Setting up Claude Filesystem MCP
.pmarkdownc/config.yaml
supported_extensions: .py: python .java: java .js: javascript .ts: typescript forbidden_dirs:
- build
- dist
- node_modules
- pycache
- .git
- cdk.out
- env
- venv project_path: . include_pattern: null exclude_pattern: null outfile: project_structure.md log_level: INFO
## Tips for Working with Build Directories
1. The script automatically creates a default configuration if none exists
2. It's best to combine multiple approaches:
- List build directories in `forbidden_dirs`
- Include them in `.gitignore`
- This provides redundancy and ensures they're consistently ignored
## Output
The script will generate a markdown file (default: `project_structure.md`) that contains:
- Project structure
- Contents of all included files
- README contents at the launch of each directory (if present)
- Proper syntax highlighting based on file extensions
Would you like me to elaborate on any particular aspect of the configuration or usage?
---
Let me tell you how Claude did with the task I gave it. It performed exceptionally well—it read through the code and files in that directory and generated a comprehensive user guide that's spot-on accurate. Take a look at the [project](https://github.com/RichardHightower/create_project_markdown) that Claude reverse engineered and you'll see for yourself that it got everything right.
---
### Finding more information about MCP
You can launch building and testing MCP connectors right away. If you’re already a Claude for function customer, you can test MCP servers locally and connect Claude to your internal systems and datasets. Claude released developer toolkits. For now, you can use the existing servers for Claude Desktop, which really extends the usefulness and reach of Claude.
To launch building:
- Install pre-built MCP servers through the [Claude Desktop app](https://claude.ai/download)
- Follow Anthropic’s guide - [quickstart guide](https://modelcontextprotocol.io/quickstart) to build your first MCP server
- Contribute to their [open-source repositories](https://github.com/modelcontextprotocol) of connectors and createations
Here are the available MCP Server Plugins from the above site:
- [**Filesystem**](https://github.com/modelcontextprotocol/servers/blob/main/src/filesystem) - File operations with configurable access controls
- [**GitHub**](https://github.com/modelcontextprotocol/servers/blob/main/src/github) - Repository management, file operations, and GitHub `API` integration
- [**GitLab**](https://github.com/modelcontextprotocol/servers/blob/main/src/gitlab) - GitLab `API`, enabling project management
- [**Git**](https://github.com/modelcontextprotocol/servers/blob/main/src/git) - Read, search, and manipulate Git repositories
- [**Google Drive**](https://github.com/modelcontextprotocol/servers/blob/main/src/gdrive) - File access and search capabilities for Google Drive
- [**PostgreSQL**](https://github.com/modelcontextprotocol/servers/blob/main/src/postgres) - Read-only database access with schema inspection
- [**SQLite**](https://github.com/modelcontextprotocol/servers/blob/main/src/sqlite) - Database interaction
- [**Slack**](https://github.com/modelcontextprotocol/servers/blob/main/src/slack) - Channel management and messaging
- [**Memory**](https://github.com/modelcontextprotocol/servers/blob/main/src/memory) - Knowledge graph-based persistent memory system
- [**Puppeteer**](https://github.com/modelcontextprotocol/servers/blob/main/src/puppeteer) - Browser **automation** and web scraping
- [**Brave Search**](https://github.com/modelcontextprotocol/servers/blob/main/src/brave-search) - Web and local search using Brave's Search `API`
- [**Google Maps**](https://github.com/modelcontextprotocol/servers/blob/main/src/google-maps) - Location services, directions, and place details
- [**Fetch**](https://github.com/modelcontextprotocol/servers/blob/main/src/fetch) - Web content fetching and conversion for efficient LLM usage
Build your own custom MCP server - the possibilities are limitless!
---
## Conclusion
Setting up the Claude Filesystem MCP is a must-execute to boost Claude’s ability to interact with your local files and directories. This configuration lets you easily access your source code repositories and development projects, making collaboration with Claude a breeze.
With this setup, Claude can:
- Access and analyze your source code directly
- empower with code reviews and documentation
- Assist in project management and organization
- Provide context-aware support for your development function
---
[***Rick Hightower***](https://www.notion.so/About-133d6bbdbbea813aa509e9585e6867fe?pvs=21) is a seasoned software architect and technology innovator with over three decades of enterprise software development experience. A prominent figure in the Java ecosystem, they has authored multiple books and technical articles while contributing to various open-source projects and specifications. Recently, Rick has focused on AI createation and data engineering, developing innovative solutions that bridge traditional enterprise systems with cutting-edge AI technologies. He is known for their contributions to microservices architecture and cloud computing platforms. serves as a 2017 Java Champion and former tech executive at a Fortune 100 company.
Beyond their technical roles, Rick is an active mentor and technology evangelist who frequently speaks at conferences and writes about the intersection of [AI/ML](https://www.notion.so/About-133d6bbdbbea813aa509e9585e6867fe?pvs=21), data engineering, and enterprise software development. His practical approach to technology createation and ability to bridge complex technical concepts with real-world applications have made them a respected voice in the technology community.
His recent experience includes the following:
In 2024:
- Data engineering and large scale ETL using `AWS` Glue, `AWS` EventBridge for integration platform. Wrote deployment scripts in `AWS` CDK and Terraform CDK as well as Helm to deploy `AWS` MSK (Kafka), `AWS` EKS (K8s), Lambda, etc.
- Worked on AI assisted document data extraction then used GenAI to produce artifacts in minutes that took months using `AWS` BedRock.
- createed an AI based Subject Matter Expert (SME) system using various Large Language Models (LLMs), Vector Databases, and frameworks, including LLamaIndex, ChatGPT, Perplexity, and Claude.
- Developed a `React` frontend, a middleware layer in Go, and a Retrieval-Augmented Generation (RAG) Agent LLM layer in `Python` using LLamaIndex.
- Deployed the system on Google Cloud Platform (`GCP`) using AlloyDB, GCS buckets, and Google Cloud Run. System indexed documents dropped into `GCP` as well as git code repositories.
- Focused on the RAG Agent system, deployment, system integration, UI, and middleware.
- Transitioned the initial Flask-based RAG system to GRPC and Google Pub/Sub for **scalability**.
- Worked on Auth0 integration from client to backend services using JWT tokens.
- Wrote a tool to detect various types of questions and answer them in real time during meetings.
- Wrote a tool to summarize meetings, extract decisions, topics, and action items.
- Collaborated with a startup on their AR/VR system, focusing on scaling the backend services in `Azure`.
- Wrote `TypeScript` CDK Terraform deployment scripts to deploy services to `Azure` `Kubernetes` Service (AKS).
- used `Azure`-managed Redis and `Azure`-managed MySQL for data storage and caching.
- Deployed a total of 7 services and developed a custom client discovery mechanism to expose services and configurations to clients in `Azure`.
- Conducted load testing and createed horizontal pod scaling and vertical scaling to ensure system **performance** and **reliability** in AKS/K8s.
- Configured the Application Gateway with the AGIC (Application Gateway Ingress Controller) component running in AKS to expose services using Layer 7 load balancing.
- used AKS/`Azure` load balancing for Layer 4 load balancing to distribute traffic effectively and enabled UDP based load balancing.
- Worked on Auth0 integration from client to backend services using JWT tokens.
2023:
- used AI and prompt engineering to evaluate legal documents, extract entities, and perform thorough analysis at a fraction of the cost compared to a legal team.
- Created a demo for investors and potential clients to showcase the automated process.
- Developed AI solutions using OpenAI `API` for documentation generation and sensitive document analysis. Created entity extraction and classification tools, createing Chain of Thought reasoning and synthetic prompts. Enhanced search capabilities using HyDE with Text Embeddings and vector sorting. createed vector databases for code base and product documentation analysis. Developed feedback validation tools that improved AI output accuracy from 70% to 90%, reducing three months of function to four hours.
- Served as Acting Senior Director of backend eCommerce site, providing engineering management consulting focused on risk mitigation and staff augmentation.
- Worked with `AWS`, Scala, Java, `JavaScript`, COTS, and platform re-engineering.
- Employed AI and prompt engineering to evaluate legacy systems, write documentation/diagrams, and extract requirements.
- Engaged in recruiting, site **reliability**, disaster recovery, business continuity, and mentoring.
- Developed software for a **security** company site using `AWS`, CI/CD, `React`, Element, `Kubernetes`, Java, and Terraform.
- Wrote integration pieces between a company and the US government.
- used AI and prompt engineering to document code with documentation and diagrams.
- Worked with embedded systems, cloud technologies, and hold a **security** clearance.
## Articles By Rick
1. [Articles Overview](https://rick-hightower.notion.site/articles)
2. [Rick and Chris Review Machine Learning](https://rick-hightower.notion.site/rick-and-chris-review-machine-learning?pvs=25)
3. [Streamlit Adventures Part 5 Article](https://rick-hightower.notion.site/streamlit-adventures-part-5-file-viewer-streamlit-refresh?pvs=25)
4. [Streamlit Part 4: Form Validation Part 2](https://rick-hightower.notion.site/article-streamlit-part-4-form-validation-part-2?pvs=25)
5. [Streamlit Part 3 - Form Validation Part 1](https://rick-hightower.notion.site/article-streamlit-part-3?pvs=25)
6. [Advanced `SQL` Techniques for ETL](https://rick-hightower.notion.site/advanced-sql-techniques-for-etl?pvs=25)
7. [Streamlit Part 2: Layouts, Components, and Graphs](https://rick-hightower.notion.site/streamlit-part-2-layouts-components-and-graphs?pvs=25)
8. [Conversation About Streamlit While Walking in the Park](https://rick-hightower.notion.site/conversation-about-streamlit-while-walking-in-the-park?pvs=25)
9. [PrivateGPT and LlamaIndex](PrivateGPT%20and%20LlamaIndex%20Revolutionizing%20AI%20Proje%20133d6bbdbbea813e9a77eeff437a145a.md)
10. [OpenAI's Latest Developments](OpenAI%E2%80%99s%20Latest%20Developments%20Reasons%20Why%20You%20Shoul%20133d6bbdbbea81c6b889fcf7ecdd9935.md)
11. [AI-Powered Knowledge Base for Product Managers](AI-Powered%20Knowledge%20Base%20for%20Product%20Managers%20133d6bbdbbea81b6a208f09cad8ae1d2.md)
12. [ChatGPT at Scale on `Azure` Cloud](ChatGPT%20at%20scale%20Azure%20Cloud%20Provides%20Access%20to%20Ch%20133d6bbdbbea815cb0c6d5a398133068.md)
13. [Prompt Engineering with CoT and Synthetic Prompts Part 2](Prompt%20Engineering%20Getting%20What%20You%20Want%20From%20Chat%20134d6bbdbbea80b3bc45e245060c81af.md)
14. [Understanding LLMs and Using Chain of Thoughts](Understanding%20LLM%20and%20using%20Chain%20of%20Thoughts%20134d6bbdbbea8043be90d741028424e2.md)
15. [Meta's Llama 2 AI Model](Meta's%20Llama%202%20Threatens%20Dominance%20of%20Other%20AI%20Mod%20134d6bbdbbea80f0ad35e3004c998249.md)
16. [ChatGPT Embeddings and HyDE for Improved Search](Using%20ChatGPT,%20Embeddings,%20and%20HyDE%20to%20Improve%20Sea%20134d6bbdbbea8002b17bfc5c7b81a69a.md)