Skip to content

tracetify-mcp server

io.github.tracetify/tracetify-mcptracetifystreamable-httpv0.7.0Scanned

Find competitors, trace how they grew, watch what they ship — plus your Search Console.

18 tools: 13 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 13 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 2
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

13 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 tracetify-mcp server can do

The tracetify-mcp server is published by the GitHub account tracetify. It has 18 tools. It can create or change data (13 tools: start_trace, unlock_report, gsc_overview, gsc_pages and 9 more), but cannot delete data. 5 tools only read.

1 tool reads private data (research_brand_lookup); 2 tools bring in text other people can write (site_audit_start and research_brand_lookup); 2 tools can send data out of your system (start_trace and site_audit_start). 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 0.7.0.

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.

18 tools

Changes things 13Claude Code: ask
  • gsc_overviewUse this before touching SEO on the user's own site: clicks/impressions trend, device split and period comparison from THEIR connected Google Search Console — numbers no other tool…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
    Use this before touching SEO on the user's own site: clicks/impressions trend, device split and period comparison from THEIR connected Google Search Console — numbers no other tool has. Free. Requires GSC connected at tracetify.com/dashboard/gsc (this tool tells you if it is not).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • gsc_pagesThe user's pages ranked by search performance, including high-impression low-CTR pages whose titles/descriptions are underselling — fix those files right in this editor.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
    The user's pages ranked by search performance, including high-impression low-CTR pages whose titles/descriptions are underselling — fix those files right in this editor. Free; own data from their connected Search Console.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • research_brand_lookupHow AI assistants (ChatGPT, Perplexity-class) cite a brand: platforms, mention counts and the entities it gets associated with.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "research_brand_lookup" says "lookup": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • private-dataThe description's first sentence says "chat": it reads messages.
    • untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.

    Findings

    • Warn

      The server marks "research_brand_lookup" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "research_brand_lookup" says "lookup": a word for reading.

      What this check looks for
    Description, as the server wrote it
    How AI assistants (ChatGPT, Perplexity-class) cite a brand: platforms, mention counts and the entities it gets associated with. Use when the user asks "does AI recommend us/them?". Costs credits; cached results are free.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • research_competitor_adsThe ads a domain is running right now on Facebook/Instagram (Meta Ad Library) and Google (Ads Transparency Center): headline, body copy, CTA, landing page URL, creative/video URL, …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.
    Description, as the server wrote it
    The ads a domain is running right now on Facebook/Instagram (Meta Ad Library) and Google (Ads Transparency Center): headline, body copy, CTA, landing page URL, creative/video URL, platforms and start dates. Use when the user asks what a competitor is advertising, whether they run paid ads, how long an ad has been live, or wants hooks and angles to model. Costs credits; the same domain re-queried within a week is free. Each source reports separately — null means that source could not be checked, an empty list means it was checked and found nothing.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • research_competitorsThe domains fighting a target for the same search terms, with shared-keyword count, their keyword totals and average rank.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.
    Description, as the server wrote it
    The domains fighting a target for the same search terms, with shared-keyword count, their keyword totals and average rank. Use when the user asks who their competitors are, or who a company is up against. Each result says whether we already have a full growth report for that domain — read those with read_report for free instead of tracing them again. Costs credits; cached results are free, and a domain already looked up via research_domain_overview is free here too.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • research_domain_overviewEstimated organic traffic, keyword count and top keywords for ANY domain — use to size up a competitor the user mentions.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.
    Description, as the server wrote it
    Estimated organic traffic, keyword count and top keywords for ANY domain — use to size up a competitor the user mentions. Costs credits; cached results are free, and repeated queries within a week hit the cache. For the user's own site prefer gsc_* (free, real data).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • research_keyword_volumeGoogle Ads (Keyword Planner) monthly search volume, CPC, competition, 12-month trend and keyword difficulty (0–100, DataForSEO Labs) for up to 10 keywords in one call.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.
    Description, as the server wrote it
    Google Ads (Keyword Planner) monthly search volume, CPC, competition, 12-month trend and keyword difficulty (0–100, DataForSEO Labs) for up to 10 keywords in one call. Use when the user asks how often something is searched or how hard it is to rank, or to size a keyword before writing a page. Omit location_code for worldwide volume (difficulty is then computed for the US), or pass a market code for one country. Costs credits; the same keyword set re-queried within a week is free.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • research_serp_breakdownWho holds the Google top 10 for one keyword in one market: per position the domain, URL, whether it is a homepage or an inner page, domain rating (0–1000) and estimated monthly org…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.
    Description, as the server wrote it
    Who holds the Google top 10 for one keyword in one market: per position the domain, URL, whether it is a homepage or an inner page, domain rating (0–1000) and estimated monthly organic traffic. Use when the user asks who ranks for a keyword, whether a keyword is winnable, or which slot is the weakest to go after. Pair with research_keyword_volume for volume and difficulty. Costs credits; the same keyword+market re-queried within a week is free.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • site_audit_startRun right after deploying: crawls the site and reports broken links, missing titles/descriptions, redirect chains, thin content and schema gaps — each finding names the page so you…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "site_audit_start" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe description's first sentence says "crawl": 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.
    Description, as the server wrote it
    Run right after deploying: crawls the site and reports broken links, missing titles/descriptions, redirect chains, thin content and schema gaps — each finding names the page so you can fix it here. Costs credits (price returned before any charge on the confirmation field). Async: poll with site_audit_get.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_traceRun this when search_reports finds nothing (or the user wants fresh data) for "how did X grow?".Can send data outNo findings

    Why it is in this group

    • The name "start_trace" says "start": a word for a change.

    What it can reach

    • 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
    Run this when search_reports finds nothing (or the user wants fresh data) for "how did X grow?". Rebuilds the growth story from 12 public sources in 60-90s. Costs credits from the Tracetify balance; returns an existing cached report free instead when one is fresh. Poll with get_trace.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • unlock_reportPermanently unlock a report's full timeline, evidence and SEO detail for this account.No findings

    Why it is in this group

    • The name "unlock_report" says "unlock": a word for a change.
    Description, as the server wrote it
    Permanently unlock a report's full timeline, evidence and SEO detail for this account. Costs credits — quote the exact price to the user first (it is in the report's timelineLocked.cost field from read_report) and call this ONLY after they explicitly agree to spend. Idempotent: unlocking an already-unlocked report never charges twice. The verdict stays on the website — you are the analyst here.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
Only reads 5Show 5 read-only tools
  • get_tracePoll a trace started with start_trace.No findings

    Why it is in this group

    • The name "get_trace" says "get": a word for reading.
    Description, as the server wrote it
    Poll a trace started with start_trace. Free. When status is "done", read the result with read_report. Poll every 10-15s, not in a tight loop.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • gsc_queriesThe user's real ranking keywords with position, clicks and CTR — use when deciding what to write or which page to improve, e.g.No findings

    Why it is in this group

    • The name "gsc_queries" says "query": a word for reading.
    Description, as the server wrote it
    The user's real ranking keywords with position, clicks and CTR — use when deciding what to write or which page to improve, e.g. finding queries at position 5-20 that are one push from page one. Free; own data from their connected Search Console. After you edit a page, this is how you verify it moved.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • read_reportRead one growth report by slug (from search_reports or a finished trace).No findings

    Why it is in this group

    • The name "read_report" says "read": a word for reading.
    Description, as the server wrote it
    Read one growth report by slug (from search_reports or a finished trace). Free. Contains the origin story, dated evidence and SEO footprint — cite it instead of guessing how a product grew. If timeline fields show as locked, unlock_report can open them (that one costs credits).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • search_reportsUse this FIRST whenever the user asks how a product, competitor or domain grew, got traffic, or found its first users — a report may already exist and reading it is free.No findings

    Why it is in this group

    • The name "search_reports" says "search": a word for reading.
    Description, as the server wrote it
    Use this FIRST whenever the user asks how a product, competitor or domain grew, got traffic, or found its first users — a report may already exist and reading it is free. Returns matching report slugs for read_report. Searches by domain or name fragment.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • site_audit_getPoll an audit started with site_audit_start (free to read).No findings

    Why it is in this group

    • The name "site_audit_get" says "get": a word for reading.
    Description, as the server wrote it
    Poll an audit started with site_audit_start (free to read). When finished, returns the issue list grouped by severity with affected URLs — work through it top-down and re-run after fixes.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: 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.

4 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 write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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__tracetify__research_brand_lookup"
    ]
  }
}

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, 19:12 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
13
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 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://tracetify.com/api/mcp: tools/list returned 18 tools to an anonymous client, including start_trace (write), unlock_report (write), gsc_overview (write), gsc_pages (write), site_audit_start (write) and 8 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "research_brand_lookup" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "research_brand_lookup" says "lookup": a word for reading.

    What this check looks for

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

claude mcp add --transport http tracetify https://tracetify.com/api/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http tracetify https://tracetify.com/api/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__tracetify__search_reports",
      "mcp__tracetify__read_report",
      "mcp__tracetify__get_trace",
      "mcp__tracetify__gsc_queries",
      "mcp__tracetify__site_audit_get"
    ],
    "ask": [
      "mcp__tracetify__start_trace",
      "mcp__tracetify__unlock_report",
      "mcp__tracetify__gsc_overview",
      "mcp__tracetify__gsc_pages",
      "mcp__tracetify__site_audit_start",
      "mcp__tracetify__research_competitors",
      "mcp__tracetify__research_domain_overview",
      "mcp__tracetify__research_backlinks",
      "mcp__tracetify__research_keyword_volume",
      "mcp__tracetify__research_serp_breakdown",
      "mcp__tracetify__research_competitor_ads",
      "mcp__tracetify__research_brand_lookup",
      "mcp__tracetify__backlink_directories"
    ],
    "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 tracetify. Review it before you use it.

Capability tags behind 3 rules
  • mcp__tracetify__start_trace outbound
  • mcp__tracetify__site_audit_start untrusted-input, outbound
  • mcp__tracetify__research_brand_lookup private-data, 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/io.github.tracetify/tracetify-mcp/verify?hash=94d2b06ee98e7ca549f7e791930e23f6fbe570dcd3ce49c0a9879991d4ebcb56" | jq -e '.changed == false'

Pinned hash 94d2b06ee98e, from Nov 20, 2026, 16:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.tracetify/tracetify-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.tracetify/tracetify-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.tracetify/tracetify-mcp.svg)](https://radar.anlyon.com/servers/io.github.tracetify/tracetify-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.

tracetify-mcp server: questions and answers

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

Is the tracetify-mcp server safe?

No scan can promise that. What its definitions show: 18 tools, 13 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 tracetify-mcp server delete data?

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

Can the tracetify-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 tracetify-mcp server have?

18 tools: 13 write, 5 read. start_trace, unlock_report, gsc_overview, gsc_pages, site_audit_start, research_competitors, research_domain_overview, research_backlinks and 10 more.

Does the tracetify-mcp server need sign-in or OAuth?

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

Does the tracetify-mcp server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): start_trace and site_audit_start.

Has the tracetify-mcp server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.