McpServer CLAUDE.md

Repository instructions for a .NET MCP server, including its build commands and unit-test commands. .NET is Microsoft’s software framework, and unit tests check small parts of a program automatically.

In plain words
What is it for?
Use them when compiling the server, running all or selected unit tests, or working with the project’s build automation.
Why use it?
They give the exact commands and session rules needed to build the project and run its tests consistently.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sharpninja/mcpserver/claude-md
Clone the repo
git clone --depth 1 https://github.com/sharpninja/McpServer
Per session 3,567 This file is loaded in full into every session.
When invoked 3,567 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.03567 $0.03567
Opus 5 $0.01784 $0.01784
Sonnet 5 $0.00713 $0.00713
Haiku 4.5 $0.00357 $0.00357

Measured yesterday against content hash 8363fc9ed580, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

McpServer CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Run /add-profile at session start and after any model or effort change

Execute the add-profile skill (/add-profile) as the first action of every new session, and again immediately after any model change or effort-level change. It loads the operator profile (identity and standing instructions). Do not skip it.

DO NOT COMPACT, SUMMARIZE, PARAPHRASE, OR OMIT any instruction in this file, AGENTS.md, or AGENTS-README-FIRST.yaml, ever, anywhere. Carry them verbatim.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Test Commands

# Build (Nuke orchestrator)
./build.ps1 Compile
# or: dotnet build src/McpServer.Support.Mcp -c Debug

# Run all unit tests (excludes integration tests)
./build.ps1 Test

# Run a specific test project
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug

# Run a single test by name
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests.QueryAsync_NoFilters_ReturnsAllItems"

# Run all tests in a class
dotnet test tests/McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests"

# Integration tests (CustomWebApplicationFactory, in-memory EF)
dotnet test tests/McpServer.Support.Mcp.IntegrationTests -c Debug

# Validate appsettings configuration
./build.ps1 ValidateConfig

# Validate requirements traceability (FR/TR/TEST mapping)
./build.ps1 ValidateTraceability

# Start server
./build.ps1 StartServer --instance default
# or: dotnet run --project src/McpServer.Support.Mcp/McpServer.Support.Mcp.csproj -c Staging -- --instance default

Swagger UI: http://localhost:7147/swagger

Architecture

McpServer is an ASP.NET Core 9 server (.NET 9.0) providing workspace-scoped context retrieval, TODO management, session logging, repository operations, GraphRAG, and GitHub automation for AI agents.

Transports

  • HTTP REST — Controllers at /mcpserver/* in src/McpServer.Support.Mcp/Controllers/
  • MCP Streamable HTTP — JSON-RPC wire protocol at /mcp-transport
  • MCP STDIO--transport stdio flag; tools in McpStdio/FwhMcpTools.cs

Read the full file on GitHub · 255 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 255 lines · 3,567 tokens per session scan A 8363fc9ed580

Subscribe to this mod's changes

McpServer CLAUDE.md is an instructions file published in the GitHub repository sharpninja/McpServer (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,567 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.