Best for
- SEO teams that want to use DataForSEO APIs through AI assistants
- Developers who need configurable modules, prompts, or response fields
- Users needing local, HTTP, or Cloudflare Worker deployment
D
DataForSEO MCP Server
Community
Access DataForSEO SEO data through MCP.
- Category
- Other #158 of 230
- Stars
- ★ 254 Very popular
- Transport
- Streamable HTTP · SSE
- Runtime
- Node.js 14+
- Credentials
- API key / credential required
- License
- Apache-2.0
- Last commit
49FMRS · D
The repository provides an MCP server implementation for multiple DataForSEO APIs with local, HTTP, and Cloudflare Worker deployment options. The README documents credentials, module configuration, response filtering, and deployment, but no cached server manifest or specific tool identifiers are provided.
Strongest · Setup experience 12/20 Weakest · Reliability 7/20
Why each score
- Reliability 7/20
- The README describes local, HTTP, and Cloudflare Worker launch modes, environment variables, and intended error formatting, but the server manifest is not cached and no source files, CI, or committed tests are provided to verify MCP initialization, tool-list handshakes, or actual tool behavior. The documentation also contains a duplicate `const result` declaration in an example and inconsistent `src/code` versus `src/core` paths, reducing reproducibility and warranting substantial deductions.
- Security and permissions 10/20
- Credentials are supplied through environment variables, Cloudflare secrets, or HTTP Basic Auth, and no real secrets appear in the installation examples. The described functionality is primarily external DataForSEO data retrieval, with no stated delete, payment, or remote-command defaults. However, there is no source evidence confirming credential handling, HTTP authentication boundaries, least-privilege module behavior, network scope, log redaction, or request confirmation, so only a moderate score is justified.
- Maintenance 9/20
- The repository is not archived, declares an Apache-2.0 license, and has 233 stars and 4 open issues, providing some public maintenance signals. The supplied material contains no release history, commit cadence, dependency update policy, maintainer response evidence, vulnerability disclosure channel, or security-response process. Stars are discovery signals only and do not increase the score, so significant points are deducted.
- Documentation 11/20
- The README covers runtime prerequisites, credential configuration, module selection, response filtering, field configuration, HTTP/Worker deployment, and a Claude client example, making the basic installation path reasonably complete. It lacks a reviewable tool inventory and parameter reference, API cost and rate-limit information, data-boundary disclosures, troubleshooting guidance, compatibility details, and security operations guidance. Module defaults, directory paths, and the Merchant spelling also contain inconsistencies, preventing a near-full score.
- Setup experience 12/20
- The material provides Node.js 14+, npm/npx commands, local and HTTP launch instructions, environment-variable examples, Cloudflare deployment steps, and a Claude HTTP configuration example. Users must still obtain DataForSEO credentials and configure environment variables manually; there is no cached manifest, directly importable complete client configuration, platform-specific guidance, or test evidence. This is workable but substantially manual, so it remains below the maximum.
Static review · not runListed 2026-07-30
Read the FMRS scoring method →Fit and risk
What it can accessUses the network
Not for
- General MCP users without a need for DataForSEO APIs
- Users without DataForSEO API credentials
- Users seeking browser automation, file storage, or database capabilities
Required permissions
- Requires a DataForSEO API username and password
- Can access data from the enabled DataForSEO API modules
- HTTP mode supports Basic Authentication or environment-based credentials
Risks and side effects
- API credentials must be protected when supplied through environment variables or Cloudflare secrets
- Enabling many modules or full responses may increase response size and API usage
- The README marks SSE transport as deprecated
- Data availability and costs depend on the DataForSEO account and service limits
Setup
Before you start
Runtime：Node.js 14+
DATAFORSEO_USERNAME
Your DataForSEO account login, obtained after registering at dataforseo.com.
DATAFORSEO_PASSWORD
Your DataForSEO API password, paired with the username; find it in your DataForSEO account settings.
Other optional settings (4)
ENABLED_MODULES
Optional comma-separated list of modules to enable (e.g. SERP,ONPAGE); all modules are enabled if unset.
ENABLED_PROMPTS
Optional comma-separated list of prompt names to enable within the enabled modules.
DATAFORSEO_FULL_RESPONSE
Optional; set to true to return full unmodified API responses instead of filtered, concise ones.
DATAFORSEO_SIMPLE_FILTER
Optional; set to true to use a simplified filters schema for LLMs like ChatGPT that cannot handle nested structures.
Node.js 14 or later and DataForSEO API credentials are required. Clone the repository, run npm install, set DATAFORSEO_USERNAME and DATAFORSEO_PASSWORD, then run npm run build and the appropriate start command. The package can also be installed globally or run with npx. HTTP mode uses port 3000 by default; Cloudflare Worker deployment requires Wrangler.
MCP config · JSON
{"name":"DataForSEO","description":"Access DataForSEO APIs via Cloudflare Worker","transport":{"type":"http","baseUrl":"https://your-worker.your-subdomain.workers.dev/mcp"}}
Works in clients that read an "mcpServers" key. For clients such as VS Code that use a different key, the configurator below converts it.
.vscode/mcp.json
{
"name": "DataForSEO",
"description": "Access DataForSEO APIs via Cloudflare Worker",
"transport": {
"type": "http",
"baseUrl": "https://your-worker.your-subdomain.workers.dev/mcp"
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
Check that it works
After starting the server and connecting your client, the tool list should include tools from the enabled modules such as SERP or KEYWORDS_DATA; running a keyword query that returns DataForSEO search volume or SERP data confirms the connection works.
Troubleshooting
- Verify that Node.js is version 14 or later
- Check that DATAFORSEO_USERNAME and DATAFORSEO_PASSWORD are set and valid
- Check the spelling and values of ENABLED_MODULES, ENABLED_PROMPTS, DATAFORSEO_FULL_RESPONSE, and DATAFORSEO_SIMPLE_FILTER
- For HTTP mode, check port 3000 and Basic Authentication credentials
- For Worker deployment, check Wrangler login, secrets, and the Worker entry path
- If fields are missing, inspect the field configuration or temporarily disable field filtering
Things to try
Once connected, you can ask your AI assistant things like:
- Get the search volume and CPC for the keyword digital marketing in the US
- Show me the live Google SERP top results for the keyword seo tools
- Analyze backlinks for example.com, including referring domains and anchor text distribution
- Crawl example.com and report on-page SEO performance metrics
Use cases
Keyword research and search-volume analysis
Real-time SERP data retrieval for Google, Bing, and Yahoo
Website crawling and on-page SEO analysis
Backlink, domain, and competitor analysis
Brand monitoring, sentiment analysis, and citation management
Supported clients
Claude
Listed from the project's documentation, not tested by this site.
Overview
DataForSEO MCP Server is a TypeScript Model Context Protocol server that lets AI assistants access selected DataForSEO APIs through a standardized interface. It covers SEO, SERP, keyword, on-page, backlink, business, domain analytics, content analysis, and merchant data, with local, HTTP, and Cloudflare Worker deployment options.
Similar servers
Hevy MCP
77 · B
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl MCP Server
75 · B
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
BioMCP
75 · B
One binary. One grammar. Evidence from the biomedical sources you already trust.
Compartment
75 · B
Encrypted, fully offline long-term memory for AI agents
Source revision 1fc6d197f114 Data synced 2026-10-19 Read the FMRS scoring method