Browse the catalog

Deploys a remote MCP server on Cloudflare Workers without authentication, allowing custom tool definitions and connections to AI Playground and Claude Desktop.

A telemetry and sprint insights dashboard built with FastAPI (Mock MCP) and React. Tracks execution metrics (input/output tokens, verification loops, human-in-the-loop delay) per Jira story and Git merge request to measure agentic throughput.

The worker version of BaSB-MCP, which can be easily deployed as Cloudflare Worker.

Provides a read-only MCP interface for Azure Data Factory monitoring and root-cause analysis, with a health check for MCP clients.

Read the contents of local files on demand. Quickly preview, copy, or analyze file text without leaving your workflow. Save time by pulling exact file content when you need it.

Allows creating and manipulating Feishu Whiteboards.

Agent skill for EaseClaw — the AI lead-finder your agent can drive. Pull warm leads scored by buying intent, draft replies in your voice, work the pipeline. Human sends every reply.

A curated MCP server for Semaphore UI that enables driving Ansible and Terraform automation from Claude with a safe, read-first tool surface.

Collaborative multiplayer AI workspace (PromptQL style)

MCP server based on saspy

MCP server for Apideck Unified APIs — Accounting, File Storage, HRIS, Vault, Proxy

MCP server for jewelry design ideation that guides users through structured interviews to create a design brief, then generates real jewelry design images via gpt-image-2.

Enables AI agents to efficiently read Python code by first providing file skeletons then fetching only needed implementations, reducing noise and cost.

MCP-domaintools is a server providing DNS and WHOIS query capabilities for AI assistants, developed by Patrick D'appollonio under the MIT license. It enables both local DNS lookups using system-configured resolvers and remote queries via DNS-over-HTTPS services (Cloudflare with Google fallback), supporting multiple record types including A, AAAA, CNAME, MX, NS, PTR, SOA, SRV, and TXT. The implementation offers three main tools: local DNS queries, remote DNS-over-HTTPS queries, and WHOIS lookups, making it particularly valuable for AI agents that need to perform domain-related investigations, verify DNS configurations, or retrieve domain registration information.

A Model Context Protocol server for DuckDuckGo search and web content fetching (using ocaml-mcp by avsm)

Enables complete Minto pyramid analysis through a 6-phase pipeline with sequential thinking, evidence gathering, and structured outputs.

MCP server for sovereign US legal workflows, providing Ed25519-signed manifests and offline-capable access via your own infrastructure.

An implementation of Anthropic's Model Context Protocol (MCP) using the Python MCP SDK. This repository demonstrates how to standardize communication between an AI agent and external tools, separating tool execution from agent logic for true cross-framework interoperability.

Create personalized greetings by name in the tone you choose. Get quick suggestions for friendly i…

Enables querying your Garmin Connect data including recent activities, detailed metrics, and daily stats through natural language.