Skip to content
View cyanheads's full-sized avatar
:octocat:
:octocat:

Block or report cyanheads

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
cyanheads/README.md

Hi, I'm Casey 👋

Software Engineer based in Seattle. Passionate about sharing knowledge through open source.

I'm currently working on projects related to the Model Context Protocol (MCP), trying to build a better way for LLMs to interact with the world. I believe AI is an incredibly powerful tool and I'm hoping to make it more accessible and useful for everyone.

🚀 What I'm Building with MCP

Project Description
model-context-protocol-resources Contains practical guides, clients, and servers built while exploring the Model Context Protocol (MCP). Serves as a learning resource and collection of tools developed during the exploration of this new protocol.
atlas-mcp-server ATLAS (Adaptive Task & Logic Automation System), a Neo4j-powered task management system designed for LLM Agents. It uses a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows and includes Deep Research scaffolding.
filesystem-mcp-server Offers platform-agnostic file system capabilities for AI agents via MCP. Enables reading, writing, updating, and managing files/directories, featuring advanced search/replace and directory traversal.
obsidian-mcp-server Enables LLMs to interact securely with Obsidian vaults via MCP. Offers token-aware tools for searching, navigating, and updating Obsidian notes, facilitating seamless knowledge base management with Properties management.
mentor-mcp-server Offers AI-powered mentorship via MCP using Deepseek-Reasoning R1 through the Deepseek API. Provides LLM agents with a 'second opinion' for code review, design critique, writing feedback, and brainstorming.
toolkit-mcp-server Provides essential system utilities and tools for LLM agents via MCP, including IP geolocation, network diagnostics, system monitoring, cryptographic operations, and QR code generation.
github-mcp-server Integrates with the GitHub API via MCP, built in TypeScript. Provides a structured interface for LLM agents to manage repositories, issues, pull requests, code, files, and releases.
git-mcp-server Provides an enterprise-ready MCP interface for Git operations. Allows LLM agents to initialize, clone, branch, commit, and manage repositories via STDIO & Streamable HTTP.
ntfy-mcp-server Integrates with the ntfy.sh push notification service via MCP. Enables LLM agents to send highly customizable notifications to external devices.
perplexity-mcp-server Unlocks Perplexity's search-augmented AI capabilities for LLM agents via MCP. Provides access to real-time web information with robust error handling, secure validation, and optional reasoning transparency (showThinking).
mcp-reporter A streamlined utility that generates comprehensive capability reports for MCP servers. Helps developers understand available functionality across their MCP ecosystem for documentation and integration.
mcp-ts-template A beginner-friendly, production-ready TypeScript template for building MCP servers and clients. Includes essential utilities, examples, and type safety for a solid starting point.

💡 Other Projects

Project Description
repo-map Generates LLM-enhanced summaries and analysis of software repositories. Provides developers valuable insights into project structures, file purposes, and potential considerations across various languages.
claude-sidebar-modifier A Firefox browser extension allowing users to disable or adjust the width of the sidebar on Claude.ai for a customized interface.
scripts-ts A collection of cross-platform, standalone TypeScript utility scripts. Automates common development tasks like cleaning artifacts, generating structures, and managing dependencies.

💼 Open to Opportunities

I'm open to software engineering roles in AI/LLM development and infrastructure, with experience in building LLM agents, MCP servers and general AI tools. I'm always looking for ways to improve my skills and help others do the same.

🔗 Connect


When we share knowledge, everyone benefits.

Pinned Loading

  1. model-context-protocol-resources model-context-protocol-resources Public

    Exploring the Model Context Protocol (MCP) through practical guides, clients, and servers I've built while learning about this new protocol.

    214 19

  2. atlas-mcp-server atlas-mcp-server Public

    A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workfl…

    TypeScript 178 27

  3. obsidian-mcp-server obsidian-mcp-server Public

    Model Context Protocol (MCP) server designed for LLMs to interact with Obsidian vaults. Provides secure, token-aware tools for seamless knowledge base management through a standardized interface.

    TypeScript 87 19

  4. mentor-mcp-server mentor-mcp-server Public

    A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and ide…

    TypeScript 27 14

  5. repo-map repo-map Public

    repo-map generates LLM-enhanced summaries and analysis of software repositories, providing developers with valuable insights into project structures, file purposes, and potential considerations acr…

    Python 22 12

  6. git-mcp-server git-mcp-server Public

    Robust Model Context Protocol server for Git tools. STDIO & Streamable HTTP

    TypeScript 62 16