roz-mcp

roz is an MCP server that gives C# coding agents the compiler's view of a solution. It finds every real reference to a symbol, including the edges text search misses: overrides, interface dispatch, DI registrations. It renames a symbol across the whole solution in one call, previews the blast radius of a proposed change, and makes edits that verify themselves against the compiler in the same round trip. roz runs as a .NET global tool over stdio; one roz-mcp setup command configures Claude Code, Cursor, VS Code Copilot Chat, or Codex CLI.

roz was developed for and dogfooded on large legacy financial codebases, and it is for that sort of work that it shines. It is most probably not worth the (inherent to the MCP protocol) token overhead for clean greenfield work; When it helps (and when it doesn't) has the measurements.

Quickstart

roz requires the .NET 10 SDK.

dotnet tool install -g Zphil.Roz
cd path/to/your/solution
roz-mcp setup

Restart the AI client, then ask it something that needs the compiler:

"Find all implementations of IRepository in this solution and show me each class's Save method."

setup auto-detects which AI clients the project uses (via the .claude/, .cursor/, .vscode/, and .codex/ marker directories), writes the matching MCP config file(s), and appends a short usage snippet to the corresponding project rules file. If several markers are present, choose explicitly with --client=claude,cursor. Setup is idempotent: re-running it updates roz's entries without disturbing sibling MCP servers or user-added environment variables, and it refreshes the # roz-mcp rules section in place without touching the rest of the file.

VS Code and Cursor users can also add the server in one click, once the tool is installed:

The badges wire the server into the client config only. roz-mcp setup is the fuller path: it also writes the project rules snippet and, for Claude Code, the permission defaults that route write tools through a confirmation prompt.

Two defaults are worth knowing before your first session:

• Solution discovery walks up from the working directory; pin a specific .sln/.slnx with ROZ_SOLUTION_PATH in the MCP config's env block.

• Tool surface: the default set is 12 of the 19 tools; most write tools are opt-in. Seed a different surface at onboarding with roz-mcp setup --tools=all (everything) or --tools=read (read-only), and see Configuration for finer control.

From source

git clone https://github.com/andypgray/roz-mcp
cd roz-mcp
dotnet pack src/Zphil.Roz/Zphil.Roz.csproj -c Release
dotnet tool install -g --add-source src/Zphil.Roz/bin/Release Zphil.Roz

roz installs as roz-mcp on your PATH.

Related MCP server: sharplens-mcp

Install as a Claude Code plugin

Claude Code users can skip the global tool install: this repository doubles as a single-plugin marketplace, and one install delivers the server with its tools, prompts, and guide resources, plus a skill carrying the usage rules that roz-mcp setup would otherwise write into CLAUDE.md:

/plugin marketplace add andypgray/roz-mcp
/plugin install roz-mcp@roz-mcp

The plugin starts the server with dotnet dnx, which fetches Zphil.Roz from nuget.org on first use. You still need the .NET 10 SDK. The plugin's launch command is global, so per-project settings go in a .roz.json file (see Configuration); the bundled skill includes a recommended permission block that keeps the write tools behind a confirmation prompt (SKILL.md).

Enable the plugin per project rather than globally: roz is measured overhead on work that never needs the compiler's view (see When it helps). A team can check the marketplace and plugin enablement into the project's .claude/settings.json, which prompts teammates to install on their next session:

{
  "extraKnownMarketplaces": {
    "roz-mcp": { "source": { "source": "github", "repo": "andypgray/roz-mcp" } }
  },
  "enabledPlugins": { "roz-mcp@roz-mcp": true }
}

The server should be registered once per project. With the plugin enabled, roz-mcp setup detects it and configures around it: permission rules under the plugin's tool-name prefix, --tools written to .roz.json, no .mcp.json entry, and a warning if a leftover classic entry would register the server twice. --plugin and --no-plugin force either mode.

Tools

roz ships 19 tools across 7 categories. Read tools are forgiving: a cursor near a declaration snaps to the nearest enclosing symbol, and the worst case is information about the wrong symbol. Write tools are conservative: symbol names are authoritative, and an ambiguous target fails with a disambiguation error.

Read tools accept includeDocs=true and (where applicable) includeBody=true; locations are either cursors (path:line:col, or path:line for member-on-line snap) or symbol names (with optional FQN, containingType, kind, or project substring filter).

The default set is 12 tools. The write tools (edit_symbol, replace_content, apply_code_fix, change_signature, add_usings, remove_unused_usings) and get_unused_references are opt-in via ROZ_TOOLS (see Configuration).

The five editing tools accept a verify mode that collapses the edit → build → re-read loop into one round trip: verify=DryRun applies the batch to an in-memory fork and reports the new-and-resolved compiler-error delta without writing anything, and verify=Delta commits first, then reports. Verified writes exist because an agent's own success report is not evidence: silently asserting completion while the state says otherwise is a pattern reported across the agent literature (Advani 2026, agentic benchmarks rather than code audits specifically).

Batched read tools (find_references, analyze_change_impact, find_implementations, find_overloads, get_type_hierarchy) accept many items per call; one round trip with symbolNames=["A","B","C"] is almost always cheaper than three separate calls.

Prompts

roz registers 10 user-invoked slash commands (/mcp__roz__<name> in a direct Claude Code install; plugin installs prefix the name differently). Each packages a multi-step Roslyn workflow into one recipe.

Resources

roz exposes three reference guides as MCP resources, so the detail loads on demand rather than in every session. Claude Code can @-mention a resource to attach it, and recent builds let the model list and read resources itself.

When it helps (and when it doesn't)

roz was A/B-measured against no-MCP baselines across four model tiers before 1.0; the write-ups are linked from each paragraph below and indexed in Evidence and methodology.

Mechanical refactors are the clearest win, at every tier measured. A 22-reference solution-wide rename via rename_symbol cost −57.5% versus a careful text-editing baseline (Haiku 4.5, 2026-07-03; the tool adopted in 3 of 3 reps, zero churn, zero residual) and −60.9% at the earlier frontier anchor (Opus 4.7, 2026-04). Both arms landed the identical semantic change. Write-up.

roz preserves live code that text search would delete. A deletion task planted five traps reachable only through Razor markup, DI, dispatch, startup, or the public API, alongside three genuinely dead symbols. The roz arm preserved all five traps at every tier tested (Opus 4.8 / Sonnet 5 / Haiku 4.5, 2026-07); only the no-MCP baseline deleted live code (Sonnet 5, the Razor-only and public-API traps, 1 of 3 reps). The counterweight: the roz arm over-corrected once at Sonnet and removed nothing that rep. The cleanup_dead_code and tighten_accessibility prompts drive this workflow with the blind-spot checks built in. Write-up.

Audit reports cite real numbers and finish faster, but they cost more. roz-armed audits scored count plausibility 0.97–1.00 versus 0.62–0.77 for a grep baseline whose cited caller counts drift or are fabricated. They ran −24.2% to −57.3% in wall-clock (Sonnet 5 / Haiku 4.5, 2026-07). They also cost +19.7% to +47.6% more on every current tier: MCP tool results are billed as input tokens (tool-use pricing), while a locally-run grep never enters the context window. At the budget tier the speed came with shallower coverage. Buy this for trustworthy-and-fast, not for cheap. Write-up.

Greenfield, pattern-following feature work does not pay. At the frontier it cost +17% and 2.1× the wall-clock for comparable code (Opus 4.7, 2026-04-18). Down-tier, neither Sonnet 5 nor Haiku 4.5 called a single roz tool on the task, so their +5.2% / +23.6% deltas were pure snippet and tool-schema overhead. Don't load roz for this. Write-up.

Pick the tool surface for the work (ROZ_TOOLS):

Tier matters too (Opus 4.8 / Sonnet 5 / Haiku 4.5, 2026-07). A frontier model trusts grep for navigation and mostly ignores routing guidance, so the read side saves nothing; the value sits in the write path and the prompts. The mid tier is strong enough to act boldly and not always right; the one baseline deletion of live code above happened at this tier. The budget tier gets the best price per outcome on renames, and its fast audits run shallow.

Configuration

All configuration is via environment variables, typically set in the MCP client's config env block.

The same variables can live in a .roz.json file at the project root, keyed by the exact variable names ({"ROZ_TOOLS": "read"}). At startup roz uses the nearest file up the directory tree and applies any key the environment leaves unset; an environment variable always wins. The file keeps per-project settings working when the launch command is configured globally and carries no per-project env block.

roz-mcp setup --tools=<value> seeds ROZ_TOOLS into the generated MCP config's env block so subsequent sessions pick it up automatically.

The table lists the most common variables; the full reference for every variable roz reads, including the .roz.json rules, is the roz://guides/configuration resource (see Resources).

Works well with

roz is a C# specialist and pairs with, rather than replaces, adjacent tools:

• Serena: when your work spans multiple languages or a polyglot repo, a cross-language LSP server covers ground a Roslyn-only tool cannot.

• ilspycmd: reads the body of a compiled BCL/NuGet symbol; the decompile_symbol prompt drives it.

• ReSharper CLI / dotnet format: whole-file style and formatting passes, which roz leaves alone.

Evidence and methodology

Every quantitative claim on this page resolves to a primary-source evaluation in docs/evidence/: the A/B studies that drove ship/hold decisions and the stress tests that shaped the design, published verbatim as dated historical records.

The harness that produced the A/B numbers is public: scripts/ab-test/. Run it on your own codebase before you trust ours.

Stress tests

roz was stress-tested against seven open-source C# codebases before 1.0.0, and each surfaced a distinct bug class that was then fixed. The reports keep roz's former name (roslyn-mcp) and period-correct tool counts, and some clones were deliberately broken to stress error handling.

Contributing

Contributions are welcome. Bug reports reproduced on public codebases, new conservative executors, client-compatibility fixes, and evaluation or harness improvements land best. See CONTRIBUTING.md for dev setup (.NET 10 SDK, Windows or Linux) and the test architecture. Default-preset changes want an A/B run, and HOLD verdicts are normal here (two of our own tools have them). The deep dive on internals (error-handling conventions, location/FQN resolution, DI-container detection, verified writes, and precision limits) is in ARCHITECTURE.md. To report a security issue privately, see SECURITY.md. roz collects nothing and processes everything locally; PRIVACY.md states that as policy.

License

MIT; see LICENSE.