Your SEO data, inside your editor.

Three steps, about two minutes

1. 1Create a key

   One click in the dashboard. Free accounts can create one — you don’t need a paid plan to read reports.

2. 2Add the server

   one command in your terminal — or skip the install entirely and point your client at our HTTP endpoint.

   claude mcp add tracetify -e TRACETIFY_API_KEY=ttfy_... -- npx -y tracetify-mcp

   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

   Or skip the manual steps — paste this into Claude Code and it does all of it, including the victory lap:

   setup promptsteps 1–3 in one pastecopy

   Set up the Tracetify MCP server for me.
   
   1. Ask me for my Tracetify API key. (Free accounts can create one at
      https://tracetify.com/dashboard/ai — I'll go grab it if I don't have one yet.)
   2. Run: claude mcp add tracetify -e TRACETIFY_API_KEY=<my key> -- npx -y tracetify-mcp
      (If npx isn't available here, use the HTTP transport instead:
      claude mcp add --transport http tracetify https://tracetify.com/api/mcp --header "Authorization: Bearer <my key>")
   3. Verify the connection by listing the tracetify tools — there should be 14.
   4. Then show me what this is for: search for an existing growth report on
      photoai.com and give me the two most interesting dated events from it.

   Claude DesktopSettings → Developer → Edit Config

   {
     "mcpServers": {
       "tracetify": {
         "command": "npx",
         "args": ["-y", "tracetify-mcp"],
         "env": { "TRACETIFY_API_KEY": "ttfy_..." }
       }
     }
   }

   CursorSettings → MCP → Add server

   {
     "mcpServers": {
       "tracetify": {
         "command": "npx",
         "args": ["-y", "tracetify-mcp"],
         "env": { "TRACETIFY_API_KEY": "ttfy_..." }
       }
     }
   }

   # same JSON as Claude Desktop — it goes in ~/.cursor/mcp.json

   Codex~/.codex/config.toml

   [mcp_servers.tracetify]
   command = "npx"
   args = ["-y", "tracetify-mcp"]
   env = { TRACETIFY_API_KEY = "ttfy_..." }

   # or run: codex mcp add tracetify --env TRACETIFY_API_KEY=ttfy_... -- npx -y tracetify-mcp

3. 3Ask something

   Your agent picks the right tool on its own. Try:

   How did photoai.com get its first users? Cite the sources.

Things you can ask that nothing else can answer

Every one of these needs data your editor doesn’t have — a rebuilt growth history, your own Search Console, a directory list someone actually checked by hand.

• How did photoai.com get its first users? Cite the sources.

  → search_reports · read_report

• My page ranks #12 for "ai headshot generator" — what should I change to reach page one?

  → gsc_queries · gsc_pages

• We just deployed — audit example.com and fix what you find.

  → site_audit_start · site_audit_get

• Where can I get my new SaaS listed for real dofollow links?

  → backlink_directories

• Does AI search ever recommend competitor.com? Compare with us.

  → research_brand_lookup

14 tools, and what each one costs

Tools that cost credits quote the price first and wait for you to say yes. Reading existing reports never costs anything.

• search_reportsfreeSearch growth reports

  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.

• read_reportfreeRead a growth report

  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).

• start_trace10 creditsTrace how a product grew

  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.

• get_tracefreeCheck a running trace

  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.

• unlock_report10 creditsUnlock full timeline & evidence

  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.

• gsc_overviewfreeSearch Console overview

  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).

• gsc_queriesfreeSearch Console queries

  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.

• gsc_pagesfreeSearch Console pages

  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.

• site_audit_start3 creditsStart a site audit

  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.

• site_audit_getfreeRead a site audit

  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.

• research_domain_overview8 creditsDomain SEO overview

  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).

• research_backlinks8 creditsBacklink profile

  Who 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_brand_lookup30 creditsAI search visibility

  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.

• backlink_directories8 creditsVerified directory list

  A 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.

Your agent reads those descriptions and decides on its own when to reach for us. If it ever picks the wrong tool, say trace <domain> and it will come straight here.