PatchLabs MCP server
dev.patchlabs/patchlabspatchlabs.devstreamable-httpv3.2.0Scanned
Finds personal-data leaks in Supabase/Lovable apps: free RLS and headers checks, proven fixes.
7 tools: 4 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- 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 PatchLabs MCP server can do
The PatchLabs MCP server is published by patchlabs.dev, a domain the MCP Registry verified. It has 7 tools. It can create or change data (4 tools: rls_check, headers_check, start_check and run_check), but cannot delete data. 3 tools only read.
4 tools bring in text other people can write (rls_check, headers_check, start_check and 1 more); 1 tool can send data out of your system (headers_check).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 3.2.0.
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.
7 tools
Changes things 4Claude Code: ask
headers_checkGrade a public site's HTTPS, TLS certificate, security headers and cookie flags from one load of its home page (no sign-up).Reads text others writeCan send data outNo findings
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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Grade a public site's HTTPS, TLS certificate, security headers and cookie flags from one load of its home page (no sign-up). Returns findings PL-027..PL-036 with fixes.
Annotations the server declares
- title: Security headers check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
rls_checkFree, no sign-up.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Free, no sign-up. Reads a public GitHub repo's supabase/migrations and lists row-level-security mistakes that could let strangers or other users read personal data (findings PL-001..PL-008 and PL-014, each with a fix). Static analysis only: it never connects to the live app or database. Suited to Supabase, Lovable and Bolt repos.
Annotations the server declares
- title: Static RLS check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
run_checkQueue a new check for a monitored app now (counts toward the plan's monthly runs).Reads text others writeNo findings
Why it is in this group
- The name "run_check" says "run": 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 Queue a new check for a monitored app now (counts toward the plan's monthly runs). Needs X-API-Key.
Annotations the server declares
- title: Run a check on an app
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
start_checkRequest the full lab check: the database is rebuilt from the repo with fake rows, leaks are proven as each kind of user, and a tested fix is written.Reads text others writeNo findings
Why it is in this group
- The name "start_check" says "start": 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 Request the full lab check: the database is rebuilt from the repo with fake rows, leaks are proven as each kind of user, and a tested fix is written. Creates a check and emails the report address; nothing runs until the repo owner proves ownership with a one-line file. Returns a check id and link. Only call when the user asks for the full check and gives their email.
Annotations the server declares
- title: Request a full leak check
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 3Show 3 read-only tools
get_checkRead one check by id.No findings
Why it is in this group
- The name "get_check" says "get": a word for reading.
Description, as the server wrote it Read one check by id. Read-only, safe to call again to poll. Returns status: awaiting_verification (includes the one-line file the repo owner must add, then nothing runs until they do), queued, running, done, no_leaks, needs_review or failed. When finished it also returns the summary (each finding with severity, CWE/OWASP and days open), the plain-English report (report_md) and the tested fix (fix_sql), plus the event timeline. Use after start_check or run_check; poll every minute or so while queued or running.
Annotations the server declares
- title: Get a check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_appsList the apps monitored in the API key's workspace, each with its id (pass it as app_id to run_check), its last finished check (id and status, for get_check) and any open_check_id.No findings
Why it is in this group
- The name "list_apps" says "list": a word for reading.
Description, as the server wrote it List the apps monitored in the API key's workspace, each with its id (pass it as app_id to run_check), its last finished check (id and status, for get_check) and any open_check_id. Needs X-API-Key.
Annotations the server declares
- title: List monitored apps
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_checksList past and running checks for the API key's workspace, newest first, optionally for one app.No findings
Why it is in this group
- The name "list_checks" says "list": a word for reading.
Description, as the server wrote it List past and running checks for the API key's workspace, newest first, optionally for one app. Each has its id (pass it to get_check for the full report and fix), app_id, client_label, repo, status, trigger (schedule, api, manual), created/finished times and the tables found leaking. Use it to see an app's history or whether a leak came back. Needs X-API-Key.
Annotations the server declares
- title: List past checks
- 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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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 19, 2026, 17:21 UTC, unchanged since Nov 12, 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
- 4
- 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.patchlabs.dev/mcp: tools/list returned 6 tools to an anonymous client, including rls_check (write), headers_check (write), start_check (write), run_check (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.
Tools1 added, 6 changed.+1 added~6 changedView diff
- Added:list_checksOnly reads
- Changed:get_checkOnly readsdescriptioninputSchemaannotations
- Changed:headers_checkChanges thingsannotations
- Changed:list_appsOnly readsdescriptionannotations
- Changed:rls_checkChanges thingsdescriptionannotations
- Changed:run_checkChanges thingsdescriptionannotations
- Changed:start_checkChanges thingsdescriptionannotations
Install
Pinned to version 3.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http patchlabs https://api.patchlabs.dev/mcpclaude mcp add --transport http patchlabs https://api.patchlabs.dev/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__patchlabs__get_check",
"mcp__patchlabs__list_apps",
"mcp__patchlabs__list_checks"
],
"ask": [
"mcp__patchlabs__rls_check",
"mcp__patchlabs__headers_check",
"mcp__patchlabs__start_check",
"mcp__patchlabs__run_check"
],
"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 patchlabs. Review it before you use it.
Capability tags behind 4 rules
- mcp__patchlabs__rls_check untrusted-input
- mcp__patchlabs__headers_check untrusted-input, outbound
- mcp__patchlabs__start_check untrusted-input
- mcp__patchlabs__run_check 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/dev.patchlabs/patchlabs/verify?hash=5761347fa032d2390459e73ab41af6d4577ae1d224ced7a87372281612de44db" | jq -e '.changed == false'Pinned hash 5761347fa032, from Nov 20, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.patchlabs/patchlabs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.patchlabs/patchlabs)Source: MCP Registry · repository. Synced Nov 20, 2026, 18:17 UTC.
PatchLabs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PatchLabs MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 4 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 PatchLabs MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PatchLabs 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 PatchLabs MCP server have?
- 7 tools: 4 write, 3 read. rls_check, headers_check, start_check, run_check, get_check, list_apps and list_checks.
Does the PatchLabs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PatchLabs MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): headers_check.
Has the PatchLabs MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.