Dataforseo

DataForSEO

Agent-callable tools for the DataForSEO API v3 (https://api.dataforseo.com/v3/): search-engine, SEO, and AI-search data. Look up Google organic SERPs; research keywords (suggestions, related terms, search volume, difficulty, intent); analyze domains (ranking keywords, rank overview, organic-traffic estimates); inspect backlink profiles; search Google Maps business listings; run an on-page SEO audit; query AI models (ChatGPT, Claude, Gemini, Perplexity) and track how brands and domains are mentioned in AI-generated answers. All 33 tools are read-only data queries against DataForSEO's live (synchronous) endpoints.

Independent, unofficial connector for DataForSEO. Not affiliated with, endorsed by, or sponsored by DataForSEO. "DataForSEO" is a trademark of its owner, used only to identify the service this connector works with.

When to use this

• SERP & keyword research — see who ranks for a query, expand a seed keyword, or pull volume / CPC / difficulty / intent for a keyword list.
• Domain & competitor analysis — the keywords a domain ranks for, its rank overview, estimated organic traffic (current or historical), and its backlink profile (summary, individual links, referring domains, anchors).
• Local & on-page — find Google Maps businesses by category or location, or audit a single page's on-page SEO.
• AI-search visibility — ask an LLM a prompt, or track where a brand / domain / keyword is mentioned across AI answers (top pages, top domains, aggregate metrics).

Setup

This is an agentskills.io skill.

If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill dataforseo (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.

Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.

The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:

Scripts

All scripts use the single connection dataforseo. Many take a location_name / language_name pair (full names, e.g. "United States" / "English") — call listLocationsAndLanguages to resolve exact accepted values. List tools page with limit / offset.

Disambiguation & refusals

This connector is read-only and live-only — it retrieves data, one query per call. It does not schedule or monitor tasks over time, run full-site crawls, or create/update/delete anything. If asked to do something outside that surface, say it's unsupported and stop — don't substitute another tool and report success for work you didn't do. Specifically:

• No task scheduling or ongoing monitoring. Each tool returns a one-shot live result; there is no "track rankings/backlinks over time" or background job. To trend a metric, the agent calls the tool again later and compares.
• No full-site crawl. auditPage audits a single URL only. There is no tool to crawl an entire site.
• No writes. Nothing here modifies a Google property, a website, or a DataForSEO resource; there is nothing to create, update, or delete.
• ChatGPT-platform LLM mentions are US/English only. getLlmMentions with platform: "chat_gpt" has no data outside the United States / English locale. If asked for another locale, say the data isn't available and stop — don't call getChatGptResponse (a live single-prompt chat, not mentions data) and present its output as mentions data, and don't silently swap to platform: "google" or a SERP search and report that instead without flagging the limitation.

Because every tool is a read that takes explicit query values (keywords, domains, URLs), there is no name-lookup-then-write step that needs disambiguation.

Auth

Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.

Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).

No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:

Output format

Every script returns a { data, meta } envelope:

• data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).
• meta.outputDataValidation — what validating data did:
  • { skipped: false, droppedPaths: null } — validated, nothing removed.
  • { skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.
  • { skipped: true } — validation was bypassed; data is the raw, unchecked script output.

Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.

Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.

References

Load the matching reference file before working in that area: