Skip to content

Shareglow MCP server

com.getshareglow/mcpgetshareglow.comstreamable-httpv0.1.0Scanned

Shareglow MCP server: scan link previews, generate OG images, short links and stats.

7 tools: 4 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 4 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 3
  • 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.
Govern this server →

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 Shareglow MCP server can do

The Shareglow MCP server is published by getshareglow.com, a domain the MCP Registry verified. It has 7 tools. It can create or change data (4 tools: scan_url, generate_og_image, create_template_from_url and create_short_link), but cannot delete data. 3 tools only read.

1 tool reads private data (refresh_preview); 4 tools bring in text other people can write (scan_url, create_template_from_url, get_link_stats and 1 more); 3 tools can send data out of your system (scan_url, create_template_from_url and refresh_preview). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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 10, 2026, version 0.1.0.

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
  • create_template_from_urlUse AI to design a new OG image template from a website's brand (logo, colors, fonts) taken from a URL.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "create_template_from_url" says "create": 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.
    • 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
    Use AI to design a new OG image template from a website's brand (logo, colors, fonts) taken from a URL. Returns the chosen layoutId (a built-in template id usable with generate_og_image), the variables to pass, and the extracted brand kit. Counts against the plan's AI quota.

    Annotations the server declares

    • openWorldHint: true
  • generate_og_imageRender a 1200x630 Open Graph image from a template id (see list_templates) and text params such as title and subtitle.No findings

    Why it is in this group

    • The name "generate_og_image" says "generate": a word for a change.
    Description, as the server wrote it
    Render a 1200x630 Open Graph image from a template id (see list_templates) and text params such as title and subtitle. Returns the permanent image URL to put in og:image, and whether it was already cached. Optional exp (Unix seconds, paid plans) makes the signed URL expire; leave it out for an og:image URL.
  • scan_urlScan a public web page and report its link-preview (Open Graph / Twitter Card) metadata, previews per platform, and issues with fix suggestions.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
    Scan a public web page and report its link-preview (Open Graph / Twitter Card) metadata, previews per platform, and issues with fix suggestions. Use it to answer 'why does my link preview look wrong?'.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • list_templatesList the OG image templates the workspace can render (built-in and custom) with id, name, version and dimensions.No findings

    Why it is in this group

    • The name "list_templates" says "list": a word for reading.
    Description, as the server wrote it
    List the OG image templates the workspace can render (built-in and custom) with id, name, version and dimensions. Call this before generate_og_image to pick a templateId.

    Annotations the server declares

    • readOnlyHint: true
  • refresh_previewForce social platforms to re-fetch a page's link preview after you changed its OG tags or image: bumps the og:image cache-buster, re-scrapes Facebook, and returns the LinkedIn Post…Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "refresh_preview" says "preview": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Force social platforms to re-fetch a page's link preview after you changed its OG tags or image: bumps the og:image cache-buster, re-scrapes Facebook, and returns the LinkedIn Post Inspector link and the X cache note.

    Annotations the server declares

    • openWorldHint: true

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.

12 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
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 out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__getshareglow__refresh_preview"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:39 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
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.

    Matched text

    https://mcp.getshareglow.com/mcp: tools/list returned 7 tools to an anonymous client, including scan_url (write), generate_og_image (write), create_template_from_url (write), create_short_link (write)

    What this check looks for

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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http getshareglow https://mcp.getshareglow.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http getshareglow https://mcp.getshareglow.com/mcp --header 'Authorization: <your-authorization>'

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__getshareglow__list_templates",
      "mcp__getshareglow__get_link_stats"
    ],
    "ask": [
      "mcp__getshareglow__scan_url",
      "mcp__getshareglow__generate_og_image",
      "mcp__getshareglow__create_template_from_url",
      "mcp__getshareglow__create_short_link",
      "mcp__getshareglow__refresh_preview"
    ],
    "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 getshareglow. Review it before you use it.

Capability tags behind 4 rules
  • mcp__getshareglow__scan_url untrusted-input, outbound
  • mcp__getshareglow__create_template_from_url untrusted-input, outbound
  • mcp__getshareglow__get_link_stats untrusted-input
  • mcp__getshareglow__refresh_preview private-data, untrusted-input, 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.getshareglow/mcp/verify?hash=3ebd878cbeaf8fec936f4389ee863af53825638028dbb97bfd57eb38424a46e5" | jq -e '.changed == false'

Pinned hash 3ebd878cbeaf, from Nov 10, 2026, 16:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.getshareglow/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.getshareglow/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.getshareglow/mcp.svg)](https://radar.anlyon.com/servers/com.getshareglow/mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:55 UTC.

Shareglow MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Shareglow 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 Shareglow MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Shareglow 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 Shareglow MCP server have?

7 tools: 4 write, 3 read. scan_url, generate_og_image, create_template_from_url, create_short_link, list_templates, get_link_stats and refresh_preview.

Does the Shareglow MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Shareglow MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): scan_url, create_template_from_url and refresh_preview.

Has the Shareglow MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.