Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Offline analyzers that find and fix intent-hiding, slow or noisy C#, including agent-written code.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"csharp-refactor": {
"command": "dnx",
"args": [
"csharp-refactor",
"--yes",
"--mcp"
]
}
}
}Run this in your terminal
claude mcp add csharp-refactor -- dnx csharp-refactor --yes --mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"csharp-refactor": {
"command": "dnx",
"args": [
"csharp-refactor",
"--yes",
"--mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"csharp-refactor": {
"type": "stdio",
"command": "dnx",
"args": [
"csharp-refactor",
"--yes",
"--mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account Thorium, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.20) reached the registry 23 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need .NET on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, LickityClick
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
The C# little-sister of FSharp.Refactor
Functional refactoring suggestions for C#, implemented in F# on Roslyn. The rules care about correctness, measured performance and clear idiomatic C# — and deliberately not about naming, layout or conventions.
Suggestions are Info severity: they mark an opportunity, not a defect, and never gate your build.
The tool is fully offline: AI has been used to make it, but it doesn't use AI.
Nothing to configure — the tool reads your project, reports what it would change, and only edits when you tell it to:
dotnet tool install --global csharp-refactor
csharp-refactor Your.csproj --dry-run --api-changes
That prints every fix it would make, with file and position, and writes nothing. When the list looks right, drop the flag to apply them:
csharp-refactor Your.csproj --api-changes
If you don't want change public methods / API, drop --api-changes:
csharp-refactor Your.fsproj
It refuses a compilation that does not already build, recompiles in memory after every pass, and builds the project for real at the end, putting the fixes back if that fails.
Using the tool:
Point it at whatever you have — the kind is read off the path:
Your.csproj | one project |
Thing.cs | one source file — its project is found and analysed, but only that file is edited |
Your.sln, Your.slnx | every C# project the solution lists |
src/ | the solution in that directory, or the projects beneath it |
"src/**/*.csproj" | everything the glob matches |
build.csx | one C# script — its own compilation (#r, #load, the NuGet cache), no MSBuild at all; a directory picks its loose scripts up too |
C:\git | a workspace of checkouts: each analysed on its own into one report |
The analyzers ship as CSharp.Refactor.Analyzers, an ordinary Roslyn analyzer package. Reference it from the project you want analysed and every host — dotnet build, Visual Studio, VS Code's C# extension, Rider — loads it by itself:
<PackageReference Include="CSharp.Refactor.Analyzers" Version="*" PrivateAssets="all" />
The package is a development dependency: it only produces hints and quick fixes, and nothing from it reaches your compiled output or your bin.
Install the CSharp.Refactor extension: every C# project opened in the IDE gets the suggestions and Ctrl+. fixes, with no project change and no effect on builds. Its Tools > CSharp.Refactor menu runs the csharp-refactor tool on the open solution (apply or dry run, with or without --api-changes), writes the SARIF report, opens the notes page and the .editorconfig block — the VS Code extension's commands, in Visual Studio. Or use the package reference above; both work, and a project with both sees each finding once.
Install the CSharp.Refactor extension. It bundles the analyzers and, with your consent, wires them into every C# project on the machine through MSBuild's user ImportBefore hook (one props file under your profile, undone by a command). Or use the package reference.
The analyzers run inside the compiler, so a build can write the findings as SARIF with no extra tool:
dotnet build -p:ErrorLog=findings.sarif
The tool's own report carries more — fixes as suggested changes, context snippets, stable fingerprints — and pairs with --dry-run for a lint gate:
- run: dotnet tool install --global csharp-refactor
A dry run exits 0 whether or not it found anything; --fail-on-findings makes it exit 3 when a finding survives the filters, and --baseline turns that into a ratchet: findings already in an earlier report are neither reported nor fixed, only new ones surface.
csharp-refactor Your.csproj [--dry-run] [--codes CR0090,CR0103] [--categories correctness,performance] [--api-changes]
| Flag | |||
|---|---|---|---|
--dry-run | Report only: lists every fix it would make, writes nothing. | ||
--codes CR0090,CR0103 | Restrict the run to chosen rules; the other rules do not run at all. Naming a rule is an ask: it outranks the rule's default-off status and a config none. | ||
--categories | Restrict to kinds of rule: correctness, performance, idiom, cosmetic. The rules of the other kinds do not run. For a repository you do not maintain, correctness,performance is the set worth a pull request. | ||
--define | Preprocessor symbols the run defines, like csc -define: or a DefineConstants entry: repeatable, or ;/,-separated (--define:A and -d:A work too). Added to each project's own DefineConstants — DEBUG, TRACE and the project's constants stay. See Code under #if. | ||
--api-changes | Also apply fixes that change internal or public signatures and shapes, rewriting call sites across the solution (the reference oracle finds them in every project; a caller in a VB project holds the fix, an F# consumer holds the surface). Held back and counted without it. | ||
--report | Write every finding: .sarif, .html (a self-contained page) or .csv. | ||
--baseline | The ratchet: findings whose fingerprints appear in this earlier report are neither reported nor fixed. | ||
--fail-on-findings | Exit 3 when any finding survives the filters. Exit contract: 0 clean, 1 failure, 2 usage, 3 findings. | ||
| `--notes [on\ | off\ | only]` | List fix-less advisory notes inline; only is the review pass, nothing written. By default a run prints its fixes and one per-category note count; reports and JSON always carry the notes. |
--format json | Machine-readable stdout; progress prose moves to stderr. | ||
--rules | Print the rule catalog. | ||
--create-config | Append a commented block of every rule and key at its default to the directory's .editorconfig. | ||
--mcp | Serve analyze and list_rules as an MCP server over stdio, one warm workspace across calls. | ||
--parse-only | No references: syntax-only rules. Not a substitute for a real run. | ||
--max-passes | Fix-then-reanalyse iterations (default 5). A pass after the first re-analyses only the files the previous pass edited or held a fix in. |
Projects are loaded through MSBuildWorkspace — SDK-style projects of any target, net48 included, in every framework flavour they list. A legacy project ( with explicit items) is read from its project file when the .NET Framework build host does not answer: compile items, defines, HintPath references that exist, the targeting pack's assemblies and project references. Without the build tree (a reference a custom .targets adds, a sibling bin) some types stay unresolved; the run says how many, the typed rules stand down where a type is unknown, the in-memory check holds the error count, and the final build runs through Visual Studio's MSBuild.exe where a baseline build succeeds — otherwise the run is verified in memory only, and says so. An executable another project of the solution references (its tests) is not a leaf: its public shape stays unless --api-changes says otherwise, and every dependent of a changed project is built too. A C# script (.csx) is a compilation of its own: the file parsed as a script, the running runtime as its references, #r resolved against the script's directory, the runtime and the NuGet cache (#r "nuget: Name, Version"), #load read by the compiler for context (a loaded file is edited when it is swept as a target of its own, and a directory sweeps every loose script). Nothing builds a script, so the run is verified in memory: the error count may not grow, and a script host's globals (Args) count as errors on both sides.
#if LOCAL_BUILDCode behind a preprocessor symbol nothing defines is not in the parse tree at all: the tool neither analyses it nor sees what a fix elsewhere does to it, and the verification build compiles without it too. A repository that keeps, say, a local-development path under #if LOCAL_BUILD names the symbol for the run:
csharp-refactor Your.sln --define LOCAL_BUILD # or --define:LOCAL_BUILD, -d:LOCAL_BUILD
csharp-refactor Your.sln --define "LOCAL_BUILD;CI" # several at once
or once for every run, in .editorconfig (csharp_refactor.defines = LOCAL_BUILD, below). The run uses both, and says at the start which symbols are active and where each came from. The symbols are added to what each project defines, exactly as dotnet build would see them with DefineConstants set in the environment: the SDK's DEBUG/TRACE, the target framework's NET8_0_OR_GREATER and the project's own $(DefineConstants);FOO all stay. (-p:DefineConstants=LOCAL_BUILD would not do: a global property replaces every one of them.) Every MSBuild the run starts — the workspace's design-time build, restores, the verification builds — gets them that way, and the loaded C# projects, legacy projects and .csx scripts get them in their parse options as well, so a project that assigns DefineConstants outright is still analysed with them. A script whose #r cannot be resolved while another #r sits under #if LOCAL_BUILD gets the hint to pass --define LOCAL_BUILD.
Rules are configured the way every Roslyn analyzer is, in .editorconfig, nearest section winning:
[*.cs]
dotnet_diagnostic.CR0103.severity = none # off dotnet_diagnostic.CR0006.severity = suggestion # a default-off rule, on csharp_refactor.CR0006.then_at_least = 30 # a rule's knob
csharp_refactor.public_api = false # nothing links to this assembly csharp_refactor.api_changes = true # --api-changes as a standing decision csharp_refactor.suppressions = no-correctness # all | no-correctness | none csharp_refactor.skip_microsoft_duplicates = true # the Microsoft analyzers run here: skip what they already report csharp_refactor.ignore_paths = generated;external/imported csharp_refactor.defines = LOCAL_BUILD # like --define on every run
csharp_refactor.defines is a run-level key: it is read once per run, from the .editorconfig nearest the target (the walk stops at root = true), and adds to --define, never replacing it.
csharp-refactor --create-config writes the block for you, every value at this build's default, so it changes nothing until you edit a line. Each rule's knobs follow its severity line, at their defaults; a knob whose default is not one value (CR0023's measured floor, a rule's wrap_column, which falls back to the file's max_line_length) is written commented out.
A generated f
Only the beginning is shown; read the rest in the repo