"Reverse engineering or reverse direction search" matching MCP servers:

Enables repository-aware lifecycle management and controlled delegation of coding tasks to trusted worker harnesses via MCP, with execution isolation, recovery, and verified handoff.

Deploys a minimal MCP-compatible Python tool server on Amazon EKS that establishes an outbound WebSocket connection to an AgentCore Gateway. It exposes two tools (get_system_info and echo_data) for tool discovery and invocation through the MCP protocol.

Scopes MCP tool definitions and strips Markdown from outputs to minimize token usage, improving agent cost and accuracy.

Universal search engine for AI agents. Discover products, services, and businesses across every category. 10 MCP tools, zero LLM calls, millisecond responses.

Enables AI agents to perform web search, extraction, and research across multiple provider backends with persistent multi-key rotation and auditable routing. Supports MCP, CLI, and Agent Skill entry points.

An MCP server that exposes an Agno agent with Google Gemini reasoning and Serper web search, enabling MCP-compatible clients like Claude Desktop to perform agent-driven web searches and receive synthesized answers.

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.

An MCP server that enables web search capabilities using OpenAI's o3 model, allowing AI assistants to perform text-based web searches and return AI-powered results.

A Model Context Protocol Server search realtime flight detail with multiple fligh carrier, price , stop , time duration for any given date using simple prompt

Enables AI-powered web searches using Google's Gemini 2.5 models with Google Search Grounding. Supports multiple Gemini models (Flash, Flash-Lite, Pro) with configurable thinking budget and web search capabilities.

Exposes SearXNG web search and query autocomplete to AI clients, returning ranked results, instant answers, and suggestions with filters for category, language, time range, engines, page, and safe search. It is distributed via npx and requires a self-hosted SearXNG instance with the JSON format enabled.

Enables free-first web search in English and Chinese with no API key required, returning compact multi-source evidence while keeping provider failures, stop reasons, and budget limits visible. Optional paid providers are used only when routing policy and credentials allow.

Enables web search for the pi coding agent using z.ai GLM native search with a DuckDuckGo fallback.

Enables free-first English and Chinese web search through zero-key sources, returning bounded multi-source evidence with visible provider failures and optional paid escalation under policy.

Enables English and Chinese web search through zero-key sources plus optional paid providers, returning compact multi-source evidence with visible provider failures and bounded request and evidence budgets.

Enables free-first English and Chinese web search through zero-key engines plus optional paid providers, returning compact multi-source evidence with bounded token and request budgets. Each result exposes provenance, independent source counts, routing decisions, and visible provider failures so agents can verify claims rather than receive unexplained empty results.

Enables parallel research across multiple cheap AI worker models, splitting a question into sub-questions and synthesizing one sourced answer with references.

Enables clients of tool-heavy MCP aggregators to find and use upstream tools on demand through four fixed bridge tools (search, describe, call, refresh), cutting per-turn tool context from ~180k tokens to ~2–3k. It merges multiple upstream servers behind sticky sessions and a local lexical BM25 index, so only the schemas actually needed are retrieved.

Enables free-first English and Chinese web search without any API key, returning compact multi-source evidence that preserves provenance, source-family counts, and visible provider failures. Request and evidence budgets bound each query, while optional paid providers run only when an explicit routing policy and credentials allow.

Enables MCP clients that lack built-in search — such as Claude Code through Bedrock or local LLM clients — to run web queries against Amazon's operated search index via a Gateway deployed in your own AWS account, with queries never leaving AWS and citation URLs preserved. Supports IAM/SigV4, Cognito, and API key authentication, per-gateway rate limits, IP and domain restrictions, and result filtering by domain and publication date.