A workflow for building Model Context Protocol servers from Bash scripts or command-line tools. Model Context Protocol is a way for programs such as Claude Desktop or Cursor to connect to tools, data, and prompts.

Use it to create or maintain an mcp-bash project, add tools, resources, prompts, or completions, and connect the server to a supported client.

It provides project setup and reference guidance for turning shell scripts into a server instead of wiring the protocol by hand.

mcp-bash — Skill for Claude Code by yaniv-golan/mcp-bash-framework

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.

Any agent

npx skills add yaniv-golan/mcp-bash-framework --skill mcp-bash

Clone the repo

git clone --depth 1 https://github.com/yaniv-golan/mcp-bash-framework

Made for: Claude Code.

Or install mcp-bash, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yaniv-golan/mcp-bash-framework/mcp-bash/github.svg)](https://agentmods.dev/skills/yaniv-golan/mcp-bash-framework/mcp-bash)

Your own site

<a href="https://agentmods.dev/skills/yaniv-golan/mcp-bash-framework/mcp-bash"><img src="https://agentmods.dev/badge/skills/yaniv-golan/mcp-bash-framework/mcp-bash/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yaniv-golan/mcp-bash-framework/mcp-bash"><img src="https://agentmods.dev/badge/skills/yaniv-golan/mcp-bash-framework/mcp-bash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,241 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.

Model	Per session	Once invoked
Fable 5.1	$0.00194	$0.04241
Opus 5.5	$0.00078	$0.01696
Sonnet 5.5	$0.00039	$0.00848
Haiku 4.5	$0.00019	$0.00424

Measured 3d ago against content hash b8d8505e9e71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-bash 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 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.

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.

plugins/mcp-bash/skills/mcp-bash/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building MCP servers with mcp-bash

mcp-bash turns Bash scripts into an MCP server (stdio, JSON-RPC). The framework is installed once; each server is a separate project directory that the framework discovers.

This skill is the workflow and the traps. For API detail, read the reference instead of guessing — it is short and current:

Installed framework: ~/.local/share/mcp-bash/llms-full.txt (default install location; docs/ is next to it).
Otherwise: https://raw.githubusercontent.com/yaniv-golan/mcp-bash-framework/main/llms-full.txt
Topic docs, same place: docs/BEST-PRACTICES.md, docs/COMPLETION.md, docs/RESOURCE-TEMPLATES.md, docs/MCPB.md, docs/ENV_REFERENCE.md, docs/SECURITY.md, docs/DEBUGGING.md. Working examples: examples/00-hello-tool … examples/15-cli-wrapper.

Workflow

Check the framework. mcp-bash --version. If missing, use the README's verified install (checksum-checked install.sh) or brew install yaniv-golan/mcp-bash/mcp-bash.
Create the project. mcp-bash new <name> (new directory) or mcp-bash init (current one). Commands run inside the project find it by walking up to server.d/server.meta.json.
Scaffold, don't hand-write. mcp-bash scaffold tool|resource|prompt|completion <name>. The scaffold gets the SDK sourcing, metadata shape and executable bit right. Then edit tools/<name>/tool.sh and tool.meta.json (inputSchema is the argument contract).
Validate. mcp-bash validate (add --fix for permissions). Fix every error; read the warnings, they usually name a real problem.
Run one tool without a client. mcp-bash run-tool <name> --allow-self --args '{"key":"value"}'. Without --allow-self the call is refused (see deny-by-default below); that refusal is expected, not a bug in the tool.
Wire a client. mcp-bash config --client claude-desktop (or --show for all clients). Keep the MCPBASH_TOOL_ALLOWLIST and MCPBASH_PROJECT_ROOT it prints.
Ship. Either mcp-bash bundle (an .mcpb for Claude Desktop; configure via mcpb.conf, see docs/MCPB.md) or mcp-bash vendor (embed the runtime in .mcp-bash/ and commit it).

Read the full file on GitHub · 237 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.

3d ago Changed · +12 lines b8d8505e9e71
5d ago First seen · 225 lines · 194 tokens per session scan A 3e68c440dca8

Subscribe to this mod's changes

mcp-bash is a skill published in the GitHub repository yaniv-golan/mcp-bash-framework (11 stars, last pushed today), licensed MIT. It adds 194 tokens to every session and 4,241 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-11.

Backend and APIs Building agents agents automation bash cli cross-platform devtools

mcp-bash

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Building MCP servers with mcp-bash

Workflow

What this file has done since we first saw it

Other skills, from other repositories

wikipedia

cve

api-less-website

jk

aiox-architect

aiox-data-engineer