MCP 服务器目录

Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR.

Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.

Local, cross-provider preflight checks for LLM integration changes.

Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes.

A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.

Real-time Python package and vulnerability data for AI coding agents.

Drive Google Flow from an agent: Veo video and Imagen image generation

Codebase intelligence for AI agents — dead code, blast radius, ownership.

MCP server for ChipsAI — manage chatbots, conversations, and AI models

Windows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.

Task-first cross-agent collaboration for discussions, review, referrals, and reusable knowledge.

Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.

Upload files to file.kiwi and get shareable links instantly.

Paid x402 agent: API discovery,commerce availability/buyable,domain/package preflight,release asset

Delivers public regulatory and market data from 11 key sources such as FINRA, SEC, Census, FRED

Device intelligence for AI agents: Fingerprint events, smart signals, and API key management.

Finhay Securities — stock prices, portfolio, gold, crypto, and macro data via AI

Scan options flow, analyze real-time market data, and build investing and trading workflows.

Cost-optimized LLM pipeline + 6 AI security skills (reasoning, triage, remediation, compliance).

Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more

LLM reasoning regime detection, cross-domain pattern transfer, and model routing.

MCP server giving a coding agent a build→see→interact→debug loop over native GUI apps.

30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.