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/ekakit/lightfast-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/ekakit/lightfast-mcp/server-development-workflow)<a href="https://agentmods.dev/rules/ekakit/lightfast-mcp/server-development-workflow"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/server-development-workflow/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/ekakit/lightfast-mcp/server-development-workflow"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/server-development-workflow.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 | $0.00527 |
| Opus 5.5 | $0.00000 | $0.00211 |
| Sonnet 5.5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
server-development-workflow 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server Development Workflow
When editing MCP server files, follow this workflow:
Immediate Actions After Code Changes
- Run Fast Tests: Execute
nox -s test_fastto get immediate feedback - Lint Check: Run
uv run task lintto catch style issues - Format Code: Run
uv run task formatto ensure consistent formatting
After Adding/Modifying Tools
- Test the Tool: Create a unit test for the new/modified tool
- Validate Tool Description: Ensure tool has clear docstring for AI consumption
- Test Server Startup: Run
uv run lightfast-{server}-serverto verify server starts - Test Tool Integration: Use
uv run lightfast-mcp-orchestrator aito test the tool interactively
Server File Validation Checklist
When editing server implementation files:
- Tool functions use
@mcp.tool()decorator - Tool functions have proper type hints
- Tool functions have descriptive docstrings
- Error handling is implemented for all tools
- Input validation is present for all parameters
- Server inherits from
BaseServer - Configuration follows
ServerConfigpattern
Automatic Commands to Run
# After any server file edit
uv run task lint && uv run task format
nox -s test_fast
# After adding new tools
uv run pytest tests/unit/test_*server*.py -v
uv run lightfast-mock-server & # Test server startup
sleep 2 && pkill -f lightfast-mock-server
# Before committing
nox -s test-3.13 # Full test suite for current Python version
Integration Testing Steps
- Start Test Server:
uv run lightfast-{server}-server - Verify MCP Tools: Check tools appear in Cursor's available tools
- Test Tool Execution: Try calling tools through Cursor chat
- Check Error Handling: Test invalid inputs to ensure graceful failures
Performance Considerations
- Monitor server startup time - should be under 5 seconds
- Test tool response time - most tools should respond under 2 seconds
- Check memory usage during tool execution
- Verify proper cleanup after tool execution
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.
- 2mo ago First seen · 65 lines · 0 tokens per session scan A 55bb84f85020
server-development-workflow is a cursor rule published in the GitHub repository ekakit/lightfast-mcp (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 527 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
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
selectools-providers
Rules for working with LLM provider adapters in selectools.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.