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/piyushptiwari1/mcpkernel/mcpkernel-securitygit clone --depth 1 https://github.com/piyushptiwari1/mcpkernelWhat 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 | $0.00000 | $0.00386 |
| Opus 5 | $0.00000 | $0.00193 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
mcpkernel-security 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
MCPKernel Security Rules
Tool Call Safety
- Never pass raw user input directly to tool calls without sanitization
- Always validate tool arguments against expected types and ranges
- Block tool calls that access sensitive files (.env, .pem, .key, credentials)
- Sandbox all code execution tools — never run on the host directly
Policy Configuration
- Define YAML policies in
policies/directory - Each rule needs: id, name, action (allow/deny/log), and tool_patterns
- Map rules to OWASP ASI 2026 categories (ASI-01 through ASI-08)
- Use
arg_patternswith regex to match dangerous argument values
Taint Tracking
- Mark all external inputs (user prompts, API responses) as tainted
- Track taint labels: SECRET, PII, USER_INPUT across tool boundaries
- Block tainted data from reaching sensitive sinks (network, file write)
- Use FULL taint mode in production, LIGHT for development
Audit & Compliance
- Enable DEE (Deterministic Execution Envelopes) for audit trails
- Every tool execution should be replayable with cryptographic verification
- Export audit logs in CEF format for SIEM integration
- Verify audit log integrity before compliance reporting
Agent Integration
- Use
mcpkernel serveas a proxy between agent and MCP tool servers - Configure via
mcpkernel.yamlat project root - Test policies with
mcpkernel validate-policy <file> - Scan Python files for taint issues with
mcpkernel scan <file>
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 · 38 lines · 0 tokens per session scan A e145c451ff25
mcpkernel-security is a cursor rule published in the GitHub repository piyushptiwari1/mcpkernel (2 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 386 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
agenthound-harness
AgentHound compatibility harness project guidance.
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.