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.
/plugin marketplace add andypgray/resharper-cli-mcpnpx agentmods add plugins/andypgray/resharper-cli-mcp/resharper-cli-mcpgit clone --depth 1 https://github.com/andypgray/resharper-cli-mcpGrade A, and why
resharper-cli-mcp 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.
What it actually says
{
"name": "resharper-cli-mcp",
"description": "JetBrains ReSharper command-line inspection and cleanup for C#, over MCP. Unofficial — not affiliated with or endorsed by JetBrains.",
"version": "1.6.0",
"author": { "name": "Andrew Gray" },
"homepage": "https://github.com/andypgray/resharper-cli-mcp",
"repository": "https://github.com/andypgray/resharper-cli-mcp",
"license": "MIT",
"keywords": ["resharper", "inspectcode", "cleanupcode", "csharp", "dotnet", "code-quality", "static-analysis", "mcp"],
"mcpServers": {
"resharper": {
"command": "dotnet",
"args": ["dnx", "[email protected]", "--source", "https://api.nuget.org/v3/index.json"],
"env": {
"JB_CACHE_HOME": "${CLAUDE_PLUGIN_DATA}/jb-cache"
}
}
}
}
What ships with it
1 file beside plugin.json 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.
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.
- yesterday First seen · 20 lines scan A 5e688b0ac933
resharper-cli-mcp is a plugin published in the GitHub repository andypgray/resharper-cli-mcp (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
roslyn-mcp
Roslyn-powered C# refactoring MCP server — 50 tools for code navigation, analysis, generation, and refactoring across entire .NET solutions.
xaf-logic-explainer
Query a specific DevExpress XAF application: its entities, controllers, actions, business rules and Model Editor customizations, extracted from source with Roslyn.
dotnet-toolkit
Compiler-aware C# code intelligence for .NET repos — Roslyn-backed symbol search, reference tracing, and edits validated against the compiler before they touch disk.
koshi
Koshi MCP — retrieval, context engineering, persistent memory, and quality scoring for AI agents. 100% offline.
roz-mcp
Roslyn-powered semantic C# navigation, impact analysis, and verified editing for coding agents: the compiler's view of a .NET solution, over MCP.
rhino-dev-skills
Complete Rhino/Grasshopper plugin development capabilities — RhinoCommon geometry API, Grasshopper GHComponent & DataTree, Eto.Forms cross-platform UI, RhinoDoc object management, project setup and Yak packaging.