Superbridger free tools MCP server
com.superbridger/free-toolssuperbridger.comstreamable-httpv1.0.0Scanned
Check captions and videos against each social platform's limits; specs, image sizes. No account.
6 tools: 2 change things and 4 only read.
- Reads private data · 1
- Reads text others write · 3
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 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 Superbridger free tools MCP server can do
The Superbridger free tools MCP server is published by superbridger.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: check_video and build_utm_links), but cannot delete data. 4 tools only read.
1 tool reads private data (get_platform_specs); 3 tools bring in text other people can write (check_caption, get_platform_specs and get_image_sizes); 1 tool can send data out of your system (build_utm_links). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 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.
6 tools
Changes things 2Claude Code: ask
build_utm_linksAdds utm_source, utm_medium (social by default), utm_campaign and optionally utm_content and utm_term to a link: one link per platform, or one for a source you name.Can send data out1 finding
Why it is in this group
- The name "build_utm_links" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "build_utm_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "build_utm_links" says "link": a word for a change.
Description, as the server wrote it Adds utm_source, utm_medium (social by default), utm_campaign and optionally utm_content and utm_term to a link: one link per platform, or one for a source you name.
Annotations the server declares
- title: Build UTM links
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_videoSays whether a video will post on each platform (as a Reel, Short or video, and as an Instagram or Facebook Story), from its technical facts: size in bytes, length, width and heigh…No 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.
Description, as the server wrote it Says whether a video will post on each platform (as a Reel, Short or video, and as an Instagram or Facebook Story), from its technical facts: size in bytes, length, width and height, frame rate, video and audio codec, sample rate, container, HDR and whether the index is at the front. Returns a verdict per platform with each check's message.
Annotations the server declares
- title: Check a video
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
check_captionCounts a post's text the way Instagram, Facebook, YouTube, TikTok, LinkedIn and X count it, against each platform's limits: characters, X's weighted 280 (emoji 2, links 23), TikTok…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "count": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "count" and "post": it reads posts, which other people can write.
Description, as the server wrote it Counts a post's text the way Instagram, Facebook, YouTube, TikTok, LinkedIn and X count it, against each platform's limits: characters, X's weighted 280 (emoji 2, links 23), TikTok's UTF-16 2,200, YouTube's 100-character title and 5,000-byte description, Instagram's 5 hashtags and 20 mentions. Returns each platform's counts, limits and whether it fits.
Annotations the server declares
- title: Check a caption
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_image_sizesReturns recommended image sizes per platform (posts, Stories, covers, banners, thumbnails, profile pictures) with each size's source.Reads text others writeNo findings
Why it is in this group
- The name "get_image_sizes" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "post": it reads posts, which other people can write.
Description, as the server wrote it Returns recommended image sizes per platform (posts, Stories, covers, banners, thumbnails, profile pictures) with each size's source.
Annotations the server declares
- title: Image sizes
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_platform_specsReturns the limits for posting to Instagram, Facebook, YouTube, TikTok, LinkedIn and X (or one of them): text length and how it's counted, hashtags, video length, file size, shape,…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_platform_specs" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "file": it reads files.
- untrusted-inputThe description's first sentence says "return" and "post": it reads posts, which other people can write.
Description, as the server wrote it Returns the limits for posting to Instagram, Facebook, YouTube, TikTok, LinkedIn and X (or one of them): text length and how it's counted, hashtags, video length, file size, shape, codecs, frame rate, Stories, photos per post and posts per day, with the date they were checked.
Annotations the server declares
- title: Platform specs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_safe_zonesReturns the margins to keep clear on a 1080×1920 vertical video for Instagram and Facebook Reels, TikTok and YouTube Shorts, where each app's buttons and captions sit, with sources…No findings
Why it is in this group
- The name "get_safe_zones" says "get": a word for reading.
Description, as the server wrote it Returns the margins to keep clear on a 1080×1920 vertical video for Instagram and Facebook Reels, TikTok and YouTube Shorts, where each app's buttons and captions sit, with sources.
Annotations the server declares
- title: Safe zones
- 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.
3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__free-tools__build_utm_links"
]
}
}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 21, 2026, 19:22 UTC, unchanged since Nov 7, 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://superbridger.com/.well-known/oauth-protected-resource
- Authorization servers
- https://superbridger.com/api/auth
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- 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://superbridger.com/api/tools/mcp: tools/list returned 6 tools to an anonymous client, including check_video (write), build_utm_links (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnbuild_utm_links
The server marks "build_utm_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "build_utm_links" says "link": a word for a change.
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 free-tools https://superbridger.com/api/tools/mcpclaude mcp add --transport http free-tools https://superbridger.com/api/tools/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__free-tools__check_caption",
"mcp__free-tools__get_platform_specs",
"mcp__free-tools__get_image_sizes",
"mcp__free-tools__get_safe_zones"
],
"ask": [
"mcp__free-tools__check_video",
"mcp__free-tools__build_utm_links"
],
"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 free-tools. Review it before you use it.
Capability tags behind 4 rules
- mcp__free-tools__check_caption untrusted-input
- mcp__free-tools__get_platform_specs private-data, untrusted-input
- mcp__free-tools__get_image_sizes untrusted-input
- mcp__free-tools__build_utm_links outbound
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/com.superbridger/free-tools/verify?hash=aa1e9ae986bf79d71dccfd0e15e743bd46b5ae8a0d688bdda5d868b98f8fbf47" | jq -e '.changed == false'Pinned hash aa1e9ae986bf, from Nov 20, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.superbridger/free-tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.superbridger/free-tools)Source: MCP Registry. Synced Nov 6, 2026, 13:17 UTC.
Superbridger free tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Superbridger free tools MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Superbridger free tools MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Superbridger free tools 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 Superbridger free tools MCP server have?
- 6 tools: 2 write, 4 read. check_video, build_utm_links, check_caption, get_platform_specs, get_image_sizes and get_safe_zones.
Does the Superbridger free tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Superbridger free tools 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): build_utm_links.
Has the Superbridger free tools MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.