AI & Agents MCP servers

Discover managed business agents. Private capabilities require owner authorization and eligibility.

MCP catalogue + x402 Doctor. Paid HTTP via x402 (USDC), IETF MPP, or Stripe cards on $1+ routes.

Human-in-the-loop expert for when your agent is stuck: math, optimization, operations research, AI.

AI agent marketplace on BNB Chain: find agents, backtest trading rules, follow live trading agents.

Owner-authorized puzzle: synthetic HTTP clues win sandboxed homepage art. No server access.

Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.

Open model files with recorded SHA-256 and licence labels. Ask for what's missing.

Read-only search over 1,771 AI agent tools and 248 MCP servers. No sign-up needed.

Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working.

China MCP gateway hosting HTTP APIs for Doubao/Tongyi/Wenxin/Claude; weather, currency, holiday.

Voidly MCP: research, Atlas score, capabilities; gated Voidpay, Voidmail, Home, board and bounty.

Agent asks a person go/stop/wait before Slack, CRM or risky steps. $49 for 30 days.

Search 300+ expert prompt templates for work, grade a prompt out of 10, and price AI models.

Read-only lookup of tested agent tools and MCP servers: scores, test evidence, deprecation.

Discover AI agent insights, open research questions, and reproducible findings in a public commons.

Ask a named human, Geoff, a question your agent cannot compute and fetch his answer later.

Ask a room of Claude, GPT and Gemini from your AI tool, search its memory and log decisions.

AI-native $0.001 interpretation and state-deviation checks over x402.

MCP marketplace: AI agents buy services from other agents per call in USDC, plus a bank cash-out

Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.

Search a curated directory of open-source AI agents, MCP servers and AI developer tools.

Say what should happen; get the right app tool per step, an n8n workflow, or the call itself.

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

Search, inspect and inject full source modules (code + AI rules + MCP) pinned to a Git commit.

Read-after-write receipts for agents: did your write actually land? Free, signed, re-checkable.

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.

Prompt marketplace for AI agents: browse and buy prompts with x402 (USDC on Base).

Find and compare headless apps (CLI, MCP, API) for agents, with sources, lessons and changes.