"Technology pre-research resources" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
A2A & MCP Pre-Flight Security: SHA-256 tool schema rug-pull detection and liveness grades.
Shared, tested playbooks (recipes) for AI agents. Your agent searches recipes for real tasks (inbox triage, lead research, freelance gig hunting, content workflows), runs them, and reports results; weaker versions roll back only after failures from several independent sources plus an automated spam check. Free, no install, no email needed: one remote MCP URL.
KAI by Black Knight Technology is a neutral AI interoperability and commerce network connecting independent AI agents, tools, APIs, businesses, and marketplaces. KAI supports discovery, coordination, and collaboration across compatible standards, including MCP, A2A, HTTP APIs, and x402, without requiring participants to surrender ownership of their systems. Its public MCP server provides read-only information about the KAI network, supported standards, pricing, developer onboarding, and partic
License-checked research archive and technical-spec search for AI agents. Pay per call via x402.
mumo is a remote MCP server for multi-model deliberation. Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Agents can run a deliberation with `create_deliberation`, wait for results with `wait_for_round`, and steer follow-up rounds with `append_round` using structured signals like KEEP, EXPLORE, CHALLENGE, CORE, and SHIFT. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free tier available. API key required.
Connect custom domains via AI agents: DNS pre-flight checks, hand-off connect sessions and checks.
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
Hosted Option Desk: option analytics over the public SYNTH synthetic sample or an option-chain snapshot the user attaches for private analysis. Validates and repairs the snapshot, then returns Greek ladders, dealer gamma positioning, structure payoffs and chat-ready plots. No live market data, no orders. Research output, not investment advice.
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Find voluntary shared agent work: signed artifacts, research and questions. Read-only introduction.
Research on how AI agents find the web: a daily task that's checked automatically, and a guestbook.
Find and try paid AI agent skills for security, on-chain data, code, markets, research and news.
All-in-one autonomous AI agent super gateway with 15+ integrated engines — web intelligence, research, SEO, databases, mobile and more.
Infrastructure layer for agentic commerce. Measure website AI readiness, connect to agentic commerce protocols (MCP, UCP, AP2, GEO), and search resources.
An MCP server for deep research or task groups
Budget-aware AI agent research router with provider selection, validation, and automatic fallback.
One-to-three-cent spend routing, lead research, token-risk, and agent-tool comparison preflights.
Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
