Fetch web search results for a query using the Kagi Search API. Supports filtering by domain, date, file type, and workflow type (news, videos, podcasts, images) with numbered results for easy reference.
MIT
604,430 tools. Updated 2026-09-23 19:54
"Kagi" matching MCP tools:
- Retrieve ranked organic web search results from a signed-in Kagi account using optional lenses, pagination, region, and time filters. Returns snippets for each result.MIT
- List your Kagi account's active and inactive lenses with stable numeric IDs. Use an active ID to set the lens parameter for searches.MIT
- Fetch web search results from Kagi for one or more queries. Results are numbered continuously so users can refer to specific results.MIT
- Search the web with Kagi for ad-free results. Use operators, date ranges, region, or lenses to refine.MIT
- Lists curated search scopes (lenses) available on your Kagi account, providing their IDs for use in search queries.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceMCP server for Kagi Search that uses your session token for web and news search without a separate API subscription.351 npmMIT
- AlicenseCqualityDmaintenanceMCP server integrating the Kagi Search API to perform web searches using the kagi_search tool.1MIT
Matching MCP Connectors
Bounded CSV profiling plus review-only host monitoring requests through one remote MCP endpoint.
8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.
- Translate text between languages with support for multiple language pairs. Uses Kagi Translate service for accurate translations.GNU Lesser General Public v2.1 only
- Execute web searches via Kagi’s API, enabling precise results retrieval using query parameters and customizable limits for efficient data access.MIT
- Search the web using Kagi. Provide a query and optional result limit to get relevant search results.MIT
- Convert any web page to clean markdown, capturing its full textual content for easy access.MIT
- Configures a tool preference for HyperRoute, specifying a preferred tool, optional margin, and note to influence future routing decisions.MIT
- Change the active chart to a specified type—bars, candles, lines, area, renko, kagi, and more—by name or number.MIT
- Retrieve recorded dead ends, no-gos, and works for a task to avoid re-attempting known failed approaches before retrying or re-planning.MIT
- Log a single autonomous action taken during a self-directed dev loop, tagging it with an impact tier, category, and description to maintain an audit ledger.MIT
- Create a markdown audit report of recent AI agent activity, grouping actions by category and listing dispatches with their resolved verdict or pending status.MIT
- Log the outcome of an approach tried or considered for a task, marking it as dead end, no-go, or works, so future attempts avoid repeating known failures.MIT
- Enumerate Windows/Samba shares, users, groups, password policies, and OS details from SMB services without authentication. Use for domain reconnaissance and identifying accessible resources.MIT
- Search the Exploit Database for public exploit code by software name, version, CVE, or vulnerability description. Use after identifying target versions to find matching exploits and their file paths.MIT
- Record subagent dispatches for audit and retry tracking. Counts retries per task to enforce budget limits via task status.MIT
- Record verification outcomes for agent dispatches by attaching CONFIRMED, REFUTED, or PARTIAL verdicts with optional notes, providing an auditable trail of subagent work validation.MIT
- Check dispatch, retry, and verdict status for a task before dispatching a subagent to enforce retry limits.MIT