rust-mcp-server copilot-instructions.md

Project instructions for building a Rust-based MCP server, including its communication method, asynchronous structure, dependencies, and required tool behaviour. Rust is a programming language, and MCP is a standard for connecting AI applications to tools.

In plain words
What is it for?
Use them when developing or reviewing the server, including its JSON-RPC communication, tools, resources, logging, error handling, formatting, and checks.
Why use it?
They give coding agents consistent rules for understanding and changing this particular server.

Instructions file for GitHub Copilot

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/vaiz/rust-mcp-server/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Vaiz/rust-mcp-server

Made for: GitHub Copilot.

Per session 691 This file is loaded in full into every session.
When invoked 691 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 $0.00691 $0.00691
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 2d ago against content hash 536319f210ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-mcp-server copilot-instructions.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 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.

.github/copilot-instructions.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for Rust MCP Server

This is a Rust implementation of a Model Context Protocol (MCP) server.

Project Context

  • Language: Rust
  • Protocol: Model Context Protocol (MCP)
  • Communication: JSON-RPC over stdio
  • Architecture: Async/await with Tokio runtime

Key Guidelines

  1. Follow Rust best practices and idioms
  2. Use proper error handling with Result<T, E> and ohno::AppError for error propagation
  3. Implement MCP protocol methods according to the specification
  4. Use structured logging with the tracing crate
  5. Ensure all async operations are properly awaited

MCP Protocol Implementation

  • Initialize: Handle client initialization and capability negotiation
  • Tools: Implement tool listing and execution
  • Resources: Handle resource discovery and reading
  • Logging: Support MCP logging protocol

Dependencies

  • tokio: Async runtime
  • serde: Serialization/deserialization
  • rmcp: MCP protocol handling
  • ohno: Error handling
  • tracing: Structured logging

AI Agent Guidelines

1. Always Use Rust MCP Tools

  • Use #cargo-check for quick code validation
  • Use #cargo-clippy for linting
  • Use #cargo-fmt for code formatting
  • Use #cargo-test for running tests

2. use @rust-docs subagent

  • For any questions about public API for dependencies or standard library, consult the @rust-docs subagent. Just ask it what you looking for in natural language, and it will fetch the relevant documentation for you.

2. Development Workflow

Follow this systematic approach when working on code changes:

  1. Check current state: Use #cargo-check with all_targets: true, all_features: true
  2. Make changes: Edit code using appropriate development tools
  3. Validate: Use #cargo-clippy with workspace: true, all_targets: true
  4. Format: Use #cargo-fmt with all: true
  5. Test: Use #cargo-test with all_features: true
  6. Build: Use #cargo-build with all_targets: true, all_features: true for final verification
  7. Check unused dependencies: Use #cargo-machete to identify unused dependencies
  8. Verify security compliance: Use #cargo-deny-check to ensure security and licensing compliance

Read the full file on GitHub · 72 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. 2d ago First seen · 72 lines · 691 tokens per session scan A 536319f210ea

Subscribe to this mod's changes

rust-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository Vaiz/rust-mcp-server (35 stars, last pushed 17d ago), licensed Unlicense. It adds 691 tokens to every session, about $0.0035 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 2026-08-30.