Browse the catalog

Memori provides SQL-native memory infrastructure that continuously captures interactions, extracts structured knowledge into facts, preferences, rules, and summaries, and intelligently retrieves relevant memory. The MCP server exposes recall and advanced augmentation tools that maintain context across sessions, reducing prompt tokens by over 95% compared to full-context approaches. Evaluated on the LoCoMo benchmark with 81.95% accuracy while using only 4.97% of full-context tokens.

innernote for Claude Code: draft, save and queue LinkedIn posts in your own voice.

Provides AI assistants with 6 tools to access Material UI component documentation, enabling consistent and well-designed React application development.

System resource monitoring that detects wasteful or suspicious processes.

Enables interaction with a PostgreSQL database via MCP, using Docker and NestJS for AI-powered database operations.

Provides access to UK Environment Agency's real-time flood monitoring data, enabling users to check flood warnings, monitor water levels and flow rates, and access historical measurements from monitoring stations across the UK.

Hawaii mortgage & VA loan expertise for Honolulu. 2026 loan limits, condo rules, FAQ.

A lightweight MCP server that converts LaTeX mathematical expressions to MathML using MathJax-node, providing both tool-based and resource-based conversion methods. Developed by happyan, this server enables easy integration of mathematical notation translation for developers and researchers working with scientific or technical documentation.

Insider political trading signal detection — this MCP server applies six institution-grade statistical algorithms to congressional stock disclosures, SEC insider filings, campaign finance records, and federal contract data, and returns scored findings to any MCP-compatible AI client in real time.

Read-only MCP server for Woodpecker CI that allows AI agents to check pipeline status and retrieve step logs across multiple self-hosted instances.

MCP server for statistical baselines — detect anomalous values

This NetBox MCP server provides the first read-write Model Context Protocol implementation for NetBox infrastructure management, enabling AI assistants to perform full CRUD operations on network infrastructure data through NetBox's REST API. Built by alexkiwi1 using FastMCP and featuring comprehensive coverage of NetBox object types (DCIM, IPAM, Circuits, Virtualization, Tenancy, VPN, Wireless), it offers 9 tools for individual and bulk operations including object creation, updates, deletion, filtering, and changelog access with proper error handling and security practices. The implementation includes an extensible client architecture with both REST API and abstract base classes for future ORM integration, making it ideal for network engineers and infrastructure teams who need AI-assisted NetBox management capabilities for device provisioning, IP address management, circuit tracking, and automated infrastructure documentation workflows.

Run long-running coding agents (Codex, Claude Code, etc.) in tmux sessions that survive orchestrator restarts.

The first open catalog and community for AI agents. Register, search, share skills, find partners. REST API + MCP. Free and open forever. First Czech MCP server included.

Enables large language models to access user geolocation information through EdgeOne Pages Functions using the Model Context Protocol.

A-share short-term trading decision skill for 1-5 day horizon.

Provides enriched blockchain data from Codex for use with MCP-compatible clients like Claude Desktop.

Build original LangGraph agents for Warden Protocol and prepare them for publishing in Warden Studio.

MCP Excel Server provides a robust interface for Excel file operations and data analysis through the Model Context Protocol. Developed by yzfly, it enables AI assistants to read, write, and analyze Excel files in various formats (XLSX, CSV, TSV, JSON), offering tools for statistical analysis, data filtering, pivot table creation, and visualization through charts and plots. The server leverages pandas, numpy, matplotlib, and seaborn to perform operations like summary statistics, data quality assessment, and visualization export, making it particularly valuable for data analysis workflows where users need to extract insights from spreadsheets without manual manipulation.

Local stdio MCP server that mirrors the public Gmail MCP server tool surface while calling the Gmail REST API directly, enabling email management tasks like creating drafts, searching threads, and managing labels.