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.
npx agentmods add rules/dxheroes/mcp-devtools/mcp-tool-implementationgit clone --depth 1 https://github.com/DXHeroes/mcp-devtoolsWhat 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 | $0.00318 | $0.00318 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
mcp-tool-implementation 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 yesterday.
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.
What it actually says
MCP Tool Implementation Guidelines
When implementing a new MCP tool, follow these patterns:
@file packages/jira/src/tools/getTicket.ts @file .cursor/rules/typescript-style.mdc
Tool Registration
export const registerToolName = (server: McpServer): void => {
const toolParams = {
// Define parameters according to JSON schema
};
// For tools with aliases, use an array of tool names
const toolNames = ["primary_tool_name", "alias_1", "alias_2"];
// Register all tool names with the same handler
for (const tool of toolNames) {
server.tool(tool, toolParams, async (params) => {
try {
// Implementation
return {
message: "Success message",
};
} catch (error) {
return {
error: `Error message: ${error.message}`,
};
}
});
}
};
Parameter Validation
- Always validate required parameters early in the function
- Use TypeScript types/interfaces for parameter typing
- Document parameters with clear descriptions
Error Handling
- Use try/catch blocks for all API calls
- Return meaningful error messages
- Log errors with appropriate context
Documentation
- Update the README.md with your new tool
- Add the tool to the Tool Reference table with all parameters
- Include any aliases in the documentation
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.
- yesterday First seen · 60 lines · 318 tokens per session scan A b4800aac0e7b
mcp-tool-implementation is a cursor rule published in the GitHub repository DXHeroes/mcp-devtools (13 stars, last pushed 1y ago), licensed MIT. It adds 318 tokens to every session, about $0.0016 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
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
rule
AI/ML Python development (PyTorch, scikit-learn).
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.