mcp-server-test-compliance

mcp-server-test-compliance is a cursor rule for Cursor from hackerdogs-ai/hd-mcpservers-docker. It costs 0 tokens per session (989 once invoked), scanned A, original, Apache-2.0.

A compliance checklist for testing MCP servers, which let coding agents call external tools. It requires checking installation and tool loading and calling over both standard input/output and HTTP.

In plain words
What is it for?
Use it when writing or reviewing an MCP server's test.sh file, verifying its container build, checking tool discovery, and testing tool calls over stdio and HTTP.
Why use it?
It catches servers that build incorrectly, fail to expose tools, or work through one connection method but not the other. This provides a repeatable minimum test for each server's test script.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when writing or reviewing an MCP server's test.sh file, verifying its container build, checking tool discovery, and testing tool calls over stdio and HTTP.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance
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/hackerdogs-ai/hd-mcpservers-docker

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 mcp-server-test-compliance

README.md
[![agentmods](https://agentmods.dev/badge/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance/github.svg)](https://agentmods.dev/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance)
Your own site
<a href="https://agentmods.dev/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance"><img src="https://agentmods.dev/badge/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance/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 mcp-server-test-compliance

Your own site · 80×15
<a href="https://agentmods.dev/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance"><img src="https://agentmods.dev/badge/rules/hackerdogs-ai/hd-mcpservers-docker/mcp-server-test-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00989
Opus 5 $0.00000 $0.00495
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 9d ago against content hash 27d32f1002f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-server-test-compliance 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 9d 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/mcp-server-test-compliance.mdc · 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.

MCP Server Test Compliance

Every MCP server's test.sh must include these five test areas. Treat this as required compliance for all *-mcp servers in this repo.

1. Test the install

  • Build or verify the Docker image (e.g. docker build -t <image> . or docker image inspect <image>).
  • Fail if the image cannot be built or is missing.

2. Test loading of tools using stdio

  • Run the server with MCP_TRANSPORT=stdio.
  • Send JSON-RPC: initialize, then notifications/initialized, then tools/list.
  • Assert the response contains a tools list (e.g. grep for "tools" or result.tools).
  • Capture full output before asserting (e.g. OUT=$( ... ); echo "$OUT" | grep -q '"tools"') to avoid pipe buffering issues.

3. Test calling one or more tools using stdio

  • Send initialize, notifications/initialized, then tools/call with a simple tool (e.g. a status tool, or a call that needs no API key).
  • Keep stdin open after the last message (e.g. ( printf '...'; sleep 4 ) | docker run ...) so the server can write the response.
  • Assert the response contains expected result (e.g. "result", "content", or a known string from the tool output).
  • Prefer tools that do not require API keys or network when possible.

4. Test loading of tools using HTTP streamable

  • Start the server with MCP_TRANSPORT=streamable-http and MCP_PORT=<port>.
  • POST to http://localhost:<port>/mcp with Content-Type: application/json and Accept: application/json, text/event-stream.
  • Send initialize; capture mcp-session-id from response headers if present.
  • Send tools/list (and notifications/initialized if required) with the same session.
  • Assert the response includes a tools list (e.g. contains "tools").

5. Test calling one or more tools using HTTP streamable

  • Using the same HTTP session (and mcp-session-id if used), POST tools/call with a simple tool and minimal arguments.
  • Assert the response contains "result" or "content" or a known success indicator.
  • Prefer tools that do not require API keys when possible.

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. 9d ago First seen · 72 lines · 0 tokens per session scan A 27d32f1002f8

Subscribe to this mod's changes

mcp-server-test-compliance is a cursor rule published in the GitHub repository hackerdogs-ai/hd-mcpservers-docker (5 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 989 tokens. 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.