Skip to content

PromptMentions MCP server

com.promptmentions/promptmentionspromptmentions.comstreamable-httpv1.1.0Scanned

Read-only AI visibility data: brand mentions, cited sources and answers across AI engines.

12 tools: 12 only read.

Tools: 0 delete, 0 irreversible, 0 write, 12 read.
  • Reads private data · 3
  • Reads text others write · 2
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 PromptMentions MCP server can do

The PromptMentions MCP server is published by promptmentions.com, a domain the MCP Registry verified. It has 12 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

3 tools read private data (list_samples, get_citations and get_sample_evidence); 2 tools bring in text other people can write (get_run_metrics and list_samples).

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 21, 2026, version 1.1.0.

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.

12 tools

Only reads 12Show 12 read-only tools
  • get_citationsDomains and pages cited in one run’s successful answers, classified (client, competitor, directory, editorial, social, other), and citation gaps.Reads private dataNo findings

    Why it is in this group

    • The name "get_citations" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    Description, as the server wrote it
    Domains and pages cited in one run’s successful answers, classified (client, competitor, directory, editorial, social, other), and citation gaps. Requires the monitoring:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_looker_rowsFlat rows for Looker Studio and spreadsheets.No findings

    Why it is in this group

    • The name "get_looker_rows" says "get": a word for reading.
    Description, as the server wrote it
    Flat rows for Looker Studio and spreadsheets. dataset "visibility" (default): per day, engine, model, prompt and tracked brand, the successful answers and how many named the brand; failed answers are not counted. "social-pages": per cited social or community page and week, as on Sources › Social pages. "lost-citations": pages cited less or not lately in the 90 days up to "to", as on Sources › Lost citations. Default: the last 30 days; at most 93. Requires the reports:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_projectOne client project.No findings

    Why it is in this group

    • The name "get_project" says "get": a word for reading.
    Description, as the server wrote it
    One client project. Requires the projects:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_reportA client report for a UTC date window (default: last 30 days, at most 93): monitoring runs with labelled metrics, opportunity changes and caveats.No findings

    Why it is in this group

    • The name "get_report" says "get": a word for reading.
    Description, as the server wrote it
    A client report for a UTC date window (default: last 30 days, at most 93): monitoring runs with labelled metrics, opportunity changes and caveats. Requires the reports:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_run_metricsOne run with labelled metrics (mention rate, citation rates, tracked mention share) and competitor share of voice with 95% Wilson ranges.Reads text others writeNo findings

    Why it is in this group

    • The name "get_run_metrics" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "mention": it reads comments, which other people can write.
    Description, as the server wrote it
    One run with labelled metrics (mention rate, citation rates, tracked mention share) and competitor share of voice with 95% Wilson ranges. Requires the monitoring:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_sample_evidenceThe preserved evidence file of one sample: the provider’s raw response, parsed answer text and citations, and the extraction summary.Reads private dataNo findings

    Why it is in this group

    • The name "get_sample_evidence" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    Description, as the server wrote it
    The preserved evidence file of one sample: the provider’s raw response, parsed answer text and citations, and the extraction summary. Over MCP the raw provider body is omitted unless includeRaw is "true". Requires the evidence:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_workspaceThe workspace this key belongs to, the key’s permissions and the client projects it can read.No findings

    Why it is in this group

    • The name "get_workspace" says "get": a word for reading.
    Description, as the server wrote it
    The workspace this key belongs to, the key’s permissions and the client projects it can read.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_opportunitiesTasks and opportunities for a client with their source evidence, priority basis, assumptions and state.No findings

    Why it is in this group

    • The name "list_opportunities" says "list": a word for reading.
    Description, as the server wrote it
    Tasks and opportunities for a client with their source evidence, priority basis, assumptions and state. Paginate with cursor. Requires the opportunities:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_projectsClient projects with their brand, aliases, tracked competitors and locale.No findings

    Why it is in this group

    • The name "list_projects" says "list": a word for reading.
    Description, as the server wrote it
    Client projects with their brand, aliases, tracked competitors and locale. Requires the projects:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_prompt_setsPrompt sets for a client, with every saved revision, its locale and prompts.No findings

    Why it is in this group

    • The name "list_prompt_sets" says "list": a word for reading.
    Description, as the server wrote it
    Prompt sets for a client, with every saved revision, its locale and prompts. Requires the projects:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_runsMonitoring runs for a client, newest first, with sample counts.No findings

    Why it is in this group

    • The name "list_runs" says "list": a word for reading.
    Description, as the server wrote it
    Monitoring runs for a client, newest first, with sample counts. Paginate with cursor. Requires the monitoring:read key permission.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_samplesEvery sample of one run: provider, interface, models, prompt, locale, time, status, extracted mentions and citations, and the evidence file hash.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_samples" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe description's first sentence says "mention": it reads comments, which other people can write.
    Description, as the server wrote it
    Every sample of one run: provider, interface, models, prompt, locale, time, status, extracted mentions and citations, and the evidence file hash. Requires the monitoring:read key permission.

    Annotations the server declares

    • 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 outbound.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
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.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:19 UTC, unchanged since Nov 21, 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
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://promptmentions.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://promptmentions.com/api/auth
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no

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

claude mcp add --transport http promptmentions https://promptmentions.com/api/mcp
claude mcp add --transport http promptmentions https://promptmentions.com/api/mcp

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__promptmentions__get_workspace",
      "mcp__promptmentions__list_projects",
      "mcp__promptmentions__get_project",
      "mcp__promptmentions__list_prompt_sets",
      "mcp__promptmentions__list_runs",
      "mcp__promptmentions__get_run_metrics",
      "mcp__promptmentions__list_samples",
      "mcp__promptmentions__get_citations",
      "mcp__promptmentions__get_sample_evidence",
      "mcp__promptmentions__list_opportunities",
      "mcp__promptmentions__get_looker_rows",
      "mcp__promptmentions__get_report"
    ],
    "ask": [],
    "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 promptmentions. Review it before you use it.

Capability tags behind 4 rules
  • mcp__promptmentions__get_run_metrics untrusted-input
  • mcp__promptmentions__list_samples private-data, untrusted-input
  • mcp__promptmentions__get_citations private-data
  • mcp__promptmentions__get_sample_evidence 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/com.promptmentions/promptmentions/verify?hash=99d00329b717ef47fef69719dfd8972ba78a4f10500eeea07ecb5a7735d50d23" | jq -e '.changed == false'

Pinned hash 99d00329b717, from Nov 21, 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/com.promptmentions/promptmentions/changes.xml

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

Badge

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

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

PromptMentions MCP server: questions and answers

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

Is the PromptMentions MCP server safe?

No scan can promise that. What its definitions show: 12 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the PromptMentions MCP server delete data?

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

Can the PromptMentions 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 PromptMentions MCP server have?

12 tools: 12 read. get_workspace, list_projects, get_project, list_prompt_sets, list_runs, get_run_metrics, list_samples, get_citations and 4 more.

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

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

Does the PromptMentions MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the PromptMentions MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.