Prompt DecoratorsBLOCK
A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](https://www.python.org/) [](https://synaptiai.github.io/prompt-decorators/) [](https://github.com/astral-sh/ruff)
[](https://github.com/synaptiai/prompt-decorators/actions?query=workflow%3A%22Code+Quality+and+Testing%22) [](https://github.com/synaptiai/prompt-decorators/actions?query=workflow%3A%22Documentation%22) [](https://github.com/synaptiai/prompt-decorators/actions?query=workflow%3A%22Publish+to+PyPI%22)
Prompt Decorators is a comprehensive framework that standardizes how prompts for Large Language Models (LLMs) are enhanced, structured, and transformed. This repository contains both the official Prompt Decorators Specification and its complete Python reference implementation.
Documentation • Prompt Decorators Specification
📋 Table of Contents
- Overview
- What Are Prompt Decorators?
- Key Components
- Background & Motivation
- Challenges in Prompt Engineering
- [Benefits of Prompt Decorators](#benefits-of-prompt-de
b7078c89c205OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add prompt-decorators --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx prompt-decorators{
"mcpServers": {
"prompt-decorators": {
"command": "uvx",
"args": [
"prompt-decorators"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (5)
3 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
apply_decorators | write | Apply decorators to a prompt using the +++ syntax. |
create_decorated_prompt | write | Create a decorated prompt using a predefined template. |
get_decorator_details | read | Get detailed information about a specific decorator. |
list_decorators | read | Lists all available prompt decorators. |
transform_prompt | read | Transform a prompt using a list of decorator strings. |
Trust audit
BLOCKgrade F · trust 60/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (21)
exec(transform_code, namespace)
exec(transform_code, namespace)
exec(transform_code, namespace)
- Remember that a story is not complete if you have not also ran ALL stories and verified all stories pass. Do not tell the user the story is complete, or mark the story as complete unless you have ru
module = importlib.import_module(package_name)
module = importlib.import_module(package_name)
client = anthropic.Anthropic(api_key="your-anthropic-api-key")
client = anthropic.Anthropic(api_key="your-anthropic-api-key")
.cursorignore
.cursorindexingignore
.pre-commit-config.yaml
.env.sample
module = importlib.import_module(module_name)
module = importlib.import_module(module_name)
exec(transform_function, namespace)
exec(transform_function, namespace)
content_hash = hashlib.md5(
return hashlib.md5(prompt.encode()).hexdigest()
prompt-decorators, openai, python-dotenv, rich, typer
mkdocs, mkdocs-material, mkdocs-autolinks-plugin, mkdocs-git-revision-date-localized-plugin, mkdocs-minify-plugin, mkdocstrings, mkdocstrings-python, pydantic
pytest, pytest-cov, jsonschema, markdown, python-dotenv
Gates applied: instruction_override, no_behavioural_pass.
b7078c89c205full audit observations/trust-audit/mcp-server/synaptiai__prompt-decorators.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | b7078c89c205 | BLOCK | F | 60 | first audit |
Questions
What is the Prompt Decorators MCP server?
A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.
What tools does Prompt Decorators expose?
5 in total: 3 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Prompt Decorators safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (60/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Prompt Decorators need?
It reads ANTHROPIC_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (b7078c89c205), read on 2026-10-08. The repository is watched and re-audited when it changes.