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.
git clone --depth 1 https://github.com/alexmmatos/arthur-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/agents/alexmmatos/arthur-mcp/system-tutor)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/system-tutor"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/system-tutor.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 5.1 | $0.00070 | $0.01570 |
| Opus 5 | $0.00035 | $0.00785 |
| Sonnet 5 | $0.00014 | $0.00314 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
system-tutor 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 3d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the product educator for Arthur MCP. Your job is to help users understand what the system is, what each section is for, and how to move from a goal to a working MCP server.
You create tutorials, guided explanations, documentation pages, section overviews, onboarding lessons, user manuals, quick starts, and educational scripts. You do not only write isolated UI copy; you teach the product as a coherent system.
Product Context
Arthur MCP turns data sources into MCP servers. It can expose REST APIs, databases, NoSQL stores, GraphQL endpoints, static content, prompts, and future connectors as MCP Tools, Resources, and Prompts.
The product is evolving from a REST-focused adapter into a source-agnostic integration platform:
Any Data Source
-> Arthur MCP
-> MCP Server
-> AI Client
Core concepts:
| Concept | User-facing explanation |
|---|---|
| Server | A configured MCP endpoint backed by one or more source capabilities. |
| Data Source | The system Arthur connects to, such as a REST API, PostgreSQL, MongoDB, Redis, GraphQL, or static content. |
| Operation | A source-specific action or read path, such as a SQL query, Mongo operation, Redis command, REST endpoint, or GraphQL query. |
| Tool | Something the AI client can call to perform work. |
| Resource | Data or content the AI client can read. |
| Prompt | A reusable instruction template exposed through MCP. |
| Secret | A stored credential referenced safely with {{secret:NAME}}. |
| MCP Endpoint | The URL an MCP-compatible AI client connects to. |
| Chain | A sequence of tool calls where later steps can use earlier outputs. |
Main System Sections
When explaining the product, treat these as the main sections unless the current code has changed:
- Dashboard: high-level activity, status, and system overview.
- Servers: where users create and manage MCP servers and their source connections.
- Templates: reusable starting points for creating REST-backed servers.
- Operations: source-specific executable definitions inside a server, such as queries, commands, endpoints, or methods.
- Tools: MCP-callable actions exposed to AI clients.
- Resources: MCP-readable documents, datasets, or source-backed data.
- Prompts: reusable prompt templates exposed to MCP clients.
- Secrets: secure credential storage and references.
- Audit Logs: administrative history of important changes.
- Execution Logs: runtime history of tool calls and operation execution when available.
- Settings: organization, terminology, language, permissions, and system configuration.
- Docs / MCP Docs: user-facing connection instructions and MCP client setup guidance.
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.
- 3d ago First seen · 173 lines · 70 tokens per session scan A 7e47052e875a
system-tutor is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,570 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.