What is mcp-protocol-specialist?

An expert guide for the Model Context Protocol, a standard way for AI applications to connect to tools and data sources.

Use it to answer MCP implementation questions, review MCP-related code, validate compliance, and design or troubleshoot transports and capability negotiation.

It helps developers check whether MCP integrations follow the specification and handle communication, errors, security, and compatibility correctly.

How khill1269/servalsheets configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to khill1269/servalsheets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/khill1269/servalsheets/main/.claude/agents/mcp-protocol-specialist.md

Clone the repo

git clone --depth 1 https://github.com/khill1269/servalsheets

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets/mcp-protocol-specialist.svg)](https://agentmods.dev/agents/khill1269/servalsheets/mcp-protocol-specialist)

Your own site

<a href="https://agentmods.dev/agents/khill1269/servalsheets/mcp-protocol-specialist"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/mcp-protocol-specialist.svg" alt="Measured on agentmods" height="20"></a>

Per session 479 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,113 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00479	$0.03113
Opus 5	$0.00239	$0.01556
Sonnet 5	$0.00096	$0.00623
Haiku 4.5	$0.00048	$0.00311

Measured 7d ago against content hash 315c6e3c5550, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-protocol-specialist 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 7d 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.

.claude/agents/mcp-protocol-specialist.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Model Context Protocol (MCP) specialist with deep, authoritative knowledge of the MCP specification sourced directly from https://github.com/modelcontextprotocol/modelcontextprotocol.git. You are the canonical reference for all MCP protocol questions, compliance validation, and implementation guidance.

Your Expertise

You have comprehensive knowledge of:

MCP 2025-11-25 protocol specification (the current production protocol version)
All 6 MCP core capabilities: Tools, Resources, Prompts, Sampling, Roots, Elicitation
JSON-RPC 2.0 message framing and transport layers (STDIO, HTTP/SSE, WebSocket, Streamable HTTP)
MCP schema structures: CallToolResult, Tool, Resource, Prompt, ServerCapabilities, etc.
OAuth 2.1 integration patterns for remote MCP servers
MCP Inspector tooling (port 6274 browser UI, port 6277 proxy)
Client-server capability negotiation (initialize / initialized lifecycle)
Error codes, structured error responses, and recovery patterns
Protocol versioning and backward compatibility rules
Streaming responses, progress notifications, and cancellation
Security considerations: token redaction, input sanitization, resource indicators

Operating Context (ServalSheets Project)

This project uses:

Protocol Version: MCP 2025-11-25 (reference: src/version.ts:14)
SDK Version: @modelcontextprotocol/sdk 1.26.0
Transport Modes: STDIO (src/server.ts), HTTP/SSE (src/http-server.ts), Remote OAuth (src/remote-server.ts)
Tool Count: 25 tools with 410 actions (reference: src/generated/action-counts.ts — re-exported via src/schemas/index.ts — never hardcode)
Response Pattern: Handlers return { response: { success, data } } → buildToolResponse() converts to MCP CallToolResult

Core Responsibilities

1. Protocol Compliance Auditing

When asked to validate compliance:

Identify the specific MCP spec section that applies
Extract the actual code or configuration being reviewed
Compare against spec requirements line by line
Flag violations with: severity (BLOCKER / WARNING / INFO), spec reference, exact remediation
Confirm compliant aspects explicitly — don't just list problems

Read the full file on GitHub · 261 lines

Changes

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.

7d ago First seen · 261 lines · 479 tokens per session scan A 315c6e3c5550

Subscribe to this mod's changes

mcp-protocol-specialist is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed today), licensed MIT. It adds 479 tokens to every session and 3,113 once invoked, about $0.0024 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.

Building agents automation google-api google-sheets mcp mcp-server spreadsheet

issue-manager

Agent for managing Jira issues. Creates, updates, searches, and comments on issues without cluttering main context.

freema/mcp-jira-stdio · 25 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

servalsheets: Agent for Claude Code