Skip to main content
Glama
Sign In
Roslyn Workbench MCP

Roslyn Workbench MCP

by lantean-code
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Related Servers

Alternatives to Roslyn Workbench MCP

Related Servers

  • LSP-MCP

    morrow-addref
    F
    license
    A
    quality
    D
    maintenance
    Minimal MCP server bridging a Roslyn C# language server to AI agents, exposing tools for diagnostics, call hierarchy, and type hierarchy.
    1
    -

  • re-dotnet

    Heretek-RE
    A
    license
    A
    quality
    C
    maintenance
    MCP server for .NET assembly analysis. Vendor-neutral wrapper around AsmResolver and ILSpy for parsing and decompiling .NET assemblies.
    11
    1
    MIT

  • sharplens-mcp

    pzalutski-pixel
    A
    license
    A
    quality
    B
    maintenance
    A Model Context Protocol (MCP) server providing 62 AI-optimized tools for .NET/C# semantic code analysis, navigation, refactoring, and code generation using Microsoft Roslyn. Built for AI coding agents - provides compiler-accurate code understanding that AI cannot infer from reading source files alone.
    62
    41
    MIT

  • CSharpAnalyserMcp

    undy-mosq
    A
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP server that gives AI assistants Roslyn-powered browsing of any C# solution, letting them list types by folder or namespace, read XML documentation, and retrieve method signatures, locations and bodies. This keeps queries targeted so agents pull only the exact slice of source they need instead of reading whole files into context.
    1
    MIT
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4/5.0

Scored across 56 tools

Disambiguation4/5

The tool set is generally well-differentiated, with descriptions explicitly pointing to related alternatives for symbol navigation, diagnostics, control/data flow, and transactions. However, with 56 tools, several clusters still require careful reading to avoid misselection, such as get-change-impact vs get-symbol-dependents vs get-dependency-graph, and analyze-control-flow vs get-control-flow-graph.

Naming Consistency4/5

Names are consistently kebab-case and mostly follow a predictable verb-noun pattern such as find-references, get-diagnostics, and stage-code-action. The main deviation is the noun-action convention used for workspace-* and transaction-* families, which is still readable and internally consistent but prevents a perfect score.

Tool Count1/5

At 56 tools, the surface is far beyond a practical selection scope for an MCP server, even for a broad Roslyn workbench. Many niche analysis and relationship tools could likely be collapsed or grouped to reduce tool-selection burden without losing core capability.

Completeness4/5

Coverage is broad and coherent across workspace lifecycle, symbol discovery and navigation, diagnostics, code actions, Fix All preparation, transactional mutation, and error reporting. A notable gap is that transaction-review is referenced for approval-required mode but is not present in the tool list, leaving that workflow incomplete.

Maintenance

ActivityActive
ResponsivenessSyncing

Resources