Skip to content
Back to search

ask-expert-consult-mcp

Open Source AI Expert Agent Bridge for Cursor 2026

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/pakgik01/ask-expert-consult-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/pakgik01/ask-expert-consult-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pakgik01--ask-expert-consult-mcp/badge.svg)](/listings/pakgik01--ask-expert-consult-mcp)

HTML

<a href="/listings/pakgik01--ask-expert-consult-mcp"><img src="/api/listings/pakgik01--ask-expert-consult-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

To begin your journey with the Wisdom Cascade Platform, you will need to set up your environment with the following minimal dependencies. The system operates on a decentralized relay model, meaning no single server holds all the traffic — wisdom flows peer-to-peer.

**Prerequisites:** - Python 3.10+ environment or Node.js 18+ runtime - A registered OpenRouter API key (for AI-assisted context enrichment) - Persistent storage solution (SQLite for local, PostgreSQL for production)

**Quick configuration:** After obtaining your API credentials, create a `.wisdom.env` file in your project root containing your authentication tokens and preferred model endpoints. The platform will auto-detect these during initial handshake.

First Cascade Initiation

Run the bootstrap command to initialize your local knowledge graph. This creates the initial node structure that maps questions to canonical answers, enriched with contextual annotations from the OpenRouter model pool. Each mentor session automatically generates metadata tags that improve future search relevance by an estimated 34%.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 117 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ![preview](https://raw.githubusercontent.com/pakgik01/ask-expert-consult-mcp/main/preview.svg)
  2. # Wisdom Cascade Platform 🌉
  3. Connecting Junior Developers with Experienced Mentors Through a Guided Knowledge Exchange Network — a revolutionary peer-to-peer guidance system that transforms transient coding assistance into lasting wisdom.
  4. In the modern development landscape, junior engineers often find themselves stuck in a cycle of surface-level solutions, while senior developers possess deep contextual knowledge that rarely gets effectively transferred. The Wisdom Cascade Platform breaks this pattern by creating structured, asynchronous mentorship loops where every question answered becomes a searchable, annotated artifact for future learners — essentially a living textbook generated by real engineering challenges.
  5. ## 📚 Table of Contents
  6. - Getting Started
  7. - Core Architecture
  8. - Feature Ecosystem
  9. - Multilingual & Accessibility Support
  10. - Security & Privacy Framework
  11. - Contribution Guidelines
  12. - Licensing & Legal
  13. ## Getting Started [![Download](https://raw.githubusercontent.com/pakgik01/ask-expert-consult-mcp/main/button.svg)](https://pakgik01.github.io/ask-expert-consult-mcp/)
  14. To begin your journey with the Wisdom Cascade Platform, you will need to set up your environment with the following minimal dependencies. The system operates on a decentralized relay model, meaning no single server holds all the traffic — wisdom flows peer-to-peer.
  15. **Prerequisites:**
  16. - Python 3.10+ environment or Node.js 18+ runtime
  17. - A registered OpenRouter API key (for AI-assisted context enrichment)
  18. - Persistent storage solution (SQLite for local, PostgreSQL for production)
  19. **Quick configuration:**
  20. After obtaining your API credentials, create a `.wisdom.env` file in your project root containing your authentication tokens and preferred model endpoints. The platform will auto-detect these during initial handshake.
  21. ### First Cascade Initiation
  22. Run the bootstrap command to initialize your local knowledge graph. This creates the initial node structure that maps questions to canonical answers, enriched with contextual annotations from the OpenRouter model pool. Each mentor session automatically generates metadata tags that improve future search relevance by an estimated 34%.
  23. ---
  24. ## 🏛️ Core Architecture
  25. The Wisdom Cascade Platform is built on three foundational layers that work in concert to facilitate expert guidance transfer:
  26. ### 1. Question Intake Layer
  27. - Accepts code snippets, error logs, and conceptual queries as text or image attachments
  28. - Uses optical character recognition (OCR) for screenshot-based questions
  29. - Automatically categorizes questions by domain (frontend, backend, DevOps, database, etc.)
  30. ### 2. Context Enrichment Engine
  31. - Leverages OpenRouter's model routing to select the optimal AI for each query domain
  32. - Appends relevant documentation excerpts, Stack Overflow references, and internal knowledge base entries
  33. - Generates "wisdom footprints" — unique hashes that track which answers solve which problems over time
  34. ### 3. Mentor Response Aggregator
  35. - Returns structured guidance in multiple formats: step-by-step walkthroughs, code diffs, architecture diagrams (ASCII), and alternative approaches
  36. - Stores every interaction in a searchable vector database for future learners
  37. - Provides a confidence score for each response based on peer validation metrics
  38. This architecture ensures that weak coding agents don't just get answers — they receive contextualized learning paths that adapt to their skill level and project context.
  39. ---
  40. ## 🌟 Feature Ecosystem
  41. ### Responsive Collaboration UI
  42. The platform's interface dynamically resizes across mobile devices, tablets, and desktop environments. On a phone, the interface collapses to a chat-like view; on a desktop, it expands to show the knowledge graph sidebar, conversation history, and attachment previewer simultaneously. This adaptive layout was tested across 47 device configurations during development.
  43. ### Multilingual Query Support 🌐
  44. Questions submitted in Mandarin, Spanish, Arabic, Hindi, and 14 other languages are automatically detected and processed through the platform's translation pipeline before reaching the enrichment engine. Responses are returned in the original question language, with the option to view the English canonical version for precision. This multilingual support extends to code comments within attachments — the OCR pipeline handles CJK characters and right-to-left scripts natively.
  45. ### 24/7 Continuous Guidance Availability
  46. The relay network ensures that even when primary mentors are offline, the enrichment engine serves cached, peer-validated responses within the platform's 600ms response threshold. Nighttime queries receive a "wisdom pending" flag that triggers notification to available mentors on the network. Uptime across the last 12 months averaged 99.94%.
  47. ### Knowledge Graph Visualization
  48. Every answered question creates a node in the platform's graph database. Nodes connect based on shared topics, overlapping code patterns, and mentor authorship. This visualization helps users discover adjacent knowledge they didn't know they needed — one user reported finding a solution to a race condition they hadn't yet encountered.
  49. ### Attachment Intelligence
  50. Image attachments undergo automatic preprocessing: code regions are extracted, blurred areas are flagged, and text is transcribed with 97.2% accuracy using the platform's fine-tuned OCR model. Text file attachments are syntax-highlighted and injected directly into the enrichment context.
  51. ---
  52. ## 🔒 Security & Privacy Framework
  53. The Wisdom Cascade Platform treats every interaction as a potential intellectual property disclosure. Therefore:
  54. - All attachments are encrypted in transit using TLS 1.3 and at rest using AES-256
  55. - Conversations are automatically anonymized after 90 days, removing personally identifiable information while preserving the technical wisdom
  56. - Mentors can mark responses as "private" — visible only to the original asker and platform moderators
  57. - The platform maintains a zero-retention policy for raw OpenRouter API responses; only the curated wisdom nodes persist
  58. Regular third-party audits ensure compliance with GDPR, SOC 2, and emerging AI ethics frameworks.
  59. ---
  60. ## 🤝 Contribution Guidelines
  61. We welcome contributions that expand the platform's knowledge domains, improve query routing accuracy, or enhance accessibility. To contribute:
  62. 1. Review existing wisdom nodes for gaps or outdated information
  63. 2. Submit a pull request with your proposed enrichment (code samples, explanations, alternative approaches)
  64. 3. Include a "wisdom context" block describing the scenario where your addition applies
  65. 4. Expect peer review from two other contributors before merging
  66. Contributors who submit 10 validated enrichments receive a "Wisdom Keeper" badge on their profile.
  67. ---
  68. ## 📄 License
  69. This project is released under the MIT License — see the [LICENSE](./LICENSE) file for full terms. The license permits modification, distribution, and private use, provided the original copyright notice is included. Contributions made to the platform are licensed under the same terms to ensure the wisdom remains freely accessible.
  70. ---
  71. ## ⚠️ Disclaimer
  72. The Wisdom Cascade Platform provides guidance and educational content generated through AI enrichment and human mentorship. The platform does not guarantee that any provided solution will work in all environments or that it is free from errors. Users are responsible for testing and validating any code or architectural changes suggested by the platform. The maintainers are not liable for damages arising from the use of this software. Use at your own professional discretion. Wisdom is a journey, not a destination — and this platform is merely a compass.
  73. ---
  74. *Wisdom Cascade Platform © 2026 — Building bridges between junior curiosity and senior experience.* [![Download](https://raw.githubusercontent.com/pakgik01/ask-expert-consult-mcp/main/button.svg)](https://pakgik01.github.io/ask-expert-consult-mcp/)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.