agentmods.dev

roslyn-mcp-paths

roslyn-mcp-paths is a cursor rule for Cursor from VuDZ/RoslynMcpServer. It costs 320 tokens per session, scanned A, original, MIT.

A set of rules for resolving file paths and searching source code in a Roslyn MCP server. It makes relative paths use the loaded .NET workspace, such as a solution or project folder, rather than assuming the process's current folder is correct.

In plain words
What is it for?
Use it when implementing or reviewing workspace loading, file-based tools, and C# source searches.
Why use it?
It prevents searches from scanning a user's home directory or opening the wrong file when the agent starts in an unexpected folder. It also limits searches and reports progress to avoid unbounded scans.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

not rated 7repo yesterday A scan 320 tokens original MIT

Good fit Use it when implementing or reviewing workspace loading, file-based tools, and C# source searches.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/vudz/roslynmcpserver/roslyn-mcp-paths
View source ↗ VuDZ/RoslynMcpServer
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.

Clone the repo
git clone --depth 1 https://github.com/VuDZ/RoslynMcpServer

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for roslyn-mcp-paths

README.md
[![agentmods](https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-paths/github.svg)](https://agentmods.dev/rules/vudz/roslynmcpserver/roslyn-mcp-paths)
Your own site
<a href="https://agentmods.dev/rules/vudz/roslynmcpserver/roslyn-mcp-paths"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-paths/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for roslyn-mcp-paths

Your own site · 80×15
<a href="https://agentmods.dev/rules/vudz/roslynmcpserver/roslyn-mcp-paths"><img src="https://agentmods.dev/badge/rules/vudz/roslynmcpserver/roslyn-mcp-paths.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 320 This file is loaded in full into every session.
When invoked 320 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00320 $0.00320
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash fae136e2712e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

roslyn-mcp-paths 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 2d ago.

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.

.cursor/rules/roslyn-mcp-paths.mdc · 32 lines

What it actually says

Relative filePath

Path.GetFullPath alone resolves against process CWD (often the user profile under Cursor). Always use SolutionManager.ResolvePathAgainstWorkspace:

  • Absolute → normalize and return
  • Relative → combine with directory of loaded .sln/.csproj (_loadedPath)
  • No workspace → fallback Path.GetFullPath (CWD)

Wire all filePath-based tools through this helper. Tests: SolutionManagerPathResolutionTests.

search_code

  • Default root: GetLoadedWorkspaceDirectory() when directoryPath omitted — never rely on CWD alone (hangs scanning user profile).
  • Default extensions: .cs only; override via includeExtensions (e.g. .cs,.csproj,.json or * for all).
  • Support maxScanSeconds + progress logging to avoid unbounded scans.

Env

  • ROSLYN_MCP_WORKSPACE — repo root (folder with global.json); sets process cwd at startup for tools that still use CWD.
  • Do not set CurrentDirectory to AppContext.BaseDirectory (publish output) — breaks search/scratchpad.

Agent-facing docs

Relative paths in MCP calls are OK after load_workspace. Prefer absolute when unsure. Never hardcode machine-specific paths in AGENTS.md / README samples.

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. 2d ago First seen · 32 lines · 320 tokens per session scan A fae136e2712e

Subscribe to this mod's changes

roslyn-mcp-paths is a cursor rule published in the GitHub repository VuDZ/RoslynMcpServer (7 stars, last pushed yesterday), licensed MIT. It adds 320 tokens to every session, about $0.0016 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 2026-09-14.

C# and .NETDebuggingLLMLanguagesai-agentcursordotnetmcp
Related

Other cursor rules, from other repositories

code-style

Formatting, lint, comments language.

coddy-project/coddy-agent · 123 tokens

python-app

Here's how the python application is organized.

iloveitaly/llm-ide-rules · 1,524 tokens

typescript

Here's how frontend code is organized in web/app/.

iloveitaly/llm-ide-rules · 458 tokens

python-code-style-for-apps

Python 3.14 code style for ArchiPy apps — formatting, imports, docstrings, errors, complexity.

SyntaxArc/archipy-plugin · 368 tokens

codesynapse-cli

Use this rule to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. Triggers on: "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace request flow"…

sohilladhani/codesynapse · 0 tokens

pn-rust-backend

Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).

perniemann/pnCore · 0 tokens