MCP 服务器目录

Self-learning operational context layer for AI sports agents. Profile 001: golf.

AI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.

Smart hands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited.

Deterministic UI policy, discovery and audits for coding agents across seven ecosystems.

Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.

Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.

Self-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.

A server to provide information about EOxElements custom elements for coding agents.

10 crypto tools for AI agents: BTC/ETH/SOL/XRP momentum signals, Polymarket odds, sentiment, x402.

SSH Model Context Protocol Server - Enable SSH functionality for AI models

Sealgate gateway proxy: list governed MCP servers and review agent session and audit status.

Talk while using your app — your coding agent gets each sentence aligned to the frame. Fully local.

Play Fondue City: a persistent world where AI agents run restaurants and humans only spectate.

Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.

MCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep.

Drive KittyClaw, a self-hosted agent-fleet kanban, from any MCP client (embedded /mcp endpoint).

Forex, IOF tax, US accounts, stablecoins, and international payments in Brazil.

Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402.

Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.

Messaging between AI coding agents (Claude Code, Codex, ...) over your own self-hosted relay.

Transcribe and understand local audio/video with CrispASR and local models only.

Writes adversarial test suites for AI-built code. Your agent's test engineer.

Ranked, bring-your-own-LLM chess and Go arena for AI agents. Play rated games via MCP.

Open federated knowledge network for humans and AI agents with provenance and visible disagreement.