Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sandraschi/resonite-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/resonite-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sandraschi/resonite-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/resonite-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/resonite-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00762 | $0.00762 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
resonite-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonite MCP — AGENTS.md
FastMCP 3.2+ | Python 3.12+ | Ports: 10978/10979
Overview
Resonite MCP Server provides natural language control of the Resonite social VR platform. It bridges AI agents (Claude Desktop, Cursor, etc.) to Resonite via OSC protocol, ResoniteLink WebSocket, and the Resonite Cloud REST API.
Quick Start
uv sync
uv run python -m resonite_mcp --port 10979
# Frontend at http://localhost:10978 (via web_sota/start.ps1)
Architecture
| Layer | Tech | Port |
|---|---|---|
| React frontend | Vite + React 19 + Tailwind | 10978 |
| FastAPI backend | FastAPI + FastMCP 3.2 | 10979 |
| MCP transport | stdio (default) / HTTP / SSE | — |
| OSC protocol | UDP to Resonite | 9000 |
| ResoniteLink | WebSocket to Resonite | 4242 |
Tool Categories
- OSC (8 tools): send/receive/monitor OSC messages
- Session (4 tools): start/stop worlds and sessions
- Avatar (3 tools): load avatars, set parameters, execute ProtoFlux
- Inventory (7 tools): list/search/spawn/upload/delete/share items
- Plugin (6 tools): load/unload/discover plugins
- REST API (6 tools): Resonite cloud API bridge
- ResoniteLink (4 tools): WebSocket world manipulation
- System (2 tools): help, status
- Integrations (3 tools): WorldLabs/Blender/Unity asset import
- Agentic (1+): plan/execute/reason via ctx.sample()
Total: ~44 tools + 5 prompt templates
Key Environment Variables
| Variable | Default | Purpose |
|---|---|---|
MCP_TRANSPORT |
stdio | Transport mode |
MCP_PORT |
10979 | Backend bind port |
MCP_HOST |
127.0.0.1 | Backend bind host |
RESONITE_OSC_HOST |
127.0.0.1 | Resonite OSC host |
RESONITE_OSC_PORT |
9000 | Resonite OSC port |
RESONITE_TOKEN |
— | Resonite cloud API auth |
Agentic Features (FastMCP 3.2+)
--agenticCLI flag enables CodeMode BM25 skill discoveryagentic_plan_execute()usesctx.sample()for autonomous multi-step reasoning- 5 prompt templates for common workflows: session setup, avatar animation, world exploration, inventory management, cross-MCP integration
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 71 lines · 762 tokens per session scan A 5b75ff37aa72
resonite-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/resonite-mcp (7 stars, last pushed 2d ago), licensed MIT. It adds 762 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
unraid CLAUDE.md
Claude Code instructions for dinglebear-ai/unraid, covering claude.md, what this is, identity and history (read before touching any url), "unraid-mcp" means five different things and agent plugins ship no claude code hooks.
unifi-fabric-mcp-server CLAUDE.md
Instructions for swkstudios/unifi-fabric-mcp-server, covering claude.md — unifi fabric mcp server, what this repo is, pass-through invariant (do not break this), project structure and development setup.
whatsapp-mcp-server CLAUDE.md
Claude Code instructions for HalemoGPA/whatsapp-mcp-server, covering working on this repo, the one idea, rules that follow from it, the box has a hard resource budget - stay inside it and repo-specific traps.
pypi CLAUDE.md
Claude Code instructions for resq-software/pypi, covering resq pypi packages — agent guide, mission, stack, repo map and commands.
microsoft-planner-mcp python.instructions.md
Use when writing or modifying Python source code. Covers module layout, async patterns, imports, and framework conventions for FastMCP + Microsoft Graph SDK.
ohmywind CLAUDE.md
Claude Code instructions for qdonnars/ohmywind, covering ohmywind — working notes, mission, architecture (cible), déploiement & règles de push (à respecter) and cloud-agnostic principle (non-négociable).