mcp-server-surface-test

mcp-server-surface-test is a skill for Claude Code from darylmcd/Roslyn-Backed-MCP. It costs 233 tokens per session (5,327 once invoked), scanned A, original, MIT.

A testing procedure for checking the live tools of a Roslyn MCP server against a C# code repository. Roslyn is Microsoft's technology for analyzing C# code, and MCP is a standard way for AI tools to call outside services.

In plain words
What is it for?
It is for running a quick read-only check or a longer audit with apply-and-review tests and an experimental-feature scorecard.
Why use it?
It helps reveal whether the server's available tools work as expected, including how they handle changes in a disposable copy of the code.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the roslyn-mcp plugin — 44 skills, 5 agents, 2 hooks, 2 MCP servers shipped together

Good fit It is for running a quick read-only check or a longer audit with apply-and-review tests and an experimental-feature scorecard.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add darylmcd/Roslyn-Backed-MCP
Claude Code
/plugin install roslyn-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.

agentmods badge for mcp-server-surface-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test/github.svg)](https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test)
Your own site
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test/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.

agentmods 80×15 button for mcp-server-surface-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/mcp-server-surface-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 233 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,327 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 $0.00233 $0.05327
Opus 5 $0.00117 $0.02663
Sonnet 5 $0.00047 $0.01065
Haiku 4.5 $0.00023 $0.00533

Measured 10d ago against content hash 5fa5f5ef2f36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-server-surface-test 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (lib/render-finding.ps1, 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.

skills/mcp-server-surface-test/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mcp-server-surface-test $ARGUMENTS

Run a Roslyn MCP server audit against a loaded C# repo. The skill bundles two prompt files — prompts/quick.md for the bounded read-only tier and prompts/full.md for the comprehensive run — and routes between them based on $ARGUMENTS.

Step 1 — Hard precondition: Roslyn MCP server must be callable

This skill is a null-op without the Roslyn MCP server. The audit's entire purpose is to exercise the server's live surface — without it, the run produces no audit-grade evidence.

Tool prefix — resolve it once from server_info, then pin it. Your MCP client prepends a prefix derived from the registration path it loaded the server under, so the same tool surfaces as mcp__roslyn__server_info on a dev-build/self-hosted entry, as mcp__plugin_roslyn-mcp_roslyn__server_info on the marketplace-plugin install, and under a different prefix again for any other registration key (a custom .mcp.json key, a forked plugin name). Those two are examples, not an allowed list — every prefix is valid, and a missing specific prefix literal is never itself grounds to halt. Resolve the prefix once, at the first gate, then pin it. (1) Scan your current tool surface for every tool whose name ends in server_info. server_info is a common MCP tool name, so there may be more than one candidate and some may belong to other servers entirely. (2) Identify the Roslyn one by its response shape, never by its prefix: a Roslyn server_info response carries connection.state, catalogVersion, and surface.*. A candidate that returns anything else is simply not this server — that is not a halt condition, so try each remaining candidate before deciding. (3) Pin the winning candidate's prefix and resolve every later bare tool name in this skill — including its phase sub-files (workspace_load, find_references, get_symbol_outline, …) — under that one pinned prefix only. Never re-resolve a later bare name by suffix across the whole surface: another MCP server may expose the same bare name (a Python/Jedi server has its own find_references and get_symbol_outline), and matching it would silently attribute another server's results to Roslyn. Every gate in this skill — including its phase sub-files — halts only when no tool ending in server_info returns a Roslyn-shaped response.

Read the full file on GitHub · 178 lines

Files

What ships with it

8 files 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.

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. 10d ago First seen · 178 lines · 233 tokens per session scan A 5fa5f5ef2f36

Subscribe to this mod's changes

mcp-server-surface-test is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed yesterday), licensed MIT. It adds 233 tokens to every session and 5,327 once invoked, about $0.0012 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.

Related

Other skills, from other repositories

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

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens