Skip to main content
Glama

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

qvac_docs_fetch(url)

Crawl/research live QVAC docs (docs.qvac.tether.io, qvac.tether.io). Every project needs correct on-device API usage for Technical 35%.

2

qvac_capability_guide(task)

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

qvac_compliance_check(design_notes)

Static check: flags openai/chat/completions, cloud URLs, API keys in inference path. DISQUALIFICATION guard (Art. 10). Pass = on-device/P2P only.

4

track_brief(which) / track_detail(which)

Returns parsed brief for track1, track2 (Psy models on edge), general (main challenge, alias main) + rules digest so every agent plans with right context.

5

hackathon_plan(track, idea)

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

judge_feedback(design_notes)

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 :8000

Available Tools

9 tools
hackathon_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.

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

    B3.4/5.0

    Scored across 9 tools

    Disambiguation5/5

    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.

    Naming Consistency3/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers