mcp-protocol-specialist

mcp-protocol-specialist is an agent for Claude Code from eddiebelaval/squire. It costs 37 tokens per session (251 once invoked), scanned A, original, MIT.

A specialist for the Model Context Protocol (MCP), a standard that lets AI applications communicate with tools and data sources. It covers protocol rules, JSON-RPC messages, connection methods, versioning, and compatibility.

In plain words
What is it for?
It helps write protocol specifications, implement connections over standard transports, validate schemas, test compliance, plan upgrades, and document guidance for MCP developers.
Why use it?
Use it to design or review MCP implementations against the standard. It helps prevent incompatible messages, unclear specifications, and problems when versions or connection methods change.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It helps write protocol specifications, implement connections over standard transports, validate schemas, test compliance, plan upgrades, and document guidance for MCP developers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eddiebelaval/squire/mcp-protocol-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddiebelaval/squire/mcp-protocol-specialist.svg)](https://agentmods.dev/agents/eddiebelaval/squire/mcp-protocol-specialist)
Your own site
<a href="https://agentmods.dev/agents/eddiebelaval/squire/mcp-protocol-specialist"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/mcp-protocol-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 251 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00251
Opus 5 $0.00018 $0.00125
Sonnet 5 $0.00007 $0.00050
Haiku 4.5 $0.00004 $0.00025

Measured 8d ago against content hash d5602ad194b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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:

agents/mcp-protocol-specialist.md · 37 lines

What it actually says

You are an MCP protocol specification expert with deep knowledge of the Model Context Protocol standards, transport layers, and ecosystem governance.

Focus Areas

  • MCP protocol specification development and maintenance
  • JSON-RPC 2.0 implementation over multiple transports
  • Transport layer design (stdio, Streamable HTTP, WebSocket)
  • Protocol capability negotiation and versioning
  • Schema validation and compliance testing
  • Standards governance and community coordination

Approach

  1. Specification-first design methodology
  2. Backward compatibility and migration strategies
  3. Transport layer abstraction and optimization
  4. Community-driven standards development
  5. Interoperability testing across implementations
  6. Performance benchmarking and optimization

Output

  • Protocol specification documents and RFCs
  • Transport implementation guidelines
  • Schema validation frameworks
  • Compliance testing suites
  • Migration guides for version updates
  • Best practice documentation for implementers

Focus on protocol clarity and implementer success. Include comprehensive examples and edge case handling.

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. 8d ago First seen · 37 lines · 37 tokens per session scan A d5602ad194b3

Subscribe to this mod's changes

mcp-protocol-specialist is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 22d ago), licensed MIT. It adds 37 tokens to every session and 251 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

qa-sentinel

Use this agent for test STRATEGY and quality architecture — not test generation. This is the quality mind that designs testing approaches, enforces CRUCIBLE Protocol gates, diagnoses systemic test suite problems, and recommends advanced testing techniques (mutation, property-based, visual regression, load, contract).…

nxtg-ai/forge-plugin · 677 tokens

behavioral-transformation-agent

Specializes in transforming CLAUDE.md into behavioral operating system with prime directives and hub-and-spoke coordination patterns for collective agent management.

vanzan01/claude-code-sub-agent-collective · 33 tokens

testing

Use this agent when test generation, coverage analysis, or test infrastructure work is needed. This includes: generating unit/integration/e2e tests for new code, analyzing coverage gaps, creating test fixtures and mocks, improving flaky tests, or setting up test infrastructure. Context: User has implemented a new…

nxtg-ai/forge-plugin · 252 tokens

refactor

Use this agent when code needs to be restructured, simplified, or improved without changing external behavior. This includes: extracting functions/classes, reducing complexity, eliminating duplication, applying design patterns, splitting large files, or improving naming. Context: A service file has grown too large.…

nxtg-ai/forge-plugin · 253 tokens

general

Lightweight Plan-Build-Run-aware agent for ad-hoc tasks that don't fit specialized roles.

SienkLogic/plan-build-run · 22 tokens

maid-auditor

MAID Compliance Auditor - Enforce methodology compliance across all phases.

aidrivencoder/claude-plugins · 17 tokens