copilot-security-instructions mcp-server.development.instructions.md

copilot-security-instructions mcp-server.development.instructions.md is an instructions file for GitHub Copilot from Robotti-io/copilot-security-instructions. It costs 346 tokens per session, scanned A, original, Apache-2.0.

Coding rules for building MCP servers, which let AI tools call functions exposed by an application over HTTP.

In plain words
What is it for?
Use them when changing server code or tests, especially for request parsing, responses, MCP tool definitions, validation, and logging.
Why use it?
They reduce common risks such as unsafe request handling, leaked internal errors, unstable tool interfaces, and sensitive data in logs.

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/robotti-io/copilot-security-instructions/mcp-server.development
Clone the repo
git clone --depth 1 https://github.com/Robotti-io/copilot-security-instructions

Made for: GitHub Copilot.

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 copilot-security-instructions mcp-server.development.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robotti-io/copilot-security-instructions/mcp-server.development.svg)](https://agentmods.dev/instructions/robotti-io/copilot-security-instructions/mcp-server.development)
Your own site
<a href="https://agentmods.dev/instructions/robotti-io/copilot-security-instructions/mcp-server.development"><img src="https://agentmods.dev/badge/instructions/robotti-io/copilot-security-instructions/mcp-server.development.svg" alt="Measured on agentmods" height="20"></a>
Per session 346 This file is loaded in full into every session.
When invoked 346 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00346 $0.00346
Opus 5 $0.00173 $0.00173
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured 3d ago against content hash 6d425b5a335e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-security-instructions mcp-server.development.instructions.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Every behavior change MUST include a verification step (test or curl reproduction).
.github/instructions/mcp-server.development.instructions.md · 48 lines

What it actually says

MCP server development rules (this repo)

These rules apply to changes under src/ and related MCP server tests.

Core standards

  • Prefer minimal diffs and incremental improvements.
  • Avoid breaking existing tool names/behaviors unless explicitly intended.
  • Every behavior change MUST include a verification step (test or curl reproduction).

Express / HTTP handling

  • Request bodies MUST be parsed safely:
    • use explicit JSON parsing middleware
    • set a reasonable size limit for JSON bodies
  • Validate content negotiation:
    • MCP endpoints should check Accept headers as appropriate for the endpoint behavior.
  • Error handling MUST be consistent:
    • do not expose internal stack traces to clients
    • return clear status codes and brief error messages

MCP tools

  • Every MCP tool MUST have:
    • stable tool name (choose and keep a consistent naming convention across tools)
    • title + description
    • zod input schema (even if empty)
    • deterministic output shape
  • Do not return raw secrets or dump large file contents by default.

Logging hygiene

  • Do not log raw request bodies.
  • If logging headers, redact authorization-like fields.
  • Prefer structured logs with source and request id (when available).

Testing

  • Add or update tests when:
    • endpoint behavior changes
    • new tools are added
    • error handling changes
  • Tests MUST be deterministic and fast.

Output requirements for Copilot edits

When generating patches:

  • Output full file contents for modified files in fenced md blocks.
  • Include a short verification checklist (commands + expected results).
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. 3d ago First seen · 48 lines · 346 tokens per session scan A 6d425b5a335e

Subscribe to this mod's changes

copilot-security-instructions mcp-server.development.instructions.md is an instructions file published in the GitHub repository Robotti-io/copilot-security-instructions (42 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 346 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.