Name: CallAI SEO
Author: callaiapi

CallAI SEO MCP

Live SEO data: Google/Bing SERP, AI Overview sources, keyword difficulty, backlinks, page audits.

Tool-list grade A Remote · Streamable HTTP API key 20 tools v1.0.0 MIT

No reviews yet by callaiapiGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Live SEO data: Google/Bing SERP, AI Overview sources, keyword difficulty, backlinks, page audits.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http callai-seo-mcp https://api.callaiapi.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'

# 2 — ask your agent for something these tools do
#   google_serp, bing_serp, keyword_overview and 17 more

It needs AUTHORIZATION (Bearer followed by your CallAI API key (create one at https://callaiapi.com/portal?tab=keys)): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.

CallAI SEO costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

callaiapi1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer followed by your CallAI API key (create one at https://callaiapi.com/portal?tab=keys)) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).

claude mcp add --scope user --transport http callai-seo-mcp https://api.callaiapi.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer followed by your CallAI API key (create one at https://callaiapi.com/portal?tab=keys). You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Live Google organic search results for a keyword in a given country and language: ranks, titles, URLs, snippets, plus the AI Overview text and the sources it cites. Billed per call (about $0.002 for depth 10).

Parameter	Type	Required	Notes
keyword	string	yes	Search query. Supports operators such as site:example.com.
depth	integer	no	Number of results to fetch, 10–100 (default 10). Cost grows with depth.
device	string	no	Default desktop.
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Live Bing organic search results for a keyword in a given country and language: ranks, titles, URLs, snippets. Billed per call (about $0.002 for depth 10).

Parameter	Type	Required	Notes
keyword	string	yes	Search query. Supports operators such as site:example.com.
depth	integer	no	Number of results to fetch, 10–100 (default 10). Cost grows with depth.
device	string	no	Default desktop.
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Google search volume, CPC, competition, keyword difficulty (0–100) and main search intent for up to 100 keywords in one call. About $0.01 per call plus $0.0001 per keyword.

Parameter	Type	Required	Notes
keywords	array	yes	Keywords to look up (max 100).
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Long-tail keywords that contain the seed keyword, with search volume, CPC, keyword difficulty and intent. Use it to find low-difficulty commercial keywords. About $0.01 per call plus $0.0001 per keyword returned.

Parameter	Type	Required	Notes
keyword	string	yes	Seed keyword.
limit	integer	no	Keywords to return, 1–200 (default 50).
max_difficulty	integer	no	Only return keywords with keyword difficulty at or below this value (0–100).
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Google organic keywords a domain (or URL) currently ranks for, sorted by estimated traffic: keyword, volume, difficulty, position, ranking URL and estimated traffic. About $0.01 per call plus $0.0001 per row.

Parameter	Type	Required	Notes
target	string	yes	Domain such as example.com.
limit	integer	no	Rows to return, 1–200 (default 50).
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Estimated Google organic traffic, number of ranking keywords and their position distribution for a domain, plus paid search totals. About $0.01 per call.

Parameter	Type	Required	Notes
target	string	yes	Domain such as example.com.
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Keywords the competitor ranks for on Google that your domain does not, sorted by search volume: the content gap to target. About $0.01 per call plus $0.0001 per row.

Parameter	Type	Required	Notes
competitor	string	yes	Competitor domain.
your_domain	string	yes	Your domain.
limit	integer	no	Rows to return, 1–200 (default 50).
location_code	integer	no	DataForSEO location code. 2840 = United States (default), 2826 = UK, 2276 = Germany, 2250 = France, 2392 = Japan, 2356 = India, 2076 = Brazil.
language_code	string	no	Language code, e.g. en (default), de, fr, ja, es, pt, zh-CN.

Backlink totals for a domain: domain rank (0–1000), backlinks, referring domains, nofollow share, broken backlinks, spam score and first-seen date. About $0.02 per call.

Parameter	Type	Required	Notes
target	string	yes	Domain such as example.com.

Domains linking to the target, strongest first: rank, backlink count, spam score and first-seen date. About $0.02 per call plus a small per-row fee.

Parameter	Type	Required	Notes
target	string	yes	Domain such as example.com.
limit	integer	no	Rows to return, 1–200 (default 50).

Fetches one URL and reports its on-page SEO: status code, title, meta description, canonical, headings, word count, link and image counts, load timing, on-page score and all on-page checks. About $0.0002 per call.

Parameter	Type	Required	Notes
url	string	yes	Absolute URL starting with https:// or http://.

Calls any DataForSEO v3 endpoint directly when no dedicated tool fits (Google Maps, YouTube, Amazon keywords, Google Trends, LLM mentions, WHOIS, technologies, task_post/task_get and more). Body and response follow the DataForSEO v3 docs at https://docs.dataforseo.com/v3/. Billed at the endpoint's DataForSEO price; task_get and tasks_ready calls are free. Always set a limit or filters: endpoints w

Parameter	Type	Required	Notes
path	string	yes	Path below /v3/, e.g. "serp/google/maps/live/advanced" or "serp/google/organic/task_get/advanced/<task_id>".
method	string	no	POST for live and task_post endpoints (default), GET for task_get and tasks_ready.
body	array	no	Array of task objects for POST requests.

Autocomplete suggestions from Google, Bing, YouTube, Amazon, Baidu, DuckDuckGo, Yahoo and Yandex, merged and de-duplicated. No search volume; pass the results to keyword_overview for metrics. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
keyword	string	yes	Seed keyword.
engines	array	no	Default google and bing.
market	string	no	Default us.
mode	string	no	seed: the keyword only (default). questions: with question words. az: with each letter a–z, the most results.

Fetches a site's robots.txt and returns its status and contents. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
url	string	yes	URL or domain, such as https://example.com/page.

Finds a site's sitemaps through robots.txt (falling back to /sitemap.xml) and returns each one's status, number of URLs and a sample. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
url	string	yes	URL or domain, such as https://example.com/page.

Fetches one URL and returns its status, final URL, title, meta description, canonical, meta robots, X-Robots-Tag, hreflang and H1s, as a browser or as Googlebot. Reads the raw HTML without running JavaScript. For a full audit use page_audit. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
url	string	yes	URL or domain, such as https://example.com/page.
fetch_as	string	no	Identify as our bot (default) or with Googlebot’s user agent, to spot cloaking.

Follows a URL's redirects and returns the status and target of every hop, up to 5. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
url	string	yes	URL or domain, such as https://example.com/page.

A, AAAA, CNAME, MX, NS and TXT records of a domain, from public resolvers. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
domain	string	yes	Domain such as example.com.

Checks a domain's MX, SPF, DKIM, DMARC and MTA-STS records and says whether it can be spoofed, with the issues to fix. Without dkim_selector it tries the common selectors, so a missing DKIM result is not proof of absence. Free: needs an API key but no balance.

Parameter	Type	Required	Notes
domain	string	yes	Domain such as example.com.
dkim_selector	string	no	The DKIM selector, if known.

Checks up to 100 domains (for buying expired or used domains): web archive history, Baidu index and backlinks, ending in a clean, suspect or rejected verdict with reasons. Charged per domain, about $0.02. Set dry_run first to see the exact cost and show it to the user. Runs in the background; read progress with domain_check_results.

Parameter	Type	Required	Notes
domains	array	yes	Domains to check (max 100).
dry_run	boolean	no	Only return the cost; nothing is started or charged.
rules	object	no	Optional pass rules; anything left out uses the defaults. Fields: tlds (string[]), firstSeenBy (year), minStableYears, noHistory (pass\|suspect\|reject), minBaiduIndexed (0–10), minReferringDomains, max

Progress and per-domain verdicts of a check started with domain_check_start: verdict, reason, first archive year, stable years, Baidu results, referring domains and spam score. A check can take minutes; rows stay pending until their steps finish. Reading is free.

Parameter	Type	Required	Notes
check_id	string	yes	The id from domain_check_start.
verdict	string	no	Only rows with this verdict.
limit	integer	no	Rows per page, up to 200 (default 50).
after	integer	no	The "next" value of the previous page.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install CallAI SEO or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.0.0 · scanned 5 Nov 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 6 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digesta3589cd4471c8f8a30fa73be76279fc589a92bb754c8a7b311de31a2c27a50a3

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
google_serp	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
bing_serp	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
keyword_overview	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
keyword_ideas	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
ranked_keywords	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
domain_overview	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
keyword_gap	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
backlinks_summary	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
referring_domains	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
page_audit	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
dataforseo_request	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
keyword_suggestions	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
check_robots	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
check_sitemap	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
page_meta	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
redirect_chain	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
dns_lookup	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
email_auth_check	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
domain_check_start	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
domain_check_results	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digesta3589cd4471c8f8a

Scanned2026-11-05

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.