GuardLayer MCP server
io.github.solvionholdings/guardlayersolvionholdingsstreamable-httpv1.0.1Scanned
Security checks for Next.js + Supabase apps: code scan, read-only live DB check, fix confirmation.
3 tools: 1 change things and 2 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 0
- 1 finding, 1 high
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the GuardLayer MCP server can do
The GuardLayer MCP server is published by the GitHub account solvionholdings. It has 3 tools. It can create or change data (1 tool: scan_files), but cannot delete data. 2 tools only read.
2 tools read private data (get_supabase_snapshot_sql and check_supabase_snapshot).
The fixed checks matched 1 finding, 1 of them high severity (sensitive-path). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.1.
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.
3 tools
Changes things 1Claude Code: ask
scan_filesStatic security scan of a Next.js + Supabase codebase: secrets in code or public env vars (NEXT_PUBLIC_, VITE_), service role keys in client code, RLS off or open policies in supab…1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- High
The description refers to ".env*".
What this check looks forMatched text
description: "...nd source files (ts, tsx, js, jsx, sql, .env*, config files) with paths relative to t..."
Description, as the server wrote it Static security scan of a Next.js + Supabase codebase: secrets in code or public env vars (NEXT_PUBLIC_, VITE_), service role keys in client code, RLS off or open policies in supabase/migrations, unauthenticated API routes, Server Actions and Edge Functions, unsafe redirects and more. Send source files (ts, tsx, js, jsx, sql, .env*, config files) with paths relative to the project root; skip node_modules, build output and lockfiles. Up to 300 files and 4 MB per call; split bigger projects. Files are scanned in memory and discarded.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
check_supabase_snapshotChecks the JSON from get_supabase_snapshot_sql: tables anyone can read, RLS off, policies that only check for a signed-in user (public in practice when sign-ups are open), users wh…Reads private dataNo findings
Why it is in this group
- The name "check_supabase_snapshot" says "snapshot": a word for reading.
What it can reach
- private-dataThe description's first sentence says "sql": it reads databases.
Description, as the server wrote it Checks the JSON from get_supabase_snapshot_sql: tables anyone can read, RLS off, policies that only check for a signed-in user (public in practice when sign-ups are open), users who can update their own role or plan columns, exposed SECURITY DEFINER functions, public buckets. Pass auth_config (the project's Auth settings) when you can: it decides whether 'any signed-in user' means anyone. Pass previous_issue_keys from an earlier result to see what is closed, still open or new. Returns each issue with its SQL fix and a fix prompt.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_supabase_snapshot_sqlReturns the read-only SQL for the live Supabase check and how to run it.Reads private dataNo findings
Why it is in this group
- The name "get_supabase_snapshot_sql" says "get": a word for reading.
What it can reach
- private-dataThe name "get_supabase_snapshot_sql" says "get" and "sql": it reads databases.
- private-dataThe description's first sentence says "return" and "sql": it reads databases.
Description, as the server wrote it Returns the read-only SQL for the live Supabase check and how to run it. It reads only catalog metadata (table and column names, RLS flags, policies, grants, triggers, SECURITY DEFINER functions, bucket settings), never table rows, and returns one JSON value.
Annotations the server declares
- readOnlyHint: 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 untrusted-input or outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 18, 2026, 16:21 UTC, unchanged since Nov 11, 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.guardlayer.io/api/mcp: tools/list returned 3 tools to an anonymous client, including scan_files (write)
Findings
Matches of fixed checks, with the text they matched.
- Highscan_files
The description refers to ".env*".
What this check looks forMatched text
description: "...nd source files (ts, tsx, js, jsx, sql, .env*, config files) with paths relative to t..."
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 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http guardlayer https://www.guardlayer.io/api/mcpclaude mcp add --transport http guardlayer https://www.guardlayer.io/api/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__guardlayer__get_supabase_snapshot_sql",
"mcp__guardlayer__check_supabase_snapshot"
],
"ask": [
"mcp__guardlayer__scan_files"
],
"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 guardlayer. Review it before you use it.
Capability tags behind 2 rules
- mcp__guardlayer__get_supabase_snapshot_sql private-data
- mcp__guardlayer__check_supabase_snapshot private-data
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/io.github.solvionholdings/guardlayer/verify?hash=58c7255e6a8473b0e572b3055b79fc3da16f74772fe3ee9f165a0951a28f9ba8" | jq -e '.changed == false'Pinned hash 58c7255e6a84, from Nov 10, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.solvionholdings/guardlayer/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.solvionholdings/guardlayer)Source: MCP Registry · repository. Synced Nov 10, 2026, 21:18 UTC.
GuardLayer MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the GuardLayer MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the GuardLayer MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the GuardLayer 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 GuardLayer MCP server have?
- 3 tools: 1 write, 2 read. scan_files, get_supabase_snapshot_sql and check_supabase_snapshot.
Does the GuardLayer MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the GuardLayer MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the GuardLayer MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.