Browse the catalog

The Deep Research Assistant is meticulously crafted on Mastra's modular, scalable architecture, designed for intelligent orchestration and seamless human-AI interaction. It's built to tackle complex research challenges autonomously.

MCP server for cover letter generation

Crypto Fear & Greed Index MCP.

E-commerce product management MCP server providing CRUD operations for product inventory through MySQL database integration. Features clean layered architecture with TypeScript models, repository pattern for data access, Zod schema validation for input sanitization, and service layer business logic. Exposes tools for creating, reading, updating, deleting, listing, and searching products with proper error handling and connection pooling. Includes comprehensive product attributes like SKU, name, description, price, and quantity with automatic timestamp management.

This PostgreSQL MCP server, developed by Anthropic, provides read-only access to PostgreSQL databases for AI models. Built with TypeScript and leveraging the pg library, it offers tools for executing SQL queries and retrieving schema information. The implementation focuses on security by enforcing read-only transactions and omitting sensitive connection details. It's particularly useful for AI assistants or applications needing to analyze database structures, execute complex queries, or integrate PostgreSQL data into their workflows without requiring direct database access or deep SQL knowledge.

An MCP server that diagnoses GitHub Actions workflow failures and automatically creates repair pull requests using LLM-generated unified diffs. It includes a governance layer to orchestrate autonomous fixes or human-reviewed repairs based on risk assessment thresholds.

Provides access to the Tamil Roman Catholic Bible and daily devotional content (daily verse, Mass readings, saint of the day, promise-box verses, daily quiz) as tools for AI assistants.

Exposes read-only location history and related data from Dawarich via MCP tools, designed to run behind an OAuth-terminating proxy.

Flask-MCP-Plus enables developers to create MCP servers using Flask, with support for defining tools, resources, and prompts with automatic schema generation and type safety.

MCP server exposing Fahsai's public fire, air quality, weather, and power plant data for mainland Southeast Asia and surrounding areas

g:Profiler (University of Tartu) — functional enrichment analysis for a gene list against GO, KEGG, Reactome, WikiPathways, TRANSFAC, miRTarBase, CORUM, HPA and HPO, plus gene/protein ID conversion and cross-species ortholog mapping. Keyless.

IBKR Portfolio Builder provides MCP tools for top-down investment research using Interactive Brokers data. It exposes 468 typed screeners across 16 categories tagged by strategy intent, enabling workflows from sector selection through stock screening to candidate refinement. Tools cover screener execution, news retrieval, account summaries, and contract searches, with support for OAuth 2.1 and static bearer token authentication.

Enables AI agents to capture screenshots of windows (e.g., WeChat developer tools) and save them locally, allowing the agent to read the image directly and close the code-change-to-review loop without OSS or network.

The social network for AI agents.

Enables Claude Code to control Ansys engineering simulations (CFD, FEA, meshing, post-processing) through natural language commands via PyAnsys.

Enables AI agents to scan payment endpoints for safety, returning a letter grade (A–F) and verdict before authorizing payments.

MCP server for scanning browser pages and collecting element locators (XPath, testId, CSS).

Enables searching the Oakland Open Data catalog and querying datasets with Socrata SoQL. Provides access to metadata and rows from over 1000 live data sources via Pipeworx.

Provides semantic search over a self-building personal technical knowledge base that automatically collects and distills content from GitHub Trending, AI news, and arXiv.

Exposes a Kubernetes cluster to MCP-compatible AI clients, enabling read-only and optional write operations on cluster resources like pods, deployments, and namespaces through natural language.