mcpField
D
dotnet-coverage-mcp

dotnet-coverage-mcp

Local
github.comDeveloper Tools2Updated 8w ago

About dotnet-coverage-mcp

dotnet-coverage-mcp gives AI assistants MCP tools to run .NET tests and inspect coverage. It supports branch-level analysis, coverage diffs, session-isolated artifacts, and appending test code.

Key features

  1. 01Discover C# source files and batch them
  2. 02Run filtered tests with coverage collection
  3. 03Summarize class and method coverage
  4. 04Find uncovered branches and compare runs
  5. 05Append test code with atomic writes
  6. 06Isolate coverage artifacts by session

Use cases

  1. 01Find low-coverage methods in a .NET project
  2. 02Identify uncovered branches before adding tests
  3. 03Compare coverage before and after code changes
  4. 04Run concurrent coverage workflows on separate projects

MCP support

The server communicates with MCP clients over stdio and exposes tools for source discovery, test execution, coverage analysis, and test-code insertion. It invokes `dotnet test` and `reportgenerator`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
nugetdotnet-coverage-mcp0.1.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

dotnet-coverage-mcp

build tests NuGet License: MIT

An MCP (Model Context Protocol) server that gives AI assistants — Claude Code, Gemini CLI, and others — direct access to .NET test-coverage tooling. Run dotnet test, parse Cobertura XML, identify uncovered branches, diff coverage between runs, and append test code — all over stdio.

Purpose

This server lets an AI assistant run unit tests, collect coverage data, and analyse results — all without leaving the chat. Instead of manually running dotnet test and parsing reports, the AI can call the server's tools directly to:

  • Discover source files and build smart batches by line budget
  • Run a filtered set of tests and collect coverage
  • Read compact, AI-optimised coverage summaries (method-level line/branch rates)
  • Check per-file coverage against a configurable target rate (default 80%)
  • Identify uncovered branches as structured JSON
  • Diff coverage between runs to see only what changed
  • Append new test code to an existing test file with atomic writes

How It Works

The server starts as a console process and communicates over stdio using the MCP protocol. An MCP-compatible client (Claude Code, Gemini CLI, etc.) launches the process and calls its tools as if they were functions.

AI Client  <--stdio/MCP-->  dotnet-coverage-mcp  <--shell-->  dotnet test + reportgenerator

Available Tools

ToolDescription
GetSourceFilesDiscover .cs files from a file, folder, or .csproj project. Returns file metadata (lines, method count) and smart batches grouped by lineBudget.
RunTestsWithCoverageRun dotnet test with XPlat Code Coverage, generate a JSON summary via reportgenerator. Returns paths to Summary.json and coverage.cobertura.xml. Supports forceRestore and sessionId for concurrent isolation.
GetCoverageSummaryParse Summary.json into structured class/method coverage data sorted worst-first by branch coverage. Optional belowTarget/topN/methodsPerClass filters trim the response to what still needs work.
GetFileCoverageGet coverage for a single source file from Cobertura XML. Returns allMeetTarget (true when all classes meet the configured targetRate for both line and branch coverage; default 0.8). Supports sessionId.
GetUncoveredBranchesFind uncovered branch conditions for methods matching a given name. Returns all matching methods with partial name support. Supports sessionId.
GetCoverageDiffCompare current Cobertura XML against baseline. Shows method-level changes including new and removed methods. Supports sessionId for concurrent isolation.
AppendTestCodeInsert or append C# test code into a test file. Supports anchor-based insertion with whitespace-tolerant fallback matching. Uses atomic writes to prevent file corruption.
CleanupSessionRemove session state files and TestResults/coveragereport directories. Pass sessionId to scope, or omit to clean artifacts older than maxAgeMinutes (default 120).

Batch Workflow

For projects with many source files, the recommended workflow is:

  1. Discover — Call GetSourceFiles on a folder or .csproj to get all files and smart batches
  2. Run once — Call RunTestsWithCoverage with a broad filter (e.g., *) to collect coverage across all files
  3. Check per-file — Call GetFileCoverage for each file in the current batch (instant XML parsing, no test re-run)
  4. Focus — Pick the 3 lowest branch-coverage methods and call GetUncoveredBranches for each
  5. Write tests — Use AppendTestCode to add test methods
  6. Re-run and diff — Run tests once, call GetCoverageDiff to verify improvement
  7. Repeat — Continue until batch files meet the target rate (default 80%) or 3 cycles with no improvement, then move to next batch

This minimises dotnet test invocations (the main bottleneck) while still tracking per-file progress.

Concurrency

Multiple AI agents can run in parallel by passing a sessionId to each tool call, which isolates their coverage artifacts:

  • Isolated output directories — RunTestsWithCoverage creates TestResults-{hash}/ and coveragereport-{hash}/ per session, preventing one agent from deleting another's XML mid-parse
  • Scoped state files — Coverage state is written to .mcp-coverage/.coverage-state-{hash}, so ResolveCoberturaPath resolves to the correct XML for each session
  • Scoped baselines — GetCoverageDiff stores baselines as .coverage-prev-{hash}.xml per session
  • Atomic writes — All file writes (state files and test code) use write-to-temp-then-rename to prevent corruption from race conditions or process crashes

Limitation — build outputs are not session-scoped. sessionId isolates coverage artifacts, not the .NET build. dotnet test compiles the target project into its shared obj/ and bin/, which are not per-session, so two agents running RunTestsWithCoverage against the same test project at the same time collide on those outputs and fail with buildError (e.g. CS2012: the file is being used by another process). Run parallel agents against different test projects, or on separate working copies of the repo. Multiple agents on one project are fine as long as their dotnet test builds don't overlap.

Without sessionId, tools use shared defaults — safe for single-agent use.

Requirements

  • .NET 9.0 SDK (or later) — https://dotnet.microsoft.com/download

  • reportgenerator global tool — the server shells out to it to render coverage reports (installed in the Install step below)

  • An MCP-compatible client (Claude Code, Gemini CLI, etc.)

  • COVERAGE_MCP_ALLOWED_ROOT — recommended. Set to your repository root to restrict every tool's filesystem access to that subtree. Any path passed by the client outside this root is rejected with pathNotAllowed. When unset, the server logs a warning once and accepts any path (backward-compatible, but not recommended for shared environments).

    export COVERAGE_MCP_ALLOWED_ROOT=/path/to/your/repo
    

Install

Install the server as a global .NET tool from NuGet:

dotnet tool install --global dotnet-coverage-mcp

The server depends on the reportgenerator global tool to render coverage reports — install it too:

dotnet tool install --global dotnet-reportgenerator-globaltool

After install, the dotnet-coverage-mcp command is on your PATH.

Build & Run (from source)

cd <path-to-dotnet-coverage-mcp>

# Restore dependencies
dotnet restore

# Build
dotnet build

# Run
dotnet run

The server will start and wait for MCP messages over stdin/stdout.

MCP Client Configuration

After installing the global tool (dotnet tool install --global dotnet-coverage-mcp), register the server with your MCP client. Set COVERAGE_MCP_ALLOWED_ROOT to the repository you want the server to operate on.

Claude Code
claude mcp add coverage --env COVERAGE_MCP_ALLOWED_ROOT=/path/to/your/repo -- dotnet-coverage-mcp
Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "coverage": {
      "command": "dotnet-coverage-mcp",
      "env": {
        "COVERAGE_MCP_ALLOWED_ROOT": "/path/to/your/repo"
      }
    }
  }
}
Cursor

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project):

{
  "mcpServers": {
    "coverage": {
      "command": "dotnet-coverage-mcp",
      "env": {
        "COVERAGE_MCP_ALLOWED_ROOT": "/path/to/your/repo"
      }
    }
  }
}
VS Code (GitHub Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "coverage": {
      "type": "stdio",
      "command": "dotnet-coverage-mcp",
      "env": {
        "COVERAGE_MCP_ALLOWED_ROOT": "/path/to/your/repo"
      }
    }
  }
}
Run from source

To run from source instead of the global tool, use dotnet run:

{
  "mcpServers": {
    "coverage": {
      "command": "dotnet",
      "args": ["run", "--project", "<path-to-dotnet-coverage-mcp>"],
      "transport": "stdio"
    }
  }
}

Or point directly at the compiled executable:

{
  "mcpServers": {
    "coverage": {
      "command": "<path-to-dotnet-coverage-mcp>\\bin\\Debug\\net9.0\\DotNetCoverageMcp.exe",
      "transport": "stdio"
    }
  }
}

Tool Parameters

GetSourceFiles
ParameterTypeRequiredDescription
pathstringYesPath to a .cs file, folder, or .csproj project
lineBudgetintNoMax total lines per batch (default: 300). Small files are grouped together; large files get their own batch.
RunTestsWithCoverage
ParameterTypeRequiredDescription
testProjectPathstringYesFull path to the .csproj test project
filterstringYesTest filter string (matched against FullyQualifiedName). Use * or , for broad runs across multiple test classes.
workingDirstringNoWorking directory; defaults to the project directory
forceRestoreboolNoWhen true, skips the --no-restore flag. Use after scaffolding a new test project or adding NuGet packages.
sessionIdstringNoIsolates output directories (TestResults-{hash}/, coveragereport-{hash}/) and state files for concurrent multi-agent use.
includeClassstringNoRestrict coverage collection to types matching this name (coverlet Include filter, applied via a generated runsettings file passed with --settings). Independent of filter — pass an explicit value to scope coverage; omit it to collect coverage for everything the run touches. Namespace-qualified names are not supported.
skipReportboolNoWhen true, skips the reportgenerator JSON-summary step and returns only the Cobertura XML path. Faster for the inner test loop, where GetFileCoverage/GetUncoveredBranches/GetCoverageDiff read the XML directly. Leave false (default) when you need GetCoverageSummary's Summary.json.
GetCoverageSummary
ParameterTypeRequiredDescription
summaryJsonPathstringYesFull path to the generated Summary.json file
belowTargetdoubleNoWhen set (a fraction in [0,1], e.g. 0.8), return only classes whose line OR branch coverage is below this threshold. Omit for all classes.
topNintNoReturn only the N lowest-branch-coverage classes (results are sorted worst-first). Omit for all classes.
methodsPerClassintNoKeep at most this many lowest-branch-coverage methods per class, trimming the rest. Omit to keep all methods.
GetFileCoverage
ParameterTypeRequiredDescription
coberturaXmlPathstringYesPath to coverage.cobertura.xml (falls back to .mcp-coverage/.coverage-state if not found)
sourceFileNamestringYesSource file name to look up (e.g., ExampleService.cs)
sessionIdstringNoResolves session-scoped state file for concurrent isolation.
targetRatedoubleNoCoverage threshold (0.0–1.0) used to compute allMeetTarget. Default 0.8.
GetUncoveredBranches
ParameterTypeRequiredDescription
coberturaXmlPathstringYesPath to coverage.cobertura.xml (falls back to .mcp-coverage/.coverage-state if not found)
methodNamestringYesMethod name to inspect (partial match supported; returns all matching methods)
sessionIdstringNoResolves session-scoped state file for concurrent isolation.
GetCoverageDiff
ParameterTypeRequiredDescription
coberturaXmlPathstringYesPath to the current coverage.cobertura.xml
workingDirstringNoDirectory for storing baseline; defaults to the XML's parent directory
sessionIdstringNoIsolates baseline as .coverage-prev-{hash}.xml and resolves session-scoped state file.
AppendTestCode
ParameterTypeRequiredDescription
testFilePathstringYesFull path to the target .cs test file
codeToAppendstringYesC# code to insert
insertAfterAnchorstringNoIf provided, inserts code after the last occurrence of this string (with whitespace-tolerant fallback). If omitted, appends before the last }.
CleanupSession
ParameterTypeRequiredDescription
workingDirstringYesProject working directory containing .mcp-coverage/ and TestResults artifacts
sessionIdstringNoWhen set, removes only state files and directories scoped to this session.
maxAgeMinutesintNoWhen sessionId is omitted, removes artifacts older than this many minutes. Default 120.

State Files

All state files are written to a .mcp-coverage/ subdirectory inside the working directory, keeping the project root clean. Add .mcp-coverage/ to the target repository's .gitignore.

FilePurpose
.coverage-stateDefault Cobertura XML path for single-agent use
.coverage-state-{hash}Session-scoped Cobertura XML path
.coverage-prev.xmlDefault coverage baseline for diff
.coverage-prev-{hash}.xmlSession-scoped coverage baseline

Plugin (Skills & Agent)

This repo includes a plugin/ directory with Claude Code skills and an agent definition for guided test coverage workflows:

plugin/
├── plugin.json
├── agents/
│   └── test-coverage.agent.md
└── skills/
    ├── scaffold-test-files/     — Create test directories and files mirroring source structure
    ├── run-coverage/            — Run tests and view coverage reports
    ├── analyze-coverage-gaps/   — Find uncovered branches and compare diffs
    └── improve-test-coverage/   — Iterative loop to reach 80% coverage

The skills support NUnit, xUnit, and MSTest with framework-agnostic reference docs in references/unit.md and references/integration.md.

Dependencies

PackageVersionPurpose
Microsoft.Extensions.Hosting10.0.7DI and hosting
ModelContextProtocol1.2.0MCP server framework
Microsoft.CodeAnalysis.CSharp5.3.0Roslyn AST for safe code insertion and accurate method counting (~15MB)

Security

dotnet-coverage-mcp runs as a local stdio process and validates every tool argument against COVERAGE_MCP_ALLOWED_ROOT to confine filesystem access. See SECURITY.md for the threat model, hardening recommendations, and how to report a vulnerability.

Contributing

Contributions are welcome. See CONTRIBUTING.md for development setup, pull request guidelines, and code conventions. Notable changes are tracked in CHANGELOG.md.

Releasing

Maintainer-only — release process, NuGet publishing, and MCP registry submission are documented in RELEASING.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.