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.
git clone --depth 1 https://github.com/atlanhq/agent-toolkitWrote 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.
[](https://agentmods.dev/rules/atlanhq/agent-toolkit/tool-development-guide)<a href="https://agentmods.dev/rules/atlanhq/agent-toolkit/tool-development-guide"><img src="https://agentmods.dev/badge/rules/atlanhq/agent-toolkit/tool-development-guide/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.
<a href="https://agentmods.dev/rules/atlanhq/agent-toolkit/tool-development-guide"><img src="https://agentmods.dev/badge/rules/atlanhq/agent-toolkit/tool-development-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01138 | $0.01138 |
| Opus 5.5 | $0.00455 | $0.00455 |
| Sonnet 5.5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
tool-development-guide 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This guide outlines the core coding patterns for implementing tools in the Atlan MCP server.
Tool Implementation Pattern
- Define core function in tools.py
- Register function as MCP tool in server.py
- Use appropriate type hints for PyAtlan and MCP compatibility
Core Function Template (tools.py)
def implement_atlan_tool(
param1: str,
param2: Optional[int] = None,
param3: Optional[Dict[str, Any]] = None
) -> Any:
"""
Implement an Atlan tool with appropriate parameters.
"""
logger.info(f"Starting tool execution with parameters: param1={param1}")
try:
# Tool-specific implementation
result = execute_atlan_operation(param1, param2, param3)
logger.info(f"Tool execution completed successfully")
return result
except Exception as e:
logger.error(f"Error executing tool: {str(e)}")
logger.exception("Exception details:")
return get_appropriate_default_value()
MCP Tool Registration Template (server.py)
@mcp.tool()
def registered_tool_name(
param1: str,
param2: Optional[int] = None,
param3: Optional[Dict[str, Any]] = None
) -> Any:
"""
Tool description with clear purpose.
Args:
param1: First parameter description
param2: Second parameter description
param3: Third parameter description (complex structure)
Returns:
Description of return value
Example:
registered_tool_name("value1", 42, {"key": "value"})
"""
return implement_atlan_tool(param1, param2, param3)
Common Operation Patterns
Asset Search Operation
def search_operation(criteria):
search = FluentSearch()
# Add filters based on criteria
request = search.to_request()
results = list(atlan_client.asset.search(request).current_page())
return results
Asset Retrieval Operation
def get_asset_operation(qualified_name, asset_type):
try:
asset = asset_type.get_by_qualified_name(
qualified_name=qualified_name,
min_ext_info=True,
atlan_client=atlan_client
)
return asset
except Exception as e:
logger.error(f"Failed to get asset: {e}")
return None
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.
- 1mo ago First seen · 202 lines · 1,138 tokens per session scan A 0db7ddd300d5
tool-development-guide is a cursor rule published in the GitHub repository atlanhq/agent-toolkit (41 stars, last pushed 17d ago), licensed MIT. It adds 1,138 tokens to every session, about $0.0046 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 2026-08-30.
Other cursor rules, from other repositories
pn-php-backend
PHP backend style, env, and error handling. Use for API and server code (Laravel, Slim).
pn-ruby-backend
Ruby backend style, env, and error handling. Use for API and server code (Rails, Sinatra).
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-go-backend
Go backend style, env, and error handling. Use for API and server code (Gin, Fiber, Echo).
pn-node-backend
Node.js and backend style, safety, and env/secrets. Use for API and server code.
pn-python-backend
Python backend style, env/secrets, and error handling. Use for API and server code (FastAPI, Flask).