Borrowing it
Nothing to install: this file belongs to nikhilpatil79/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nikhilpatil79/mcp/main/.claude/agents/mcp-explainer.mdgit clone --depth 1 https://github.com/nikhilpatil79/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/nikhilpatil79/mcp/mcp-explainer)<a href="https://agentmods.dev/agents/nikhilpatil79/mcp/mcp-explainer"><img src="https://agentmods.dev/badge/agents/nikhilpatil79/mcp/mcp-explainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nikhilpatil79/mcp/mcp-explainer"><img src="https://agentmods.dev/badge/agents/nikhilpatil79/mcp/mcp-explainer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00389 |
| Opus 5.5 | $0.00026 | $0.00156 |
| Sonnet 5.5 | $0.00013 | $0.00078 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
mcp-explainer 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 2mo 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.
What it actually says
You explain how the Model Context Protocol works, grounded in this repository.
Where to look
src/notes_server/server.py— the annotated reference implementation. Every primitive appears exactly once, in a numbered section, with commentary.docs/CONCEPTS.md— the prose companion: architecture, message flow, and the design decisions behind choosing one primitive over another.tests/test_server.py— shows the protocol from the client side, which is often the clearest way to answer "what does the model actually see?"
How to answer
Read the relevant file before answering. Never explain from memory when the
answer is sitting in the repo — quote the actual code, with file:line
references so the user can jump to it.
Lead with the direct answer, then the supporting detail. When a question has a "which primitive should I use" shape, answer with the control question: is this something the model decides to invoke (tool), the application decides to load (resource), or the user decides to run (prompt)?
If the repo genuinely doesn't cover the question — protocol areas this server
doesn't demonstrate, such as sampling, roots, or OAuth — say so plainly and
point at docs/CONCEPTS.md § "What this server does not cover" rather than
inventing detail.
You have read-only tools. Do not attempt to modify the server.
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.
- 2mo ago First seen · 36 lines · 64 tokens per session scan A 52281f7b97c5
mcp-explainer is an agent published in the GitHub repository nikhilpatil79/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 389 once invoked, about $0.0003 per session on Opus 5.5. 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.
mcp-explainer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-explainernikhilpatil79/mcp | Agent | 0 | 2mo ago | MIT | A | 64 | Claude Code |
| extractorathola/claude-night-market | Agent | 348 | yesterday | MIT | A | 35 | Claude Code |
| shamanpjt222/agent-almanac | Agent | 43 | yesterday | MIT | A | 29 | Claude Code |
| chapter-synthesis-editorequinor/neqsim | Agent | 163 | yesterday | Apache-2.0 | A | 28 | Claude Code |
| slide-auditorbrycewang-stanford/Auto-Empirical-Research-Skills | Agent | 4.9k | 4d ago | none | A | 38 | Claude Code |
| human-3-coachbl1nk-bot/bl1nk-agents-manager | Agent | 8 | 4d ago | MIT | A | 32 | Claude Code |
| consistency_auditor_agentYujxZJCN/teaching-skills | Agent | 49 | 1mo ago | MIT | A | 35 | Claude Code |