servalsheets-v2: Agent for Claude Code

.claude/agents/mcp-protocol-expert.md

mcp-protocol-expert is an agent for Claude Code from khill1269/servalsheets-v2. It costs 59 tokens per session (1,864 once invoked), scanned A, a copy of mcp-protocol-expert, MIT.

An expert guide for checking whether ServalSheets follows MCP, the Model Context Protocol used to connect AI clients with tools and servers.

In plain words
What is it for?
Use it when adding or changing tools, reviewing STDIO, HTTP/SSE, WebSocket, or OAuth servers, checking tool registration, and debugging protocol issues.
Why use it?
It helps catch invalid tool schemas, transport problems, incompatible SDK usage, and incorrect errors before they cause integration failures.

Agent for Claude Code

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

This is khill1269/servalsheets-v2's own configuration. It tells Claude Code how to work on servalsheets-v2 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything servalsheets-v2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khill1269/servalsheets-v2. 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-v2/main/.claude/agents/mcp-protocol-expert.md
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets-v2

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-v2/mcp-protocol-expert.svg)](https://agentmods.dev/agents/khill1269/servalsheets-v2/mcp-protocol-expert)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets-v2/mcp-protocol-expert"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets-v2/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 1,864 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 94% copy Near-identical to another mod 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 $0.01864
Opus 5 $0.00030 $0.00932
Sonnet 5 $0.00012 $0.00373
Haiku 4.5 $0.00006 $0.00186

Measured 7d ago against content hash a997661cb1c4, 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-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 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.

Origin

This is a copy

94% identical to mcp-protocol-expert — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/mcp-protocol-expert.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 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
  • 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

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 · 313 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. 7d ago First seen · 313 lines · 59 tokens per session scan A a997661cb1c4

Subscribe to this mod's changes

mcp-protocol-expert is an agent published in the GitHub repository khill1269/servalsheets-v2 (0 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,864 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to mcp-protocol-expert, differing in 23 lines, and is treated as a copy.