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/netanelavr/trading-mcpWrote 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/netanelavr/trading-mcp/mcp-tool-definition)<a href="https://agentmods.dev/rules/netanelavr/trading-mcp/mcp-tool-definition"><img src="https://agentmods.dev/badge/rules/netanelavr/trading-mcp/mcp-tool-definition/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/netanelavr/trading-mcp/mcp-tool-definition"><img src="https://agentmods.dev/badge/rules/netanelavr/trading-mcp/mcp-tool-definition.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 | $0.00058 | $0.00541 |
| Opus 5 | $0.00029 | $0.00270 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
mcp-tool-definition 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Definitions
When adding or editing an MCP Server's tool, follow this structure to make it clear when and how the tool should be used:
Tool Title
The title should clearly indicate what the tool accomplishes or produces. Focus on the outcome or capability - what will it do for the user? Examples:
- "Screen Stocks by Technical Patterns" (not "Stock Screening Tool")
- "Analyze Insider Trading Activity" (not "Insider Data Tool")
- "Calculate Financial Health Score" (not "Health Score Generator")
Tool Description
The description should cover four key aspects:
- What is it? - Brief explanation of the tool's purpose
- What does it do? - Functionality explanation
- When to use it? - Clear use cases and scenarios
- What it returns/effects? - Expected outputs or side effects
Descriptions should be comprehensive enough for an AI agent to understand when this tool is the appropriate choice over others.
Example format:
"This tool [what it is] that [what it does]. Use this when [when to use it, specific scenarios].
The tool will [what it returns/effects]. [Additional context or limitations if relevant]."
Trading-Specific Examples:
Good:
"Comprehensive stock screening using Finviz filters that supports technical patterns, fundamental criteria, and multi-parameter filtering. Use this when you need to find stocks matching specific investment criteria like channel down patterns, profitable companies, or large-cap stocks. The tool returns a ranked list of stocks with key metrics including market cap, P/E ratios, and current prices. Supports complex filter combinations for advanced screening strategies."
Poor:
"Advanced stock filter for custom screening with multiple filter combinations."
Good:
"Financial health analysis tool that calculates a comprehensive score based on profitability, liquidity, leverage, efficiency, and growth metrics. Use this when evaluating the overall financial strength of a company for investment decisions or risk assessment. Returns a weighted health score (0-100) with detailed breakdowns of each category and actionable insights. Allows custom weighting of different financial factors."
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.
- 9d ago First seen · 55 lines · 58 tokens per session scan A f1e99473e5a5
mcp-tool-definition is a cursor rule published in the GitHub repository netanelavr/trading-mcp (75 stars, last pushed 1y ago), licensed MIT. It adds 58 tokens to every session and 541 once invoked, about $0.0003 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 2026-08-30.
Other cursor rules, from other repositories
savee
Use the Savee MCP tools when the task involves design inspiration, visual references, moodboards, or the user's own saved work.
agentmemory
AgentMemory MCP server rules — use addmemory before answering any question that introduces a project-specific convention, dependency, or constraint.
blekline-chat-guard
Blekline chat guard — mask prompts via MCP and respect Cursor hook blocks.
cost-awareness
Cost-aware AI model selection guidance for Cursor Enterprise teams.
rust-clap
Rust CLI Best Practices with clap.
devenv-tools
Devenv Development Tools and Utilities.