mcp-stdio-parity-testing

A testing pattern for checking a Python MCP server that communicates over standard input and output. It also covers testing an LLM client, including TDD-style negative cases, where TDD means testing expected behavior before or alongside implementation.

In plain words
What is it for?
Use it to test server initialization, successful and failed tool calls, `/proc` system reads, fake-model tool workflows, and command-line behavior when credentials are absent.
Why use it?
It catches broken startup, tool-discovery, invalid-tool, system-read, and missing-credential behavior before review or release.

Skill for Claude CodeCodex

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 skills/alonf/mcppythondemo/mcp-stdio-parity-testing
Any agent
npx skills add alonf/MCPPythonDemo --skill mcp-stdio-parity-testing
Clone the repo
git clone --depth 1 https://github.com/alonf/MCPPythonDemo

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 286 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 $0.00000 $0.00286
Opus 5 $0.00000 $0.00143
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00029

Measured yesterday against content hash 18a36d6855fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-stdio-parity-testing 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 yesterday.

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.

.squad/skills/mcp-stdio-parity-testing/SKILL.md · 39 lines

What it actually says

MCP STDIO Parity Testing Skill

When to use

Use this pattern when a repo needs reviewer-grade validation for:

  • a Python MCP stdio server
  • a lecture/demo parity path against another reference implementation
  • a client-side LLM workflow that should fail cleanly when credentials are missing

Pattern

  1. Validate the server with the official SDK client

    • start the server with StdioServerParameters
    • run initialize
    • assert tool discovery
    • call the target tool on happy path
    • call an invalid tool and confirm an error payload, not a crash
  2. Add negative-path unit coverage around live system reads

    • patch /proc readers
    • require zero/fallback payloads instead of exceptions
  3. Split client validation into two lanes

    • fake-model/unit lane for deterministic tool-calling orchestration
    • real CLI lane with credentials stripped so missing-config messaging is tested exactly as users see it
  4. Make smoke output human-readable

    • print the live server payload
    • print the validated client failure message
    • keep transport details out of the final QA summary

Files in this repo that follow the pattern

  • tests/test_m1_smoke.py
  • tests/test_system_info.py
  • tests/test_client.py
  • scripts/smoke_test.py
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. yesterday First seen · 39 lines · 0 tokens per session scan A 18a36d6855fb

Subscribe to this mod's changes

mcp-stdio-parity-testing is a skill published in the GitHub repository alonf/MCPPythonDemo (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 286 tokens. 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 skills, from other repositories