Brightdata MCP vs Agent Search MCP
A side-by-side look at the Brightdata MCP and Agent Search MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Brightdata MCP for search & data extraction work as a local process; choose Agent Search MCP for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Brightdata MCP when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
API_TOKEN. - You want tools like
search_engine, scrape_as_markdown, search_engine_batch.
Choose Agent Search MCP when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
free_search, free_search_advanced, free_extract.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 73/100 · Great | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | Freemium | Free |
| Required env vars | API_TOKEN | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2,685 | 112 |
| Directory activity | 4 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 11 | 7 |
| Full listing | View Brightdata MCP | View Agent Search MCP |
Tools & capabilities
Brightdata MCP tools 11
search_engineScrape search results from Google, Bing or Yandex. Returns SERP results in JSON or Markdown (URL, title, description),Ideal forgathering current information, news, and detailed search results.scrape_as_markdownScrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.search_engine_batchRun multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.scrape_batchScrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.discoverSearch the web and rank results by AI-driven relevance. Returns scored results with title, description, and URL. Supports intent-based ranking, geo-targeting, date filtering, and keyword filtering.search_scrapersFind a Bright Data pre-built scraper (Web Scraper API, 1,200+ sites) for a site or data type, e.g. "amazon reviews" or "linkedin.com". Returns dataset_id, name, domain and collection_methods. Next: call get_scraper_details with a dataset_id and one method.get_scraper_detailsShow the scraper description, input fields, example input and main output fields for one method. Call before run_scraper and build the input from sample_input or input_fields. Records may contain more fields than output_fields lists.run_scraperRun a scraper method. input is a list of objects shaped like sample_input from get_scraper_details, one per URL or query. collect_by_url returns one record per input; discover_by_* methods return up to limit_per_input records per input, and every record is billed. Waits up to 45 seconds; if still running it returns snapshot_id with status "running": then poll get_scraper_progress and call get_scraper_results when ready. Records with an "error" field explain failed inputs.get_scraper_progressStatus of a run: starting, running, ready, failed or canceled.get_scraper_resultsRecords of a finished run. Returns status "running" if not ready yet.refresh_scrapersReload the scraper list now instead of waiting for the daily refresh.
Agent Search MCP tools 7
free_searchQuick public-web search for current facts and discovery. Use free_search_advanced for verification or domain filters. Use free_extract for one selected URL. Returns compact multi-source evidence with confidence, relevance, source_count, stop_reason, evidence_budget, and partialFailures. Provider families are counted once even when several adapters use the same upstream. Optional API providers run only when credentials and policy allow. @readOnly true @idempotent true — makes outbound HTTP requests to configured search engines. Injection detection and SSRF protection active.free_search_advancedVerification-oriented search with domain filters and waterfall fallback. Use for claim checking, Chinese-source search, or publisher restrictions. Start with free_search for quick discovery. The response exposes source_count, stop_reason, evidence_budget, and partialFailures. @readOnly true @idempotent true — runs waterfall progressive search across policy-allowed engines. Makes outbound HTTP requests to search engines and optionally to Jina Reader for content enrichment.free_extractExtract one selected URL into clean Markdown. Use after search when snippets are insufficient, or for a URL supplied by the user. It fetches one page; it does not search or bulk-extract URLs. Behavior: Makes an outbound HTTP request to Jina Reader (r.jina.ai) which fetches and converts the page to markdown. Has SSRF protection: blocks private IPs, localhost, and metadata endpoints. 10s request timeout — pages exceeding this will fail with a timeout error. HTTP errors (4xx, 5xx) are returned as structured error responses.fetch_github_readmeFetch README content from a GitHub repository. Best for: Getting project documentation quickly. Not recommended for: Non-GitHub URLs — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to raw.githubusercontent.com.fetch_csdn_articleFetch content from a CSDN blog article. Best for: Chinese developer blog content on CSDN. Not recommended for: Other Chinese sites — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to the CSDN article URL.fetch_juejin_articleFetch content from a Juejin article. Best for: Chinese developer articles on Juejin. Not recommended for: Non-Juejin content — use free_extract instead. @readOnly true @idempotent true — makes outbound HTTP requests to juejin.cn API.search_with_synthesisOpt-in deep search with waterfall verification and content enrichment. Returns structured results plus a prompt_hint; it does not call an external LLM. Use when multi-source evidence needs a synthesis handoff. free_search is the default for discovery; this path uses more tokens and network time. @readOnly true @idempotent true — runs waterfall search across free+paid engines with content enrichment.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Brightdata MCP
{
"mcpServers": {
"brightdata-mcp": {
"command": "npx",
"args": [
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "YOUR_API_TOKEN_HERE"
}
}
}
}
Agent Search MCP
{
"mcpServers": {
"lennney-agent-search-mcp": {
"command": "npx",
"args": [
"-y",
"agent-search-mcp"
]
}
}
}
Frequently asked questions
Brightdata MCP is categorized under Search & Data Extraction and uses a local stdio subprocess. Agent Search MCP belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Brightdata MCP for search & data extraction work and Agent Search MCP for search & data extraction.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Brightdata MCP is listed as freemium — a free tier with paid plans. Auth: api key required. Agent Search MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add brightdata-mcp and lennney-agent-search-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Brightdata MCP has a quality signal of 73/100 (Great) with 4 views, 0 installs and 2,685 GitHub stars. Agent Search MCP has 67/100 (Great) with 4 views, 0 installs and 112 GitHub stars.