mcp-echo CLAUDE.md

mcp-echo CLAUDE.md is an instructions file for coding agents from NimbleBrainInc/mcp-echo. It costs 306 tokens per session, scanned A, original, MIT.

A project instruction file for an echo MCP server, a small service used to test connections between AI tools and external programs. It documents commands, end-to-end tests, and releases.

In plain words
What is it for?
Use it when changing the server, running unit or end-to-end tests, checking code quality, or preparing a versioned release.
Why use it?
It gives the coding agent the project-specific rules and commands needed to work consistently. It also explains the extra tools required to run tests in Docker containers.

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/nimblebraininc/mcp-echo/claude-md
Clone the repo
git clone --depth 1 https://github.com/NimbleBrainInc/mcp-echo

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-echo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nimblebraininc/mcp-echo/claude-md.svg)](https://agentmods.dev/instructions/nimblebraininc/mcp-echo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nimblebraininc/mcp-echo/claude-md"><img src="https://agentmods.dev/badge/instructions/nimblebraininc/mcp-echo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 306 This file is loaded in full into every session.
When invoked 306 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 $0.00306 $0.00306
Opus 5 $0.00153 $0.00153
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 4d ago against content hash b42933e0b3da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-echo 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 34 lines

What it actually says

Echo MCP Server

FastMCP echo server for testing MCP connections.

Commands

make test               # Unit tests
make test-e2e           # E2E tests (requires Docker + mcpb CLI)
make check              # Format + lint + typecheck + unit tests
make bump VERSION=x.y.z # Bump version in all files

E2E Tests

e2e/ contains end-to-end tests that build and deploy the actual MCPB bundle in a Docker container, then verify health, tool listing, and tool invocation over HTTP.

Prerequisites: Docker running, mcpb CLI installed

The tests automatically vendor Linux-compatible deps (matching the Docker daemon's architecture) using uv pip install --python-platform, so they work on macOS and Linux hosts.

Config: e2e/conftest.py has BASE_IMAGE, PYTHON_VERSION, CONTAINER_PORT, and BUNDLE_NAME.

Release

See mcp-servers/CLAUDE.md for the full release workflow.

make bump VERSION=0.2.0
git add -A && git commit -m "Bump version to 0.2.0"
git tag v0.2.0 && git push origin main v0.2.0
gh release create v0.2.0 --title "v0.2.0" --notes "- changelog"
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. 4d ago First seen · 34 lines · 306 tokens per session scan A b42933e0b3da

Subscribe to this mod's changes

mcp-echo CLAUDE.md is an instructions file published in the GitHub repository NimbleBrainInc/mcp-echo (1 stars, last pushed 1mo ago), licensed MIT. It adds 306 tokens to every session, about $0.0015 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.