Search

Enables AI assistants to interact with the Cocos Creator editor through the Model Context Protocol, providing 50 core tools for editor functionality.

An MCP server that enables Claude to retrieve real-time cryptocurrency market data from CoinGecko and answer price queries with live, grounded responses.

Per-unit cost of 13 back-office tasks done by a person vs by software, in the US, Greece and Ukraine, with an official statistic behind every hourly wage. Bundled data, works offline.

Provides a stdio MCP server for single-user local operation of the otaman platform, enabling agent orchestration, slash commands, and skill management within Claude Code without a remote bridge daemon.

Provides a single read-only tool to fetch extended Brazilian company registration data from a CNPJ number, including basic details. Works over HTTP MCP with any client.

MCP skill registry for writing styles — unlimited skills, live from GitHub, no re-installs.

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

Official Python client for Caura (formerly MemClaw; the memclaw_client import and MemClaw class remain permanent aliases) — governed shared memory for AI agent fleets (multi-agent, multi-tenant, MCP-native).

MCP server exposing the three-platform sandboxed runner protocol: run tasks in an evidence-protected sandbox, read the EXIT protocol, and get an autopsy report. Zero runtime dependencies. Every claim carries an experiment number.

给不支持多模态的 AI 模型（如 DeepSeek）提供识图能力——把图片发给云端视觉模型，返回文字描述。支持任意 OpenAI 兼容接口与 Anthropic 原生接口、主备双模型自动切换、BMP 智能路由、报错自动翻译。

Standard MCP server: query a SQLite database and return ready-to-render ECharts options (line/bar/pie/scatter) for data analysis.

Model Context Protocol server for documonster — lets AI assistants read, write and convert Excel, Word, PDF, CSV and ZIP documents.

Enterprise-grade LLM security guardrail library — 100+ Active Guards, LLM Traffic Monitor, 509 tests, zero core dependencies. Protects against prompt injection, data leakage, PII exposure, tool poisoning, goal hijacking, and supply chain attacks.

Permisyn MCP Gateway — every MCP tool call checked against an agent passport, and signed into a receipt.

SERP Lens SEO audits, browser inspection, and Search Console tools for AI assistants via MCP.

Self-contained local code intelligence: SQLite index, hc CLI, and hc_* MCP tools