Provides access to Google's comprehensive prompting guide, covering techniques, best practices, and LLM configuration for crafting effective prompts.
Instant access to Google and Anthropic's official prompting guides within your LLM workflow—optimized for crafting high-quality meta-prompts and system prompts.
Meta-Prompt MCP is an MCP server that surfaces official prompting best practices from Google and Anthropic directly within your LLM workflow. Instead of searching documentation or guessing how to instruct an LLM, you can query expert guides on-demand.
This is especially valuable when crafting meta-prompts (system prompts for agents) or optimizing your own prompting strategies. By grounding your prompts in proven methodology, you'll generate more effective, well-structured outputs.
Your MCP host (Claude Desktop, Cursor, etc.) communicates with the server via stdio. When you ask for a guide, the server retrieves it from bundled markdown files—no API calls, no latency.
┌────────────────────────┐ ┌──────────────────────────┐
│ Your LLM Host │◄─stdio──►│ Meta-Prompt MCP Server │
│ (Claude Desktop, etc) │ │ │
└────────────────────────┘ │ • get_google_guide │
│ • get_anthropic_guide │
│ │
│ Data layer: │
│ ./data/ │
│ ├── google_*.md │
│ └── anthropic_*.md │
└──────────────────────────┘get_google_guide — Retrieves Google's comprehensive prompting guide covering techniques, best practices, and LLM configuration
get_anthropic_guide — Retrieves Anthropic's guide on chain-of-thought, multishot prompting, and extended thinking
Zero dependencies — Runs entirely offline with bundled guides; no API keys or network calls required
Related MCP server: MCP Prompt Optimizer
We ran a benchmark comparing prompts generated with and without guide access across 5 diverse tasks. An independent judge LLM scored each on Clarity, Specificity, Structure, Effectiveness, and Overall quality (1–10 scale).
To reproduce the benchmark:
export OPENROUTER_API_KEY=sk-or-...
make benchmark# Via uvx (recommended — run without installing globally)
uvx meta-prompt-mcp
# Or install via pip
pip install meta-prompt-mcpThe package ships with bundled markdown guides — no API keys or setup needed.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"meta-prompt-mcp": {
"command": "uvx",
"args": ["meta-prompt-mcp"]
}
}
}Add to your MCP settings:
{
"mcpServers": {
"meta-prompt-mcp": {
"command": "uvx",
"args": ["meta-prompt-mcp"]
}
}
}Run the following command in your terminal:
claude mcp add meta-prompt-mcp -- uvx meta-prompt-mcpQuery the guides while crafting your prompts. Examples:
"I'm building a code reviewer agent. Reference the Google guide to help me write a better system prompt."
"Based on the Anthropic guide, suggest improvements to this prompt for better reasoning."
"What technique from the guides would work best for this task?"
The LLM reads the guides and uses that knowledge to give you more informed suggestions and feedback on your prompts.
# Clone the repo
git clone https://github.com/kapillamba4/meta-prompt-mcp.git
cd meta-prompt-mcp
# Install in dev mode
make dev
# Run the server
make runmake dev # Install in editable mode with dev dependencies
make run # Start the MCP server locally
make lint # Check code quality
make format # Auto-format code with Black & isort
make test # Run test suite
make benchmark # Run prompt quality benchmark (requires OPENROUTER_API_KEY)
make build # Build distribution packages
make publish # Publish to PyPImeta-prompt-mcp/
├── pyproject.toml # Dependencies and package config
├── Makefile # Development commands
├── .env.example # Template for OPENROUTER_API_KEY
│
├── benchmarks/
│ ├── benchmark.py # Prompt quality evaluation script
│ └── results.md # Benchmark results
│
└── src/meta_prompt_mcp/
├── __init__.py
├── __main__.py # Entry point (python -m)
├── server.py # FastMCP server & tool definitions
└── data/
├── google_prompting_guide.md
└── anthropic_prompting_guide.mdIssues, feature requests, and contributions welcome. Please open an issue on GitHub.
MIT
USE THIS TOOL proactively when you need to write, create, refine, or optimize prompts specifically for Claude/Anthropic models. Retrieves Anthropic's official Prompting Guide as reference material.
ALWAYS CALL THIS TOOL when:
You are writing a prompt that will be used with Claude (Opus, Sonnet, Haiku)
You need to design system prompts for Claude
You are structuring prompts with XML tags, tool definitions, or multi-turn conversations
The user mentions Anthropic, Claude, or wants Claude-specific prompt optimization
Prefer this over get_google_guide when targeting Claude/Anthropic models.
Returns: The complete Anthropic Prompting Guide markdown content.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It clearly states the tool returns markdown content and is for reference material. It could be more explicit about side effects (likely none, as it's read-only), but the usage context strongly implies no destructive actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three paragraphs but each earns its place: first gives purpose and proactive use instruction, second lists conditions, third differentiates sibling. No wasted words, front-loaded with key action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and a clear output (markdown content), the description is complete. It covers purpose, usage guidelines, differentiation, and return format. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (100% coverage by default), so the description does not need to explain parameters. It adds no param info because none exist; the description's value lies elsewhere. A baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool retrieves Anthropic's official Prompting Guide, with specific use cases like writing/optimizing prompts for Claude models. It clearly identifies the resource and distinguishes from sibling tool get_google_guide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use scenarios (prompt writing for Claude, structuring XML tags, etc.) and even states 'Prefer this over get_google_guide when targeting Claude/Anthropic models,' offering clear guidance on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
USE THIS TOOL proactively when you need to write, create, refine, or optimize any prompt. Retrieves Google's official Prompting Guide as reference material to help you generate higher-quality prompts.
ALWAYS CALL THIS TOOL when:
You are tasked with writing a prompt (for yourself or another system)
You need to refine or improve an existing prompt
You are designing system prompts, few-shot examples, or chain-of-thought structures
The user asks you to "write a prompt for..." or "help me craft a prompt"
Do NOT wait for explicit permission — call this tool at the start of any prompt-writing task to ensure your output follows proven best practices.
Returns: The complete Google Prompting Guide markdown content.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description clearly states it retrieves guide content and returns markdown. Could mention read-only nature explicitly but sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with bold headings and bullet points. Front-loaded with imperative. Slightly verbose but effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Completely covers purpose, usage, and return type for a zero-parameter tool with output schema present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, baseline of 4. No additional parameter info needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool retrieves Google's official Prompting Guide for prompt writing. Distinguishes from sibling get_anthropic_guide by name and content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly lists when to use (writing, refining prompts) and includes imperative 'ALWAYS CALL' and 'do not wait for explicit permission'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a specific provider (Anthropic vs Google) with clear usage guidelines, so there is no ambiguity about which to use.
Both tools follow a consistent verb_noun pattern: get_anthropic_guide and get_google_guide.
Two tools are appropriate for the narrow scope of retrieving prompting guides from two major providers, covering the primary need without bloat.
The set covers Anthropic and Google guides well, but may miss guides from other providers (e.g., OpenAI), which is a minor gap.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for AI agent profiles and smart notes. 60+ coding prompt packs with expert personas.
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for agentverse documentation, generated by doc2mcp.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kapillamba4/meta-prompt-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
