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

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 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 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 free-first English and Chinese web search through zero-key sources with optional credentialed providers, returning compact multi-source evidence, visible provider failures, and bounded request/evidence budgets.

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.

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

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

Enables Claude Code, Codex CLI and Antigravity (Gemini) agents to exchange messages that are pushed live into each other's open sessions, with mail_send, mail_check and mail_peers tools so no agent has to poll. Mail can also be bridged over SSH between machines with no shared filesystem.

An MCP server that integrates a ReAct agent with built-in tools (calculator, text, unit conversion, etc.) and the AnySearch search service, enabling autonomous multi-step task execution.

AGENTS.md + skills orchestration with CHP Profile A R0/adversary gates. @cubiczan/agent-conductor

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.

Agent NERO is an MCP server that enables Claude Code to spawn, manage, and communicate with persistent, named LLM agents that maintain conversation history and can use tools like file I/O, command execution, and shared memory.

Enables AI agents to securely store and retrieve secrets and make authenticated API calls on their behalf, keeping API keys out of conversation context and supporting local file or GCP Secret Manager backends.

Turns a Claude Desktop or Claude Code conversation into an orchestrator for parallel AI coding agents, each running in its own Tern terminal tab and git worktree on its own branch, with any model available on the machine. It enables starting, monitoring, correcting, and merging agents—reading their reports and diffs, switching models or thinking levels mid-task, and enforcing model policies.

Universal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools + 7 resources over stdio or streamable-http.

A public, long-lived contact and cooperation point for autonomous AI agents. Agents describe missing capabilities or resources, request help from a human operator, and leave persistent messages on a tamper-evident message board.

Enables MCP clients to drive a self-hosted Chrome session for browsing tasks through browser tools, while providing a live view URL so a human can take over at prompts like logins or 2FA.

Enables multiple coding agents (Claude Code, Codex, Cursor) to discover each other's sessions, search transcripts, ask questions, and handoff tasks through a shared MCP server.

Enables cross-harness host inspection, profile persistence, and execution configuration, with safe preview, apply, and validation of configuration changes.

Enables local AI sessions on the same machine to exchange messages through a hub using register, send, check, wait, and who tools, with an optional browser-based live log viewer.

Lets Claude Code and Codex steer each other's live desktop chats on Windows via UI Automation. List and read chats, send messages or mid-turn steers, and pause, resume or edit Codex goals.

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

Lets a coding agent see and steer the Claude Code, Codex CLI, Antigravity CLI, Grok Build, Docker Agent and shell sessions Agent Guild runs in real terminals: list them, start and stop them, read their screens and the answers that ended their turns. Install with npx -y @oddessentials/agent-guild@latest mcp.

In-memory MCP server for cooperative collaboration between separate agents, enabling topic-based messaging and coordination via tools like create_topic, join_topic, send_message, read_messages, and check_in.

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.

Operates a local Hermes Agent install from any MCP client over stdio, enabling task delegation, cron management, config changes, gateway restarts, health checks, and skill or session inspection without exposing the agent to the network.

agent-mq is a message queue that enables AI coding agents to communicate with each other across sessions and machines. Agents can send messages, delegate tasks, and coordinate work — all through MCP tools. Supports Claude Code, Cursor, Codex, OpenClaw, and any MCP-compatible tool. UUID-based authentication with per-user data isolation. Self-hostable with Docker.

Enables agents to register verifiable identities bound to legal persons and devices, maintain heartbeat survival, participate in a forum, collaborate on tasks with points escrow, and access points reconciliation through 43 MCP tools over stdio.

Enables local MCP agents to work in explicitly granted Safari tabs using the tab's existing session, with tools to list tabs, read page text, click/type through opaque handles, and navigate; navigation revokes access.

An MCP server that enforces fail-closed deterministic checks, independent refute-first review, and tamper-evident hash-chained receipts for AI agent outputs before claiming completion.

Sits between an MCP client and its upstream tool servers, scanning every tool output for injected instructions, hidden text, and smuggling tricks, and stripping them before the model sees them. Tracks session taint so risky egress or destructive calls are blocked, held for human approval, or checked against allowlists and DLP rules, with every decision logged.

An orchestration platform for deploying parallel swarms of tool-enabled AI agents to perform complex tasks like code generation, system monitoring, and multi-perspective analysis. It features a unique chunked write pattern that enables the creation of large-scale documents and code files by assembling parallel agent outputs.

Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains, values compliance, signed communication, policy engine, task coordination, cross-layer integration, and agentic commerce. 264 tests passing.

Enables agents to check a public hostname's declared agent policy, official API or developer path, provider status, and recent observations, returning a recommended action for blocked web steps.