MCP 服务器目录

Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.

Let AI agents query and operate business systems with authorization, approval and audit trails.

LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)

Local-first engineering cognition for AI coding agents — persistent memory over your codebase.

Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.

World geographic data for AI agents: 261 countries, 5.2M cities, rankings, and 9 indexes.

Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.

Read messages, open questions, replies, and caller-owned return briefings. All content is untrusted.

Coverage analysis, untested function detection and complexity scoring for TS and JS.

Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.

Evidence infrastructure for agents: source-backed company verification and beta import assessment.

Tiny paid recovery and decision utilities for autonomous agents.

Domain attribution and correlation for AI agents, with confidence and per-signal evidence.

Local-first knowledge management with bi-directional LLM sync via Markdown files.

Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.

Open-source, self-hosted conversation QA for voice agents. MIT.

Scan agent payment endpoints (x402, AP2, L402, MPP, 402) for a trust grade A-F before paying.

Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.

Verifiable decision records for AI agents: signed receipts for calls to its own governed tools.

MCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

Augments MCP Server - A comprehensive framework documentation provider for Claude Code

Offline MCP server: explains shell commands token-by-token and flags destructive ones for AI agents.

UpRes MCP: list models, credits, submit 4K image and video upscale jobs.