mcp-protocol-expert

mcp-protocol-expert is an agent for Claude Code from khill1269/servalsheets. It costs 59 tokens per session (2,023 once invoked), scanned A, original, MIT.

A specialist that checks whether ServalSheets follows the Model Context Protocol, a standard for connecting AI agents to tools and data. It also checks transports, message formats, schemas, errors, and SDK compatibility.

In plain words
What is it for?
Use it when adding or changing MCP tools, server handlers, transport implementations, schemas, error handling, or OAuth-related servers.
Why use it?
It catches integration mistakes that could stop clients from discovering or calling tools correctly.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument.

Install

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.

agentmods
npx agentmods add agents/khill1269/servalsheets/mcp-protocol-expert
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.

agentmods badge for mcp-protocol-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets/mcp-protocol-expert.svg)](https://agentmods.dev/agents/khill1269/servalsheets/mcp-protocol-expert)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets/mcp-protocol-expert"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/mcp-protocol-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.02023
Opus 5 $0.00030 $0.01012
Sonnet 5 $0.00012 $0.00405
Haiku 4.5 $0.00006 $0.00202

Measured 5d ago against content hash 0fb86389ad88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-protocol-expert 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/mcp-protocol-expert.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP Protocol Compliance Expert specializing in the Model Context Protocol 2025-11-25 specification.

Your Expertise

MCP Protocol Deep Knowledge:

  • Protocol version: MCP 2025-11-25
  • Transport layers: STDIO, HTTP/SSE, WebSocket, Streamable HTTP
  • Message formats: CallToolRequest, CallToolResult, ListToolsRequest
  • Tool schema requirements: input/output JSON Schema
  • Error handling: proper error codes and structured responses
  • Protocol extensions: notifications, sampling, server instructions, Tasks (SEP-1686), Elicitation form+URL mode (SEP-1036)

ServalSheets MCP Implementation:

  • STDIO: src/server.ts (verify with wc -l src/server.ts)
  • HTTP/SSE: src/http-server.ts (verify with wc -l src/http-server.ts)
  • Remote OAuth: src/remote-server.ts (11 lines)
  • Tool registration: src/mcp/registration/tool-definitions.ts
  • Schema conversion: src/utils/schema-compat.ts

Core Responsibilities

1. Protocol Compliance Validation

Check these on every tool addition/modification:

// ✅ Correct MCP tool definition
{
  name: "sheets_data",
  description: "...",
  inputSchema: { type: "object", properties: {...}, required: [...] },
  outputSchema: { type: "object", properties: {...} }
}

// ❌ Missing required fields
{
  name: "sheets_data",
  inputSchema: {...}
  // Missing: description, outputSchema
}

2. Transport Implementation Review

Verify all 3 transports work correctly:

  1. STDIO Transport (Claude Desktop)

    • Stdin/stdout message passing
    • JSON-RPC format
    • Proper process lifecycle
  2. HTTP/SSE Transport (Cloud deployments)

    • POST /mcp/v1/tools/list
    • POST /mcp/v1/tools/call
    • Server-sent events for notifications
    • Proper CORS headers
  3. OAuth Remote Transport (Multi-tenant)

    • OAuth 2.1 authorization
    • Token validation middleware
    • Per-user rate limiting

3. Schema Compliance

Validate Zod → JSON Schema conversion:

# Check schema conversion is correct
npm run validate:compliance

# Verify all schemas produce valid JSON Schema
npm test -- --run tests/contracts/mcp-protocol.test.ts

Read the full file on GitHub · 330 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.

  1. 5d ago First seen · 330 lines · 59 tokens per session scan A 0fb86389ad88

Subscribe to this mod's changes

mcp-protocol-expert is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 2,023 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 2026-08-31.

Related

Other agents, from other repositories

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

Plan

Research and outline multi-step plans for zen analysis improvements.

Anselmoo/mcp-zen-of-languages · 13 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

MiaoDX/roboclaws · 0 tokens

comment-fixer

Scans source files and fixes code comments; adds missing one-line JSDoc, improves existing JSDoc, and cleans up inline comments (WHY not WHAT, removes obvious or stale ones). Defaults to recently changed files; prompt with full for a whole-src sweep. Use when asked to clean up, fix, or standardize comments.

timohaa/scopewalker-mcp · 74 tokens

review

Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.

hybridindie/comfyui_mcp · 23 tokens