"Agent Dilemma - Concept or Topic Search" matching MCP servers:

Enables LLMs to perform conceptual search over local PDF/EPUB documents using a RAG pipeline with corpus-driven concept extraction and WordNet enrichment.

Concept-test your product with synthetic consumers, straight from Claude Code. It turns free-text reactions from roleplayed personas into purchase-intent reports using Semantic Similarity Rating.

Enables access to a local Markdown knowledge base via MCP, currently only providing a ping tool.

Enables MCP agents to perform native X (Twitter) searches with original-post citations and transparent usage tracking. Supports existing Grok login sessions or explicit xAI API billing without runtime dependencies.

An MCP server that enables Claude Code to perform web searches via Bing, read webpage content, and get current time, with a smart search skill for structured multi-source verification.

Provides DuckDuckGo web search through MCP with automatic failover across multiple backends, enabling reliable query results even when individual backends are rate-limited or blocked.

MCP server for searching files on macOS by name or content using semantic and lexical search, providing file paths and line numbers for agents to read from.

Enables AI clients to run local semantic search over your own documents and code in Chinese or English, with embeddings computed on an Intel NPU. Also lets clients check index status and trigger reindexing.

Provides real-time Google search capabilities to AI assistants like Claude, bypassing anti-scraping mechanisms.

Screens AI agent tool calls before execution and tool results before the agent reads them, acting as an MCP proxy and hooks adapter with shadow, enforce, and strict policy modes.

A local-first MCP server that enables semantic search over PDF and DOCX documents using structure-aware parsing and vector storage. It allows users to query their local knowledge base through Claude Code without cloud dependencies or GPU requirements.

A local MCP server that gives Claude Code web search capabilities using DuckDuckGo, enabling discovery of URLs from natural language queries.

A local-first, no-API-key MCP server that enables LLMs to search the web, fetch pages, and read documents using multiple engines and smart fallbacks.

MCP server that finds open-source, commercially-usable icons and returns direct SVG download links, searching over 300,000 icons with license filtering.

MCP server for full-text search across PDF document collections with offline indexing, ranked results, snippets, and page rendering.

Enables Claude to plan trips by performing live searches against Google Flights, hotels, vacation rentals, activities, and events, plus weather and currency conversion.

MCP server for Google Search using a logged-in browser profile, delivering personalized, ad-free results with advanced operators and pagination. It also fetches web pages as markdown through the same browser session.

Job search mechanics for an AI assistant: search Arbeitnow/Adzuna/JSearch, fetch a single job posting, render a CV to PDF, lint it against your own configurable anti-fabrication rules, and log the outcome to your application registry. Never auto-applies.

A personal job-search assistant for Claude Desktop that searches real job boards, scores each job 0–100 for fit, and displays a ranked board for fast triage.

Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary tokens in honeypot files that trigger zero-false-positive leak alerts when they surface in agent output, files, or outbound requests.

Enables blazingly fast file and content searching in large codebases using ripgrep, with intelligent filtering, fuzzy finding, and directory tree visualization while respecting .gitignore and avoiding common bloat directories.

Clones a Git repo into a temp directory so MCP clients can search and read files from another repo for context.

Enables AI assistants to search JLCPCB's 450K+ electronic component catalog with real-time stock levels and pricing, supporting keyword search, filtering, and detailed component information.

Enables full-text search of macOS iMessages including link preview metadata. Works as an MCP server for Claude Desktop to search your messages locally.

Enables any MCP-capable harness to run queries through a real browser driving real search engines in a configurable fallback chain (Google, DuckDuckGo, Bing, Baidu, Sogou), with CAPTCHA or sign-in handoff, persistent per-engine cookies, and reported provenance for each result.

Enables searching and retrieving documents from a local folder to ground LLM answers in your files.

Enables AI assistants to search real content from Xiaohongshu and Zhihu, supporting keyword search, note details, and question retrieval.

Enables keyless web search across multiple engines with fallback and relevance ranking, plus anonymous HTTP(S) page fetching, all without API keys or vendor dependencies.

Exposes tools that let an agent search a local Markdown-based memory store, fetch full cards by id, write new knowledge cards that are indexed immediately, and inspect or rebuild the SQLite index. All retrieval runs locally over Chinese-friendly full-text search with graded exact/prefix matching, so agents without a memory system can recall prior notes while existing Markdown files stay read-only.

Enables natural-language search over locally indexed files such as markdown, text, images, videos, and PDFs, and retrieves indexed text or media metadata by path. It lets Cursor query a local embedding index built with Gemini and SQLite.

Enables agents to run multi-engine web searches, find GitHub repositories, and fetch web pages as Markdown with headless-browser fallback and automatic system-proxy support.

Federated, local-first search for AI agents: one query fans across transcripts, files, a knowledge graph, a vector store, the live web, and YouTube, fused by trust-weighted RRF into one ranked answer. Five modes (grep/lexical/semantic/hybrid/rerank), runs entirely on your machine over MCP.

Enables AI coding assistants to semantically search codebases by meaning rather than exact text, with zero external daemons and fully local embeddings. Works out-of-the-box with Claude Code, Gemini CLI, Antigravity, and Cursor.

A self-hosted MCP server for web search with multi-engine support, combining search, URL fetching, and deep research along with proxy routing and deduplication.

Enables to search academic papers in Japanese and English, inspect availability of full text, and download public PDFs locally.

A standalone MCP server that searches multiple scholarly metadata providers (PubMed, Europe PMC, bioRxiv, Crossref, OpenAlex, Semantic Scholar, arXiv), deduplicates results, and returns ranked literature with optional open-access full-text retrieval from Europe PMC.

A multi-engine web search MCP server that integrates with coding agents, offering parallel search, page fetching, X/Twitter search, deep research, and configurable free/API layers.

Enables AI assistants to evaluate job postings under a UK visa constraint, including sponsor-licence checks with confidence grades, screening for seniority and hard requirements, and role searches that exclude recruitment agencies. It also tracks application history to help avoid duplicate applications.

Free, unlimited web search MCP server using Gemini CLI's Google Search grounding to provide cited, live web results for any AI agent.

Google Search Console for Claude, Cursor & any MCP client — one sign-in, 30 seconds, no Google Cloud project. Six read-only tools (search analytics incl. Google Discover, period comparison with computed deltas, batch URL inspection, sitemaps) plus five built-in SEO analyses as slash-commands. Tokens stay on your machine. MIT.