CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Roslyn CodeLens

marcelroozekrans/roslyn-codelens-mcp
15STDIOregistry active
Summary

This is Roslyn as an MCP server. It exposes the full .NET Compiler Platform APIs to Claude: find implementations, callers, and test coverage; inspect DI registrations and type hierarchies; run diagnostics and apply refactorings; detect dead code, async violations, and disposable misuse. You can switch between loaded solutions at runtime, decompile IL from referenced assemblies, run data flow analysis, and even generate test skeletons for uncovered methods. If you're working with a .NET codebase and need semantic understanding beyond grep, this gives Claude the same view your IDE has. Ships as a NuGet package, runs over stdio, and includes a trust model for analyzer execution.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Roslyn CodeLens MCP Server

NuGet NuGet Downloads Build Status License Docs GitHub Sponsors

A Roslyn-based MCP server that gives AI agents deep semantic understanding of .NET codebases — type hierarchies, call graphs, DI registrations, diagnostics, refactoring, and more.

roslyn-codelens-mcp MCP server

Hosted deployment

A hosted deployment is available on Fronteir AI.

Features

  • find_implementations — Find all classes/structs implementing an interface or extending a class
  • find_callers — Find every call site for a method, property, or constructor
  • find_event_subscribers — Every += / -= site for an event symbol, with resolved handler and subscribe/unsubscribe tag
  • find_tests_for_symbol — List xUnit/NUnit/MSTest methods that exercise a production symbol; opt-in transitive walk through helpers
  • get_test_summary — Per-project inventory of test methods with framework, attribute kind, data-row count, location, and production symbols referenced
  • find_uncovered_symbols — Public methods and properties no test transitively reaches; sorted by cyclomatic complexity for prioritization
  • generate_test_skeleton — Emit a compilable test-class skeleton (as text) for a method or type. Auto-detects xUnit/NUnit/MSTest; surfaces constructor dependencies as TodoNotes; returns a suggested file path. Closes the loop with find_uncovered_symbols
  • get_type_hierarchy — Walk base classes, interfaces, and derived types
  • get_di_registrations — Scan for DI service registrations
  • get_project_dependencies — Get the project reference graph
  • get_symbol_context — One-shot context dump for any type
  • get_public_api_surface — Enumerate every public/protected type and member in production projects; flat, deterministically-sorted list suitable for API review or breaking-change baselines.
  • find_breaking_changes — Diff the current API against a baseline JSON or DLL; report removed members, kind changes, and accessibility changes with Breaking/NonBreaking severity.
  • find_reflection_usage — Detect dynamic/reflection-based usage
  • find_references — Find all references to any symbol (types, methods, properties, fields, events)
  • go_to_definition — Find the source file and line where a symbol is defined
  • get_diagnostics — List compiler errors, warnings, and Roslyn analyzer diagnostics
  • get_code_fixes — Get available code fixes with structured text edits for any diagnostic
  • search_symbols — Fuzzy workspace symbol search by name
  • get_nuget_dependencies — List NuGet package references per project
  • find_attribute_usages — Find types and members decorated with a specific attribute
  • find_obsolete_usage — Every [Obsolete] call site grouped by deprecation message and severity, errors first; for planning migrations
  • find_circular_dependencies — Detect cycles in project or namespace dependency graphs
  • get_complexity_metrics — Cyclomatic complexity analysis per method
  • find_naming_violations — Check .NET naming convention compliance
  • find_async_violations — Sync-over-async, async void misuse, missing awaits, fire-and-forget tasks; per-violation report with severity
  • find_disposable_misuse — IDisposable/IAsyncDisposable instances not wrapped in using/await using/returned/assigned to field; severity error/warning per violation.
  • find_large_classes — Find oversized types by member or line count
  • find_god_objects — Types combining high size with high cross-namespace coupling; sharper signal than raw size for SRP violations
  • find_unused_symbols — Dead code detection via reference analysis. Auto-filters test methods (xUnit/NUnit/MSTest), MCP tool entry points, source-generator output, MEF-composed services, and interop-laid-out fields; filter counts surface in summary.filteredOut
  • get_project_health — Composite audit aggregating 7 quality dimensions per project (complexity, large classes, naming, unused symbols, reflection, async violations, disposable misuse) with counts and top-N hotspots inline
  • get_source_generators — List source generators and their output per project
  • get_generated_code — Inspect generated source code from source generators
  • inspect_external_assembly — Browse types, members, and XML docs from closed-source NuGet packages and referenced assemblies
  • peek_il — Decompile any method to ilasm-style IL bytecode from closed-source or generated assemblies
  • get_code_actions — Discover available refactorings and fixes at any position (extract method, rename, inline variable, and more)
  • apply_code_action — Execute any Roslyn refactoring by title, with preview mode (returns a diff before writing to disk)
  • list_solutions — List all loaded solutions and which one is currently active
  • set_active_solution — Switch the active solution by partial name (all subsequent tools operate on it)
  • load_solution — Load an additional .sln/.slnx at runtime and make it the active solution
  • unload_solution — Unload a loaded solution to free memory
  • rebuild_solution — Force a full reload of the analyzed solution
  • start_background_task — Queue a long-running tool (currently rebuild_solution) to run in the background; returns a taskId to poll
  • get_task_status — Get the current status, result, or error of a background task by its taskId
  • list_running_tasks — List background tasks running or completed within the last 5 minutes
  • trust_solution — Authorize a solution to run Roslyn analyzers (required before get_diagnostics with includeAnalyzers: true)
  • list_trusted_paths — Inspect the persistent trust store + session-trusted solutions
  • revoke_trust — Revoke a previously-granted trust for a solution path
  • analyze_data_flow — Variable read/write/capture analysis within a statement range (declared, read, written, always assigned, captured, flows in/out)
  • analyze_control_flow — Branch/loop reachability analysis within a statement range (start/end reachability, return statements, exit points)
  • analyze_change_impact — Show all files, projects, and call sites affected by changing a symbol — combines find_references and find_callers
  • get_type_overview — Compound tool: type context + hierarchy + file diagnostics in one call
  • analyze_method — Compound tool: method signature + callers + outgoing calls in one call
  • get_overloads — Every overload of a method/constructor (source + metadata) with full parameter and modifier detail in one call
  • get_operators — Every user-defined operator and conversion operator on a type (source + metadata) with kind, signature, parameters, and source location. Includes synthesized record equality and .NET 7+ checked variants
  • get_call_graph — Transitive caller/callee graph for a method, depth-bounded with cycle detection
  • get_file_overview — Compound tool: types defined in a file + file-scoped diagnostics in one call

Response shape

All list-returning tools wrap their results in a uniform envelope:

{
  "items": [ ... ],
  "totalCount": 142,
  "truncated": false,
  "limit": 500,
  "summary": { ... }
}

When truncated is true, the items are the top N by the tool's natural sort order (severity-first, worst-first, by-project, etc.) — usually that's exactly what you want. Raise limit only if the missing tail items matter for the task.

Tools that include a summary aggregate today:

  • get_diagnostics — { error, warning, info, hidden } counts
  • find_references, find_callers, find_attribute_usages — { byProject: { name: count } }
  • search_symbols, find_reflection_usage — { byKind: {...} }
  • find_unused_symbols — { byKind, filteredOut: { testMethod, testContainer, mcpTool, generated, composition, interop } }
  • find_naming_violations — { byRule: {...} }
  • get_complexity_metrics — { max, avg, overThreshold }

Single-object tools (get_type_overview, get_symbol_context, apply_code_action, etc.) return their bespoke shape directly — the envelope only wraps list-returning tools.

Error responses

When a tool can't proceed (symbol not resolved, solution not trusted, file not found, ambiguous match, etc.), the response is an isError: true content block carrying a structured JSON body:

{
  "code": "SolutionNotTrusted",
  "message": "Solution 'Foo.sln' is not trusted for analyzer execution. ...",
  "details": { "solutionPath": "C:\\Foo.sln" }
}

Error codes (switch on code to handle each):

  • SymbolNotFound — type / method / property could not be resolved.
  • SolutionNotTrusted — get_diagnostics or get_code_fixes requested analyzers but the solution hasn't been authorized via trust_solution.
  • AmbiguousMatch — set_active_solution / unload_solution matched multiple solutions; details.matches lists them.
  • FileNotFound — file path or baseline doesn't exist (or isn't in any loaded project).
  • ProjectNotFound — solution name didn't match any loaded solution.
  • InvalidArgument — caller-supplied input was malformed, unsupported, or out of range.
  • Internal — unexpected error not modeled above; message carries the underlying exception text.

Cancellation: the MCP framework's native cancellation is honored. Cancelling a tools/call request mid-flight terminates the operation; long-running tools (get_diagnostics with analyzers, get_code_actions, apply_code_action, get_code_fixes) check the token at hot-loop boundaries.

External Assemblies

Metadata-origin symbols (from NuGet packages and referenced assemblies) are first-class citizens:

  • Tier 1 — Navigation (find_references, find_callers, find_implementations): Accepts closed-source type and member names. Resolves them from assembly metadata and reports all source-level usage sites.
  • Tier 2 — Inspection (inspect_external_assembly): Browse namespaces, types, members, and XML doc comments from any referenced assembly without decompiling.
  • Tier 3 — IL (peek_il): Decompile a specific method to annotated ilasm-style IL using ICSharpCode.Decompiler — useful for understanding the internals of NuGet libraries.

Location-returning results include an Origin field (source or metadata) and an IsGenerated flag to distinguish hand-written code from closed-source or generated output.

Runtime configuration

  • ROSLYN_CODELENS_OPEN_PROJECT_TIMEOUT_SECONDS — per-project MSBuild load timeout (default 300). When a project exceeds this duration during workspace open, it's recorded as a SkippedProjects entry with kind: "Timeout" and the rest of the solution still loads. Useful when a legacy or malformed project wedges the BuildHost-net472 subprocess.

Security: Trust Model

get_diagnostics and get_code_fixes can load Roslyn analyzers — DLLs that execute in-process. To prevent untrusted analyzers from running automatically, this server uses a VS/Rider-style trust model:

  • Solutions passed on the CLI at startup are auto-trusted for the current session.
  • Other solutions must be explicitly trusted via the trust_solution MCP tool.
  • Analyzer DLLs must come from the user's NuGet global packages folder, the dotnet SDK install dir, or the solution's own bin/obj. Other paths are skipped.

Use the list_trusted_paths and revoke_trust tools to inspect and manage trust state. Persistent trust is stored at %APPDATA%\roslyn-codelens\trust.json.

See SECURITY.md for the full threat model.

Quick Start

VS Code / Visual Studio (via dnx)

Add to your MCP settings (.vscode/mcp.json or VS settings):

{
  "servers": {
    "roslyn-codelens": {
      "type": "stdio",
      "command": "dnx",
      "args": ["RoslynCodeLens.Mcp", "--yes"]
    }
  }
}

Claude Code Plugin

claude install gh:MarcelRoozekrans/roslyn-codelens-mcp

.NET Global Tool

dotnet tool install -g RoslynCodeLens.Mcp

Then add to your MCP client config:

{
  "mcpServers": {
    "roslyn-codelens": {
      "command": "roslyn-codelens-mcp",
      "args": [],
      "transport": "stdio"
    }
  }
}

Usage

The server automatically discovers .sln files by walking up from the current directory. You can also pass one or more solution paths directly:

# Single solution
roslyn-codelens-mcp /path/to/MySolution.sln

# Multiple solutions — switch between them with set_active_solution
roslyn-codelens-mcp /path/to/A.sln /path/to/B.sln

When multiple solutions are loaded, use list_solutions to see what's available and set_active_solution("B") to switch context. The first path is active by default.

Performance

All type lookups use pre-built reverse inheritance maps, member indexes, and attribute indexes for O(1) access. Benchmarked on an i9-12900HK with .NET 10.0.7:

ToolLatencyMemory
go_to_definition2.1 µs576 B
find_implementations2.5 µs720 B
get_project_dependencies2.8 µs1.5 KB
get_type_hierarchy3.5 µs1.3 KB
find_circular_dependencies3.7 µs2.7 KB
get_symbol_context4.1 µs1.0 KB
get_source_generators16 µs23 KB
analyze_data_flow19 µs1.6 KB
find_attribute_usages72 µs904 B
get_generated_code78 µs24 KB
analyze_control_flow115 µs14 KB
inspect_external_assembly (summary)159 µs35 KB
find_large_classes265 µs3.5 KB
get_di_registrations478 µs16 KB
inspect_external_assembly (namespace)564 µs259 KB
find_reflection_usage705 µs19 KB
get_complexity_metrics781 µs25 KB
get_code_actions792 µs54 KB
get_file_overview797 µs101 KB
get_diagnostics822 µs99 KB
get_nuget_dependencies849 µs48 KB
get_public_api_surface885 µs247 KB
get_type_overview1.1 ms104 KB
peek_il1.1 ms34 KB
find_disposable_misuse3.5 ms286 KB
find_uncovered_symbols3.8 ms224 KB
search_symbols3.9 ms557 KB
analyze_method5.8 ms333 KB
find_async_violations7.0 ms335 KB
find_tests_for_symbol (direct)8.4 ms396 KB
find_callers10 ms337 KB
find_tests_for_symbol (transitive)12 ms399 KB
find_naming_violations15 ms788 KB
find_unused_symbols23 ms1.0 MB
find_references28 ms1013 KB
analyze_change_impact33 ms1.3 MB
Solution loading (one-time)~4.1 s16 MB

Hot Reload

The server watches .cs, .csproj, .props, and .targets files for changes. When a change is detected, affected projects are lazily re-compiled on the next tool query — only stale projects and their downstream dependents are re-compiled, not the full solution.

Location-returning tools include an IsGenerated flag to distinguish source-generator output from hand-written code.

Requirements

  • .NET 10 SDK
  • A .NET solution with compilable projects

Project compatibility

The server analyses every project that MSBuildWorkspace can load under the .NET SDK runtime.

Supported: SDK-style projects (<Project Sdk="...">), any target framework — net48, net6.0, net8.0, net10.0, etc. .NET Framework targets work fine as long as the csproj uses the SDK-style format.

Skipped (with a warning, not a crash): legacy non-SDK-style projects (<Project ToolsVersion="..." xmlns="http://schemas.microsoft.com/developer/msbuild/2003">, typically .NET Framework projects authored in older versions of Visual Studio). These rely on Microsoft.Common.props imports from the .NET Framework MSBuild that ships with Visual Studio, which is not available in the .NET SDK MSBuild runtime.

When a solution contains legacy projects, the server:

  1. Loads every SDK-style project normally — all tools work for those.
  2. Skips each legacy project and records it in LoadedSolution.SkippedProjects.
  3. Surfaces the skipped list via list_solutions (the SkippedProjects array on each SolutionInfo) and in the return message of load_solution. Each entry includes the project name, kind (Legacy), and reason.

To analyse a legacy project, convert it to SDK-style format (see Microsoft's migration guide) or open the solution from a Visual Studio Developer Command Prompt so the full Visual Studio MSBuild is on PATH.

Development

dotnet build
dotnet test
dotnet run --project benchmarks/RoslynCodeLens.Benchmarks -c Release

Third-party licenses

  • ICSharpCode.Decompiler — MIT license (v8+). Used for IL disassembly in the peek_il tool.

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Registryactive
PackageRoslynCodeLens.Mcp
TransportSTDIO
UpdatedMay 26, 2026
View on GitHub