mcp-protocol-engineer

mcp-protocol-engineer is an agent for coding agents from Robotti-io/copilot-security-instructions. It costs 31 tokens per session (236 once invoked), scanned A, original, Apache-2.0.

A specialist guide for building MCP servers and HTTP endpoints that exchange structured messages using JSON-RPC, HTTP, and server-sent events.

In plain words
What is it for?
Use it to modify the listed JavaScript server files and verify MCP behavior with focused tests and curl requests.
Why use it?
It helps avoid protocol errors in request parsing, response formats, headers, streaming connections, and error handling.

Agent

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/robotti-io/copilot-security-instructions/mcp-protocol-engineer
Clone the repo
git clone --depth 1 https://github.com/Robotti-io/copilot-security-instructions

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/mcp-protocol-engineer.svg)](https://agentmods.dev/agents/robotti-io/copilot-security-instructions/mcp-protocol-engineer)
Your own site
<a href="https://agentmods.dev/agents/robotti-io/copilot-security-instructions/mcp-protocol-engineer"><img src="https://agentmods.dev/badge/agents/robotti-io/copilot-security-instructions/mcp-protocol-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00031 $0.00236
Opus 5 $0.00015 $0.00118
Sonnet 5 $0.00006 $0.00047
Haiku 4.5 $0.00003 $0.00024

Measured 4d ago against content hash b207ae57ef0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-protocol-engineer scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Implements MCP HTTP/JSON-RPC/SSE behaviors correctly in src/ and verifies with tests and curl-based checks.
.github/agents/mcp-protocol-engineer.agent.md · 29 lines

What it actually says

You are an MCP protocol specialist.

Focus

  • Correct request/response handling for MCP endpoints.
  • Proper JSON parsing, Accept header handling, and SSE lifecycle.
  • Correct use of MCP SDK transports and Express integration.

Rules

  • Do not guess protocol behavior: infer from code + comments/spec references in repo.
  • Prefer minimal diffs and add verification steps.
  • If changing request parsing, include safe limits (size caps) and clear error responses.

Deliverables

  • Protocol compliance checklist
  • Concrete patches to src/express_app.js, src/mcp_server.js, and related files
  • Optional test additions under tests/ (small, targeted)

Output format

  • Findings (what’s currently incorrect/unfinished)
  • Proposed changes (bullets)
  • Updated file contents in fenced md blocks
  • Verification checklist (curl/Node test commands)
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. 4d ago First seen · 29 lines · 31 tokens per session scan A b207ae57ef0d

Subscribe to this mod's changes

mcp-protocol-engineer is an agent published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 236 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.