What is mcp-server-stress?

A maintainer-only shortcut for running an MCP server surface test, an audit of the tools and interfaces exposed to an AI agent.

Use it in the specified Roslyn-Backed-MCP repository to run the surface test and optionally create finding fragments.

It keeps the audit process consistent and can turn findings into backlog files for later work.

How darylmcd/Roslyn-Backed-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to darylmcd/Roslyn-Backed-MCP. 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/darylmcd/Roslyn-Backed-MCP/main/.claude/skills/mcp-server-stress/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCP

Made for: Claude Code.

Or install roslyn-mcp, the plugin that ships this one along with the rest of its 44 skills, 5 agents, 2 hooks, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress/github.svg)](https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress)

Your own site

<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-stress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 320 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,521 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.

Model	Per session	Once invoked
Fable 5.1	$0.00320	$0.01521
Opus 5	$0.00160	$0.00760
Sonnet 5	$0.00064	$0.00304
Haiku 4.5	$0.00032	$0.00152

Measured 11d ago against content hash 64e0eaf6b37a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-server-stress 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/archive-old-reports.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/mcp-server-stress/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mcp-server-stress $ARGUMENTS

Maintainer-only repo-local alias for /mcp-server-surface-test --output-mode=fragments. Routes to the canonical audit prompt at ${CLAUDE_PLUGIN_ROOT}/skills/mcp-server-surface-test/prompts/full.md with fragments-mode emission so findings produce <audited-repo-root>/backlog.d/<finding-id>.md files for the /backlog-intake pipeline.

What this skill does

Invoke /mcp-server-surface-test --output-mode=fragments against the current Claude Code session's repo root (the only path the Roslyn MCP server's sanctioned-root restriction permits — see Limitations below). Forward any additional flags (--no-worktree, --single-agent, --quick) verbatim.

Why this skill exists (and why it's a thin alias)

Before v1.X.Y, /mcp-server-stress used a separate maintainer-overlay.md prompt that duplicated ~85% of full.md while adding three repo-coupled phases (backlog.d/ fragment emission, ai_docs/audit-reports/ report path, ai_docs/backlog.md regression cross-check). Every prompt fix had to be applied to both files, and they drifted in subtle ways.

The v1.X.Y refactor folded the maintainer-overlay's unique content into full.md behind:

--output-mode=fragments → Phase 19 emits backlog.d/ fragments (the maintainer-overlay's Phase 19 behavior).
Auto-detection of ai_docs/audit-reports/ vs audit-reports/ → reports land in the maintainer's doc-audit schema location when that schema exists, top-level otherwise.
Auto-detection of ai_docs/backlog.md vs backlog.md for regression source → Phase 18's "prior source" probe handles both.

/mcp-server-stress survives as a 1-line alias because:

Muscle memory. The maintainer types /mcp-server-stress reflexively; renaming to /mcp-server-surface-test --output-mode=fragments everywhere is friction.
Repo-local discoverability. This skill is only available from Claude Code sessions rooted in Roslyn-Backed-MCP (per .claude/skills/ discovery). The repo-local placement signals that fragments-mode is the maintainer-standard invocation.

Read the full file on GitHub · 55 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/archive-old-reports.ps1 5.3 KB runs code

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.

11d ago First seen · 55 lines · 320 tokens per session scan A 64e0eaf6b37a

Subscribe to this mod's changes

mcp-server-stress is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 320 tokens to every session and 1,521 once invoked, about $0.0016 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

Roslyn-Backed-MCP: Skill for Claude Code