Browse the catalog

Provides a Streamable HTTP MCP proxy for VS Code Copilot and Claude Code, using JWT client assertion to securely access NetSuite APIs.

Search 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.

An MCP server that bridges Claude Code with Emacs via emacsclient, enabling buffer, file, org-mode, git, and diff operations.

Enables Claude to write, compile, and execute formal verification models in Alloy and read raw mathematical graph structures back into its context window.

Enables MCP clients to submit long-running jobs that are executed safely in isolated child processes with a durable SQLite queue, configurable timeouts, retries with backoff, and backpressure.

Web tools for AI agents over MCP: scrape pages to Markdown, extract metadata, links and JSON-LD, run SEO audits, detect tech stacks, check XML sitemaps

Enable systematic scientific research through an 8-stage graph-based framework that supports hypothesis generation, evidence integration, causal inference, and collaborative analysis. Facilitate rigorous, interdisciplinary research with advanced features like Bayesian confidence tracking, bias detection, and temporal pattern analysis. Streamline research workflows with export capabilities and customizable configurations tailored to scientific domains.

Enables file operations and bash command execution on the local workspace, securely exposed to ChatGPT via OpenAI Tunnel.

Enables users to search for locations, businesses, and points of interest on an interactive OpenStreetMap map within ChatGPT conversations.

Cross-project memory sharing for Claude Code. One command install: claude mcp add memory-bridge -- uvx claude-memory-bridge

Connects to the Velixar memory API to provide persistent memory capabilities for AI assistants. Stores, searches, lists, updates, and deletes memories that persist across conversations. Supports memory tiers including pinned, session, semantic, and organization-level scoping.

Context Mem is a persistent memory infrastructure for AI coding assistants that automatically captures and retrieves context across sessions. It stores tool outputs, extracts meaning with content-aware summarization, and scores observations by importance for retrieval. The system provides 44 MCP tools across categories including core memory, content, knowledge graph, session, events, agents, and intelligence — all running fully locally with SQLite storage and no required API keys.

Enables AI language models to interact with Microsoft OneNote via a standardized interface, supporting notebook and page management through natural language.

这是一个MCP(Model Context Protocol)工具，用于统计AI生成的代码行数。该工具可以帮助您跟踪和分析每次AI生成的代码的规模。

Designed to highlight the power of Microsoft Fabric in the retail sector. How Fabric can serve not only as a unified data platform but also as a strategic foundation for preparing data for future AI-driven use cases

An MCP server that enables AI assistants to manage Dokploy infrastructure (Docker, projects, applications, databases, etc.) through natural language, acting as a universal translator between AI and cloud systems.

Enables read-only access to Pipedrive data including deals, persons, organizations, and pipelines, allowing LLMs like Claude to query and analyze CRM information through natural language.

MCP server that gives AI coding agents the ability to design UIs through Google Stitch. It generates production-ready HTML and screenshots from natural language prompts.

Provides seven tools for Dynatrace support workflows: knowledge search across documentation and community forums, page reading, customer concern classification, case triage with severity assessment, bug escalation drafting, customer response generation, and investigation planning. Caches knowledge locally for offline use.

Contextful is a context management system for AI coding agents that indexes projects using SQLite with FTS5 lexical search, symbol indexing, and graph-based expansion. Instead of repeatedly reading files, agents retrieve ranked, cited context packs, achieving significant token efficiency. A memory ledger lets agents store session learnings backed by evidence references from actual code files, persisting insights across sessions.