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/aamar-shahzad/mcp-screenshot-serverWrote 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/aamar-shahzad/mcp-screenshot-server/mcp-tools)<a href="https://agentmods.dev/rules/aamar-shahzad/mcp-screenshot-server/mcp-tools"><img src="https://agentmods.dev/badge/rules/aamar-shahzad/mcp-screenshot-server/mcp-tools/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/aamar-shahzad/mcp-screenshot-server/mcp-tools"><img src="https://agentmods.dev/badge/rules/aamar-shahzad/mcp-screenshot-server/mcp-tools.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 | $0.00000 | $0.00631 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
mcp-tools 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Authoring Rules
Return Types
All MCP tool functions must return Pydantic BaseModel subclasses, never bare dict[str, ...].
Good:
class DeleteResult(BaseModel):
message: str = Field(description="Status message")
@mcp.tool()
def delete_image(image_id: str) -> DeleteResult:
return DeleteResult(message="Deleted")
Bad:
@mcp.tool()
def delete_image(image_id: str) -> dict[str, str]:
return {"message": "Deleted"}
Input Validation
All numeric parameters with documented ranges must include Pydantic Field constraints:
opacity: Annotated[int, Field(ge=0, le=255, description="Opacity (0-255)")] = 100
font_size: Annotated[int, Field(gt=0, description="Font size")] = 24
quality: Annotated[int, Field(ge=1, le=100, description="JPEG quality")] = 95
Private Helpers
Use existing private helpers instead of duplicating code:
_get_font(size)- Cross-platform font resolution_get_image(image_id)- Retrieve image from store with error handling_store_image(image, image_id, save_history)- Store image with undo history_parse_position(pos, ...)- Parse named/percentage/pixel positions_auto_adjust_position(...)- Keep annotations within bounds
Imports
All imports must be at the top of the file. No inline imports inside functions except for platform-specific imports that may fail (e.g., ImageGrab on Linux without display).
Parameter Naming
Do not shadow Python builtins. Use descriptive names:
annotation_typeinstead oftypeimage_formatinstead offormat
Global State
Global state is managed in the storage module. Use the provided functions instead of accessing globals directly:
store_image(image, image_id, save_history)- Store image with undo historyget_image(image_id)- Retrieve image from storeget_next_callout_number()- Get and increment callout counterreset_callout_counter()- Reset callout counter to 0configure_limits(max_images, max_memory_mb, undo_levels)- Configure memory limitsget_limits()- Get current limitsget_total_memory_mb()- Get current memory usage
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 · 80 lines · 0 tokens per session scan A b49754af95c4
mcp-tools is a cursor rule published in the GitHub repository aamar-shahzad/mcp-screenshot-server (4 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 631 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.