DataForSEO API Endpoint Index

A searchable, LLM-friendly markdown index of all 554 DataForSEO v3 API endpoints — ready to drop into Claude Code, Cursor, or any other AI coding assistant as a single reference file.

Made by Piz Digital.

TL;DR — Point your AI coding assistant (Claude Code, Cursor, Aider, Antigravity) at dataforseo-endpoint-index.md whenever you're building a DataForSEO integration, and it will know exactly which of the 554 v3 endpoints to call. Every row links directly to the exact lines of DataForSEO's upstream OpenAPI spec that define the operation — commit-pinned GitHub permalinks, so the agent can fetch parameters, request body, and responses for a single endpoint without ever downloading the full ~4 MB YAML. The file is small enough for any LLM context window, regenerated weekly, and free to use. Three usage options below: raw URL, fork, or clone.

What	Where
Endpoint index file	dataforseo-endpoint-index.md
Total endpoints	554 across 12 categories
Per-endpoint spec link	Commit-pinned GitHub permalink in the Spec column of every row
Update cadence	Weekly (Mondays 06:00 UTC, automated)
License (generator)	MIT
License (generated index)	Derivative of DataForSEO's OpenAPI spec — see NOTICE
Upstream source	dataforseo/OpenApiDocumentation

---

Why this exists

DataForSEO is one of the most comprehensive SEO and SERP data APIs on the market, with 554 endpoints spanning SERP data, keyword research, backlinks, on-page analysis, content analysis, business data, and AI-optimization signals. Working with that API from an LLM-based agent or coding assistant hits two practical problems:

Problem 1 — the DataForSEO MCP server does not cover everything. The official DataForSEO MCP exposes a useful but deliberately curated subset of endpoints. If you need something outside that subset (and there is a lot outside it), the MCP will not tell you the endpoint exists.

Problem 2 — the full OpenAPI spec is too large for an LLM context window. The authoritative openapi_specification.yaml is several megabytes of YAML. Loading it into an LLM prompt is either impossible (context limit) or wildly expensive (tokens). Even a grep tool struggles without an intermediate index.

This repository solves both problems with a single markdown file — dataforseo-endpoint-index.md — that flattens every endpoint into a category-grouped table showing HTTP method, path, operationId, and a short description. It is small enough to load into any LLM context, greppable enough to find the right endpoint in seconds, and regenerated weekly from the upstream spec.

Who this is for

• SEO and marketing engineers building integrations on top of DataForSEO
• Developers using LLM-based coding assistants (Claude Code, Antigravity, etc.) that need to know which endpoint to call

Usage — pointing a coding agent at the index

You're building an SEO or marketing tool with a coding agent and you want it to know exactly which DataForSEO endpoint to call. Pick whichever option fits your workflow — all three point your agent at the same up-to-date index.

Option 1 — Reference the raw URL (recommended, zero-install)

The committed dataforseo-endpoint-index.md on main is regenerated weekly by a scheduled GitHub Action, so the raw URL is always current within ~7 days of any upstream DataForSEO change.

Claude Code — add a pointer in your project's CLAUDE.md:

## DataForSEO reference
When writing code that calls the DataForSEO API, first consult the
endpoint index at
https://raw.githubusercontent.com/thomas-huerlimann/dataforseo-api-docs/main/dataforseo-endpoint-index.md
It lists all 554 v3 endpoints grouped by category with HTTP method,
path, operationId, description, and a commit-pinned GitHub permalink
(the "Spec" column) pointing at the exact lines of the upstream
openapi_specification.yaml that define the operation — including its
parameters, request body, and response schemas. Grep the index for the
right endpoint, then fetch that permalink to read the full spec for
just that endpoint. Never download the full openapi_specification.yaml.

Claude Code will WebFetch the index on demand, then fetch the Spec permalink for whichever endpoint it decides to call.

Cursor / Windsurf / Aider — equivalent instructions in .cursorrules / AGENTS.md / the tool's rules file.

One-off prompt — paste the raw URL into the chat and ask the agent to fetch it.

Option 2 — Fork and run your own scheduled regeneration

For users who want their own auto-updating copy, immune to upstream repo changes or inactivity-based workflow disabling:

1. Fork thomas-huerlimann/dataforseo-api-docs into your own account.

2. Go to the Actions tab on your fork and click I understand my workflows, go ahead and enable them (GitHub disables Actions on forks by default).

3. The scheduled workflow will run weekly in your fork. You can edit the cron in .github/workflows/regenerate-index.yml to change the cadence, or trigger it manually via the Actions tab (workflow_dispatch).

4. Point your coding agent at the raw URL of your fork's main branch instead:

   https://raw.githubusercontent.com/<your-username>/dataforseo-api-docs/main/dataforseo-endpoint-index.md
   

This gives you full control and no dependency on the upstream repo staying maintained.

Option 3 — Clone and regenerate locally

For offline, air-gapped, or fully-controlled environments:

git clone https://github.com/thomas-huerlimann/dataforseo-api-docs
cd dataforseo-api-docs
npm install
npm run generate                              # fetches latest spec from upstream
npm run generate:local path/to/spec.yaml      # or use a pre-downloaded spec

Then reference the local dataforseo-endpoint-index.md from your project (e.g. copy it into docs/ and @-attach it in Claude Code).

Typical agent workflow (applies to all three options)

1. Agent greps the index for a keyword (e.g. backlinks live, serp google organic) → finds the operationId, path, and the Spec permalink for that endpoint.
2. Agent follows the Spec permalink — a commit-pinned GitHub blob URL with a line range like #L9974-L9998 — to fetch just the lines that define that operation. The page shows parameters, request body schema, response schemas, and examples for the single endpoint, nothing else.
3. Agent writes the HTTP call.

This keeps the agent's context small at every step: the index is the cheap lookup (~180 KB of markdown, fits in any context window), and the Spec permalink gives exact, targeted access to the relevant ~30–100 lines of upstream YAML — never the full ~4 MB file. Because the permalinks are pinned to a specific commit SHA, they never rot even after DataForSEO edits the spec.

How the index stays fresh

The committed dataforseo-endpoint-index.md is regenerated every Monday at 06:00 UTC by a scheduled GitHub Action (.github/workflows/regenerate-index.yml). The workflow runs npm run generate against DataForSEO's upstream OpenAPI spec and commits the result only if the diff is non-empty. You can also trigger it manually from the Actions tab. GitHub disables scheduled workflows on public repositories after 60 days of inactivity, so if you notice the raw file going stale, open an issue and we'll re-enable the workflow.

Regenerating manually

Most users never need to run these — the scheduled Action keeps dataforseo-endpoint-index.md current. Run the generator yourself only if you want to test changes or work offline.

npm install
npm run generate                              # download the latest spec from GitHub
npm run generate:local path/to/spec.yaml      # offline, use a pre-downloaded copy

Output: dataforseo-endpoint-index.md at the repository root.

FAQ

How do I get a list of all DataForSEO API endpoints?

Read dataforseo-endpoint-index.md. It flattens all 554 DataForSEO v3 endpoints into a single greppable markdown table grouped by category, with HTTP method, path, operationId, and a short description for every endpoint.

How do I make Claude Code (or Cursor) aware of DataForSEO endpoints?

Add a pointer to the raw URL of dataforseo-endpoint-index.md in your project's CLAUDE.md (for Claude Code) or .cursorrules (for Cursor), and instruct the agent to consult it before writing DataForSEO calls. See Option 1 above for the exact snippet.

Why not just use the official DataForSEO MCP server?

The DataForSEO MCP exposes a curated subset of endpoints, not the full 554. This index complements the MCP: use the MCP for the endpoints it covers, and use this index when you need something outside the MCP's exposed surface.

Why not just load DataForSEO's OpenAPI spec directly into the LLM?

The upstream openapi_specification.yaml is several megabytes of YAML, which blows past most LLM context budgets and burns tokens on schemas you do not need. This index is a few hundred KB of markdown — small enough to load wholesale, and large enough to answer the only question the agent needs answered: which endpoint do I call?

How often is the index updated?

A scheduled GitHub Action regenerates it every Monday at 06:00 UTC from the upstream spec and commits if the diff is non-empty. Users who want a different cadence can fork the repo and edit the cron in .github/workflows/regenerate-index.yml (see Option 2).

Is this affiliated with DataForSEO?

No. This is an independent community tool published by Piz Digital, derived from DataForSEO's publicly available OpenAPI specification. See NOTICE for the full derivation statement.

Where do I report an outdated or missing endpoint?

Open an issue on this repo. If you have write access on a fork, you can also trigger the regeneration workflow manually from the Actions tab to force a fresh rebuild.

Source and attribution

The generated index is derived from DataForSEO's own publicly available OpenAPI specification:

• Upstream source: https://github.com/dataforseo/OpenApiDocumentation
• Upstream file: openapi_specification.yaml on the master branch
• Upstream author: DataForSEO

DataForSEO is the original author of the API specification content. This repository is an independent, community-published reference tool and is not affiliated with, endorsed by, or sponsored by DataForSEO. "DataForSEO" is a trademark of its respective owner.

License

• The generator source code in this repository (scripts/, package.json, README.md, LICENSE, NOTICE, .gitignore) is released under the MIT License. See LICENSE.
• The generated reference artifact dataforseo-endpoint-index.md is a derivative view of DataForSEO's OpenAPI specification. Piz Digital makes no claim of ownership and no claim of license over its content. See NOTICE for the full derivation statement.

If you intend to redistribute, republish, or build a product on top of the generated markdown, please consult DataForSEO's own terms of service and, if in doubt, contact DataForSEO directly.

---

Published by Piz Digital. Not affiliated with DataForSEO.