Find Google search results with privacy protection using Startpage. Specify query, language, time range, and max results for your search.
MIT
622,085 tools. Updated 2026-09-29 18:05
"Startpage" matching MCP tools:
- Run a multi-engine web search to discover relevant URLs, returning a ranked, deduplicated link list to fetch and read next.MIT
- Retrieve web information from multiple engines with no API key required. Solve coverage gaps by specifying domestic or overseas engines, running concurrent queries, and citing relevant URLs as markdown links.Apache 2.0
- Run web searches through multiple engines with automatic fallback, no API key needed. Filter results by region, safety, and time.MIT
- Search live web sources to find local businesses and leads, prioritizing Google Maps then other engines like Yahoo, DuckDuckGo, Bing, and Startpage. No API keys required.-
- Divide a combined file, e.g. a scanned bundle of invoices or a merged PDF of statements, into typed segments with page ranges (split group), using a saved splitter or inline split classifications. Also the right FIRST step to locate one document or section inside a larger bundle — split, then parse/extract only the relevant segment instead of processing the whole file. Provide exactly one of splitter or config; inline config.splitClassifications needs a type: "other" entry. Each split includes startPage/endPage and, when Extend materializes child files, a fileId usable directly in other tools. Raw text input is not supported — splitting is page-based. Async: a status: "running" result with a runId is not an error — resume with get_split_run passing that runId, the same workspaceId and environment, and wait: true, repeating until the status is terminal; never re-submit the document. On UNAUTHORIZED or NOT_FOUND, re-call get_me for the granted targets. Output shape is documented at https://docs.extend.ai/splitting/response-format.md (get_documentation).ConnectorOAuth
Matching MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables web search across multiple search engines (DuckDuckGo, Bing, Startpage) with parallel execution and result deduplication. Also provides web page content extraction capabilities.2-
- AlicenseAqualityAmaintenanceName: MyWebSearch Type: MCP Server (stdio + streamable-http/SSE) Repository: https://github.com/wtznicy/my-websearch npm: my-websearch (npx -y my-websearch@latest) Description: Multi-engine web search MCP server, CLI and local daemon — no API keys or registration required. Searches bing/baidu/csdn/juejin/sogou (domestic, no proxy needed in mainland China) and duckduckgo/exa/brave/startpage (overse7847 npm1Apache 2.0
- Full-text keyword search across financial reports. <strategy> Choose the fastest path: 1. SPECIFIC DATA OR FACTS: use this tool with 1-5 keywords, then getFinancialReportPages at the returned page number. 2. LOCATE A SECTION OR FINANCIAL STATEMENT: use the statement name as keyword, matchMode="ALL", then read that page. 3. FULL REPORT STRUCTURE / TOC: skip this tool. Use getFinancialReportPages(startPage=1, pageCount=3~5) and read the TOC. 4. KNOWN PAGE NUMBER: skip this tool. Use getFinancialReportPages(startPage=N). Unknown company name/code: call searchCompanyInfo first (market required) and pass back stockCode + market. Currently CN-A and HK have data. </strategy> <critical_rules> 1. NEVER input full sentences. Extract 1-5 core keywords. 2. LANGUAGE ALIGNMENT — keywords MUST match the report language: - CN-A: Simplified Chinese (e.g. "净利润", "合并资产负债表") - HK: English (e.g. "net income", "consolidated balance sheet") 3. COGNITIVE TRANSLATION: convert conversational wording into financial terminology. 4. Report types (all markets): annual '{year}a4' (e.g. '2025a4'), interim '{year}h2' (e.g. '2026h2'). 5. Stock code format: CN-A 6 digits (000001), HK 5 digits (00700). Prefer stockCode and market returned by searchCompanyInfo. Do not invent padding. 6. Cross-company search (no stockCode): reportType is REQUIRED. 7. market is optional ('CN-A' | 'HK'). Omit to search all markets. </critical_rules>ConnectorDestructiveAPI key
- Read full page content from a financial report by page range. <strategy> 1. READ BY KNOWN PAGE: set startPage from financialKeywordSearch or a TOC. pageCount max 5. 2. DISCOVER REPORT STRUCTURE (TOC): startPage=1, pageCount=3~5. Read the returned pages for chapter names and page numbers, then call again with the target startPage. Unknown company name/code: call searchCompanyInfo first (market required) and pass back stockCode + market. Currently CN-A and HK have data. </strategy> <critical_rules> 1. startPage is 1-based. pageCount defaults to 5, max 5. 2. Report types (all markets): annual '{year}a4' (e.g. '2025a4'), interim '{year}h2' (e.g. '2026h2'). 3. Stock code format: CN-A 6 digits (000001), HK 5 digits (00700). Prefer stockCode and market returned by searchCompanyInfo. Do not invent padding. 4. market is optional ('CN-A' | 'HK'). Omit to search all markets. 5. For specific facts, prefer financialKeywordSearch first — it is faster than reading pages sequentially. </critical_rules>ConnectorDestructiveAPI key