Analyze competitor growth patterns, audit websites for SEO, and access Google Search Console data through an AI agent.
Also known as tracetify/tracetify-mcp
- Stars
- 1
- Tools
- 18
- Downloads, 30 days
- —
- Latest version
- 0.7.0
- Last commit
- Oct 8, 2026
- License
- MIT
What is Tracetify MCP?
Tracetify analyzes competitor growth patterns, audit websites for SEO, and access Google Search Console data through an AI agent. It exposes 18 tools, such as search_reports, read_report, start_trace.
Summary generated from the project's README
About Tracetify MCP server
Tracetify-mcp allows developers to integrate competitive intelligence and SEO auditing directly into AI clients like Claude Code, Cursor, and Codex. By connecting via an API key, users can reconstruct the growth history of any product using twelve different sources to identify launch spikes and directory mentions. The server functions as a protocol adapter that translates MCP tool calls into Tracetify API requests, ensuring your credentials only leave your machine as an authorization header.
Users can access a variety of specialized tools ranging from free Google Search Console data retrieval to credit-based research tasks. You can perform site audits to find broken links and thin content, analyze competitor advertising on Meta and Google, or research keyword volumes and SERP breakdowns. The system manages costs through a unified credit balance, and tools that require credits will always quote the price and wait for user confirmation before proceeding.
What you can do with it
- 1Reconstruct competitor growth historyAsk the agent to explain how a specific domain acquired its initial user base using sourced evidence.
- 2Optimize search engine rankingsIdentify specific changes needed to move a webpage from a lower ranking to the first page of search results.
- 3Perform technical website auditsRequest a crawl of a website to identify technical issues like redirect chains or missing titles.
- 4Analyze competitor advertising strategiesExtract current ad copy, landing pages, and creative URLs used by a competitor on Google and Meta.
Written from the project's README. Every use case is checked against a quote from it.
How to install Tracetify MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Tracetify MCP in Claude Code
$ claude mcp add --env 'TRACETIFY_API_KEY=<YOUR_TRACETIFY_API_KEY>' tracetify-mcp -- npx -y tracetify-mcpInstall Tracetify MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"tracetify-mcp": {
"command": "npx",
"args": [
"-y",
"tracetify-mcp"
],
"env": {
"TRACETIFY_API_KEY": "<YOUR_TRACETIFY_API_KEY>"
}
}
}
}Install Tracetify MCP in VS Code
.vscode/mcp.json
{
"servers": {
"tracetify-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tracetify-mcp"
],
"env": {
"TRACETIFY_API_KEY": "<YOUR_TRACETIFY_API_KEY>"
}
}
}
}Install Tracetify MCP in VS Code CLI
$ code --add-mcp '{"name":"tracetify-mcp","type":"stdio","command":"npx","args":["-y","tracetify-mcp"],"env":{"TRACETIFY_API_KEY":"<YOUR_TRACETIFY_API_KEY>"}}'Install Tracetify MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"tracetify-mcp": {
"command": "npx",
"args": [
"-y",
"tracetify-mcp"
],
"env": {
"TRACETIFY_API_KEY": "<YOUR_TRACETIFY_API_KEY>"
}
}
}
}Install Tracetify MCP in Codex
$ codex mcp add tracetify-mcp --env 'TRACETIFY_API_KEY=<YOUR_TRACETIFY_API_KEY>' -- npx -y tracetify-mcpInstall Tracetify MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.tracetify-mcp] command = "npx" args = ["-y", "tracetify-mcp"] [mcp_servers.tracetify-mcp.env] TRACETIFY_API_KEY = "<YOUR_TRACETIFY_API_KEY>"
Install Tracetify MCP in Gemini CLI
$ gemini mcp add -s user -e 'TRACETIFY_API_KEY=<YOUR_TRACETIFY_API_KEY>' tracetify-mcp npx -- -y tracetify-mcpInstall Tracetify MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"tracetify-mcp": {
"command": "npx",
"args": [
"-y",
"tracetify-mcp"
],
"env": {
"TRACETIFY_API_KEY": "<YOUR_TRACETIFY_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for tracetify-mcp 0.7.0 in an isolated container with no network and no keys. It answered and listed 18 tools.
Tracetify MCP tools 18
Read from the server with tools/listsearch_reportsRead-onlyUse 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.
read_reportRead-onlyRead 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).
start_traceActionRun 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.
get_traceRead-onlyPoll 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.
unlock_reportActionPermanently 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.
gsc_overviewRead-onlyUse 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).
gsc_queriesRead-onlyThe 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.
gsc_pagesRead-onlyThe 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.
site_audit_startActionRun 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.
site_audit_getRead-onlyPoll 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.
research_competitorsActionThe 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.
research_domain_overviewActionEstimated 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).
Show all 18 toolsShow fewer tools
research_backlinksActionWho links to a domain: referring domains, authority and anchor texts. Use when planning link building or judging how defensible a competitor's ranking is. Costs credits; cached results are free. Pair with backlink_directories to find places the user can actually get listed.
research_keyword_volumeActionGoogle 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.
research_serp_breakdownActionWho 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.
research_competitor_adsActionThe 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.
research_brand_lookupActionHow 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.
backlink_directoriesActionA hand-verified list of directories and launch platforms that actually give links — checked one by one, dead and nofollow-only entries removed. Use when the user wants backlinks or launch exposure for a new product; filter client-side by language/type/pricing. Costs credits once per day per account — repeat calls the same day are free, so refine freely.
Configuration
TRACETIFY_API_KEYRequiredSecretTracetify API key — create one at https://tracetify.com/dashboard (AI & MCP page)
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachabletracetify/tracetify-mcp is public and reachablegithub.com/tracetify/tracetify-mcp ↗Pass
- Package names this repository as its sourcetracetify-mcp names tracetify/tracetify-mcp as sourcenpmjs.com/package/tracetify-mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-14github.com/tracetify/tracetify-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from tracetify-mcpPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model18 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 169 msPass
README
View on GitHubtracetify-mcp
MCP server for Tracetify — trace how any product actually grew, read your own Search Console, and audit a site, without leaving Claude Code or Cursor.
Most competitive tools tell you where a product stands today. Tracetify reconstructs how it got there: the first mention, the quiet weeks, the directory wave, the launch spike. Twelve sources per trace, every claim linked to the page it came from.
Full setup guide and example questions: tracetify.com/mcp
Free agent skills
Start with Competitor Research and GSC SEO Optimizer for sourced competitor briefs and prioritized Search Console work. These free, MIT-licensed workflows use public sources or your own exports and do not require a Tracetify account. Browse the skill source. Connect this MCP server when you want additional Tracetify tools and data; authentication and applicable credit charges still apply.
Setup
Create an API key in the dashboard, then pick one of the two transports.
Claude Code — one command:
claude mcp add tracetify -e TRACETIFY_API_KEY=ttfy_... -- npx -y tracetify-mcp
Or skip the install entirely — nothing to install, not even Node:
claude mcp add --transport http tracetify https://tracetify.com/api/mcp --header "Authorization: Bearer ttfy_..."
Same tools, same balance; the server runs on our side.
Claude Desktop / Cursor take the same JSON (Cursor reads
~/.cursor/mcp.json):
{
"mcpServers": {
"tracetify": {
"command": "npx",
"args": ["-y", "tracetify-mcp"],
"env": { "TRACETIFY_API_KEY": "ttfy_..." }
}
}
}
Codex uses TOML in ~/.codex/config.toml — note the snake_case table name:
[mcp_servers.tracetify]
command = "npx"
args = ["-y", "tracetify-mcp"]
env = { TRACETIFY_API_KEY = "ttfy_..." }
Try asking
Your agent picks the right tool on its own — these are real questions, not placeholders:
- How did photoai.com get its first users? Cite the sources.
- My page ranks #12 for "ai headshot generator" — what should I change to reach page one?
- We just deployed — audit example.com and fix what you find.
- Where can I get my new SaaS listed for real dofollow links?
- What is competitor.com running on Meta and Google right now? Pull the hooks and landing pages.
If your agent ever reaches for the wrong tool, say trace <domain> and it will
come straight here.
Tools
Tools that cost credits quote the price first and wait for you to say yes. Reading existing reports never costs anything.
| Tool | Cost | What it does |
|---|---|---|
search_reports |
free | Find existing growth reports by domain |
read_report |
free | Read a full report — timeline & verdict follow your account's unlocks |
start_trace |
10 credits | Rebuild a competitor's growth from 12 sources (~60–90s); a fresh cached report comes back free |
get_trace |
free | Poll a running trace |
unlock_report |
10 credits | Permanently unlock a report's full timeline, evidence & SEO detail (idempotent — never charges twice) |
gsc_overview |
free | Your own Search Console: clicks, impressions, period comparison |
gsc_queries |
free | Your real ranking keywords with position and CTR — find what sits at #5–20 |
gsc_pages |
free | Your pages by search performance, including high-impression low-CTR ones |
site_audit_start |
3 credits | Crawl a site for broken links, missing titles, redirect chains, thin content |
site_audit_get |
free | Poll an audit and read the issue list grouped by severity |
research_competitors |
2 credits | Who fights a domain for the same keywords, flagging which ones already have a report |
research_domain_overview |
3 credits | Estimated organic traffic and top keywords for any domain |
research_keyword_volume |
2 credits | Google Ads monthly search volume, CPC, 12-month trend and keyword difficulty (0–100) for up to 10 keywords (per market or worldwide; difficulty is US-based when worldwide) |
research_serp_breakdown |
3 credits | Who holds the Google top 10 for one keyword in one market: per position the domain, homepage vs inner page, domain rating (0–1000) and estimated monthly organic traffic — the weakest slot stands out |
research_backlinks |
3 credits | Referring domains, authority and anchor texts |
research_competitor_ads |
3 credits | The ads a domain is running on Meta (Facebook/Instagram) and Google right now — copy, CTA, landing page, creative URL, platforms, start dates |
research_brand_lookup |
12 credits | How AI assistants cite a brand: platforms, mentions, associated entities |
backlink_directories |
8 credits | Hand-verified directories that actually give dofollow links (billed once per day) |
Everything draws from your Tracetify credit balance — the same balance the website uses. No seats, no per-tool add-ons. Top up at tracetify.com/pricing.
What this package does
It is a thin protocol adapter: MCP tool calls in, Tracetify HTTP API calls out.
No business logic, no data of its own — your API key never leaves your machine
except as an Authorization header to tracetify.com.
License
MIT
Tracetify MCP questions
How do I add Tracetify MCP to Claude Code?
Run claude mcp add --env 'TRACETIFY_API_KEY=<YOUR_TRACETIFY_API_KEY>' tracetify-mcp -- npx -y tracetify-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Tracetify MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Tracetify MCP provide?
It exposes 18 tools, including search_reports, read_report, start_trace, get_trace, unlock_report.
How do I set up Tracetify with Claude Code?
You can add it using a single command: claude mcp add tracetify -e TRACETIFY_API_KEY=ttfy_... -- npx -y tracetify-mcp.
Does using this MCP server require a Tracetify account?
While some free workflows use public sources and do not require an account, connecting this MCP server for additional tools and data requires authentication and uses your Tracetify credit balance.
How are tool costs handled?
Tools that cost credits will quote the price first and wait for your approval before proceeding.