QVAC-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@QVAC-MCP Check these design notes for cloud or API key violations."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
QVAC-MCP — shared MCP for Decentralized AI Hackathon (TryDojo / ISD Summit 2026)
Shared Model Context Protocol server used across all 4 track projects + main repo. Stack: Python + FastMCP + UV. Inference rule: QVAC on-device / P2P only, never cloud.
Proposed toolset (shared across projects)
# | Tool | Why (hackathon use) |
1 |
| Crawl/research live QVAC docs ( |
2 |
| Returns minimal working snippet + model hint for a task: text-generation, embeddings, rag, transcription, translation, tts, ocr, vision, image-generation, classification, fine-tuning. Avoids hallucinated APIs. |
3 |
| Static check: flags |
4 |
| Returns parsed brief for |
5 |
| Returns a 48h plan template weighted by jury criteria (Technical 35 / Innovation 25 / Impact 20 / Design 10 / Completion 10) + deliverables checklist (repo + 5-min ES video). |
6 |
| Self-critique prompt enforcing jury weights + disqualification rules before coding. |
Skills exposed as resources: skill://planner, skill://builder, skill://reviewer — same behaviour in all repos.
Related MCP server: RAG MCP Server
Run
uv sync
uv run python main.py # stdio (for agents)
uv run python main.py --http # Streamable HTTP on :8000Available Tools
9 toolshackathon_planHackathon PlanA
How it works: input track+idea → returns a concrete 48h task breakdown + checklist. It does NOT code; it forces the plan to cover jury weights so nothing scores 0. Example: hackathon_plan('track1','Teams bot extracting MR/CT observations') → day-by-day tasks mapped to Technical/Innovation/Impact/Design/Completion + video script slot.
Inputs: idea (required), track (required).
hackathon_rulesHackathon RulesA
Bases/rules of the whole hackathon (TyC+Reglas digest). Call when AI needs event rules.
Inputs: no named parameters.
judge_feedbackJudge FeedbackA
How it works: paste design/code summary → returns a scoring rubric the agent must self-fill 0-10 per criterion with one concrete fix each, plus compliance verdict. Run BEFORE coding and BEFORE delivery.
Inputs: design_notes (required).
qvac_compliance_checkQvac Compliance CheckB
DQ guardrail: scans design/code notes for cloud-inference patterns.
Inputs: design_notes (required).
qvac_fetchQvac FetchB
Fetch one allowlisted QVAC page as plain text. Use URLs from qvac_index.
Inputs: url (required), max_chars.
qvac_indexQvac IndexA
Curated map of WHAT QVAC does + WHERE to read. Call first, then qvac_fetch(url).
Inputs: no named parameters.
qvac_searchQvac SearchB
Keyword filter over the QVAC index (e.g. 'rag', 'transcription', 'fine-tune', 'models').
Inputs: keyword (required).
track_briefTrack BriefC
ONE-PARAGRAPH summary only. For full spec call track_detail(which).
Inputs: which.
track_detailTrack DetailC
ENTIRE track brief, verbatim full file. Track 1 = ~9k chars transcribed docx.
Inputs: which.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool has a clearly distinct role: qvac_index/fetch/search form a browse-retrieve-filter flow, track_brief/track_detail are explicitly tiered summaries, and the remaining tools (rules, compliance, planning, feedback) target separate workflow stages. Even the two discovery-ish tools (qvac_index and qvac_search) are differentiated by map vs. keyword filter.
All names use snake_case and are readable, but they follow multiple conventions: qvac_* for one group, track_* for another, hackathon_* for another, and a lone judge_feedback. There is no uniform verb_noun pattern, though the prefix grouping helps orient an agent.
Nine tools is well within the ideal 3-15 range and each tool earns its place. The count covers knowledge retrieval, track details, hackathon rules, compliance checking, planning, and self-assessment without redundancy or bloat.
The surface is complete for its apparent purpose: an agent can discover QVAC resources, fetch content, search, get track summaries/details, access rules, verify compliance, generate a plan, and run a final judging self-evaluation. There are no dead ends, and the tool chain supports a full hackathon workflow.
Maintenance
Related MCP Connectors
Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Shared project docs, task planning and GitHub evidence for people and their AI agents.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.71MIT
- FlicenseNot gradedqualityDmaintenanceProvides tools for ingesting documents into a local vector database and retrieving relevant information via semantic search, enabling retrieval-augmented generation for MCP clients.8-
- AlicenseAqualityDmaintenanceProvides tools for managing tasks, searching docs, and running a heuristic quality gate to check agent output for common issues before human review.6MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI clients to browse, read, update, and search a document store through tools, resources, and prompts, including summarizing and comparing documents via URI-addressable resources and reusable prompt templates.-