across 3 items; 3 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
  • Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the ai.kaiv/can-i-use MCP server?

ai.kaiv/can-i-use is a hosted endpoint at https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.kaiv.ai

# add to Claude Code
claude mcp add --transport http ai-kaiv-can-i-use 'https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b'
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-kaiv-can-i-use": {
      "url": "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-kaiv-can-i-use": {
      "type": "http",
      "url": "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.ai-kaiv-can-i-use]
url = "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-kaiv-can-i-use": {
      "type": "remote",
      "url": "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-kaiv-can-i-use --url 'https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  ai-kaiv-can-i-use:
    url: "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-kaiv-can-i-use": {
      "Transport": "http",
      "Url": "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
    }
  }
}
# add to Vellum
assistant mcp add ai-kaiv-can-i-use -t streamable-http -u 'https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b'
// mcp.json
{
  "mcpServers": {
    "ai-kaiv-can-i-use": {
      "type": "http",
      "url": "https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Sept 26 +1
    • Stability: unverified → 0.03 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=kaiv.ai CN=WE1,O=Google Trust Services,C=US 9 Sept 2026 8 Dec 2026 ECDSA 256 ECDSA-SHA256 b225111947d906a40e56536076ff66c0
SANs: kaiv.ai, *.kaiv.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of api.kaiv.ai. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
kaiv.ai. present 2371 13 Verified
api.kaiv.ai. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
content-security-policy default-src 'self';form-action 'self' https://auth.kaiv.ai;script-src 'self' https://cdnjs.cloudflare.com https://challenges.cloudflare.com 'unsafe-inline';style-src 'self' https://cdnjs.cloudflare.com 'unsafe-inline';img-src 'self' data: blob:;connect-src 'self' https://api.openai.com https://api.anthropic.com https://generativelanguage.googleapis.com https://challenges.cloudflare.com https://*.kaiv.ai;frame-src 'self' https://challenges.cloudflare.com;font-src 'self' https://cdnjs.cloudflare.com;object-src 'none';media-src 'self';base-uri 'self';frame-ancestors 'self';script-src-attr 'none';upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options DENY
referrer-policy same-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b Verified 200
http (plaintext) http://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b HTTPS enforced 301 https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b
MCP tools · 3 exposed · ~237 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_feature_support ~116

Can I use this feature, and from which browser version? Accepts a loose name (":has()", "container queries", "css-grid") and resolves it to a caniuse feature, then returns the earliest continuously-supported version per major browser, global usage percentage, and a conservative safe_to_use flag. Use this first; it answers the whole question in one call.

NameTypeReqDescription
featurestringyesFeature name or caniuse id. Loose names are resolved, e.g. "has selector" finds "css-has".
NameTypeReqDescription
descriptionstring
featurestringyesResolved caniuse feature id.
global_partial_percentnumber
global_support_percentnumberPercentage of tracked global users on a browser version that fully supports it.
meaningstringyesOne sentence, safe to show a user verbatim.
other_matchesarrayOther features the query could have meant.
resolved_fromstringThe query that was matched, so a caller can see what it actually asked about.
safe_to_usebooleanTrue only when global support is at least 90% AND no major browser is missing it. A conservative single answer.
specstring
supportobjectyesPer-browser detail, keyed by caniuse browser id.
titlestringyes
unsupported_inarrayMajor browsers whose newest release still does not support it.

No examples provided.

get_feature_by_id ~63

Support table for an exact caniuse feature id. Use when the id is already known, for example from a previous search. No fuzzy matching is applied.

NameTypeReqDescription
idstringyesExact caniuse feature id, e.g. "css-has".
NameTypeReqDescription
descriptionstring
featurestringyesResolved caniuse feature id.
global_partial_percentnumber
global_support_percentnumberPercentage of tracked global users on a browser version that fully supports it.
meaningstringyesOne sentence, safe to show a user verbatim.
other_matchesarrayOther features the query could have meant.
resolved_fromstringThe query that was matched, so a caller can see what it actually asked about.
safe_to_usebooleanTrue only when global support is at least 90% AND no major browser is missing it. A conservative single answer.
specstring
supportobjectyesPer-browser detail, keyed by caniuse browser id.
titlestringyes
unsupported_inarrayMajor browsers whose newest release still does not support it.

No examples provided.

search_features ~58

Find the caniuse feature id for a loose query. Use when a query is ambiguous and you want to choose between candidates before checking support.

NameTypeReqDescription
qstringyesFree-text query, e.g. "grid" or "web share".
NameTypeReqDescription
countinteger
matchesarray
querystring

No examples provided.

Common questions

What is the ai.kaiv/can-i-use MCP server?

ai.kaiv/can-i-use is an MCP server listed in the public MCP registry as ai.kaiv/can-i-use. Browser support for web features, live from caniuse. From which version, and is it safe to ship? This page covers its hosted endpoint (https://api.kaiv.ai/api/bridge/mcp/can-i-use-5446c68b).

Is the ai.kaiv/can-i-use MCP server safe to use?

ai.kaiv/can-i-use scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ai.kaiv/can-i-use MCP server expose?

ai.kaiv/can-i-use exposes 3 tools: check_feature_support, get_feature_by_id, search_features. Their descriptions and schemas cost roughly 237 tokens of context every time the server is loaded.

Does the ai.kaiv/can-i-use MCP server require authentication?

No. We connected to ai.kaiv/can-i-use without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the ai.kaiv/can-i-use MCP server still maintained?

ai.kaiv/can-i-use is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.