mlawsonking

12 mods across 1 repository, 0 stars between them.

agent-guards

01

mlawsonking/MCP

Plugin Claude Code

Deterministic security checks for coding agents, from the repo that publishes the six agent-guards MCP servers.

0 yesterday A tokens not measured original MIT

agent-guards

02

mlawsonking/MCP

Plugin Claude Code

Deterministic security checks in Claude Code's path: package names before an install, secrets and code rules on what was just written, injection and Unicode-obfuscation patterns in fetched pages. No network call in any hook, no model in any check.

0 yesterday A tokens not measured original MIT

PreToolUse

03

mlawsonking/MCP

Hook

Runs before the agent uses a tool for Bash tool calls, running node. From mlawsonking/MCP.

0 yesterday A tokens not measured original MIT

PostToolUse

04

mlawsonking/MCP

Hook

Runs after a tool call finishes for Edit, Write and WebFetch tool calls, running node (2 commands). From mlawsonking/MCP.

0 yesterday A tokens not measured original MIT

guard

05

mlawsonking/MCP

Skill Claude CodeCodex

Run an agent-guards security check on demand. Use when the user asks to scan a file, directory or diff for secrets, vulnerable code patterns or prompt injection; to check a package before installing it; to look at an .eml file; or to see what the guards have caught (stats). Also use when the user says "/guard".

0 yesterday A 72 tokens original MIT

payment-guard-mcp

06

mlawsonking/MCP

MCP server Claude CodeCodexCursor

Pre-send risk check for AI agents that move money — screen an address or payment URL before sending. Runs locally from the payment-guard-mcp npm package.

0 yesterday A tokens not measured original MIT

agent-firewall-mcp

07

mlawsonking/MCP

MCP server Claude CodeCodexCursor

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets. Runs locally from the agent-firewall-mcp npm package.

0 yesterday A tokens not measured original MIT

agent-guards

08

mlawsonking/MCP

MCP server Claude CodeCodexCursor

All six agent guard suites in one local MCP server, with optional cloud intelligence. Runs locally from the agent-guards npm package.

0 yesterday A tokens not measured original MIT

code-guard-mcp

09

mlawsonking/MCP

MCP server Claude CodeCodexCursor

Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization. Runs locally from the @mlawsonking/code-guard-mcp npm package.

0 yesterday A tokens not measured original MIT

email-guard-mcp

10

mlawsonking/MCP

MCP server Claude CodeCodexCursor

Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks. Runs locally from the email-guard-mcp npm package.

0 yesterday A tokens not measured original MIT

package-guard-mcp

11

mlawsonking/MCP

MCP server Claude CodeCodexCursor

Supply-chain guard for AI coding agents: verify packages, check vulns/malware, detect typosquats. Runs locally from the package-guard-mcp npm package.

0 yesterday A tokens not measured original MIT

web-tools-mcp

12

mlawsonking/MCP

MCP server Claude CodeCodexCursor

10 no-LLM web tools: URL to Markdown, metadata, JSON-LD, MX, scrape, RSS, DNS, RDAP, SSL, HTTP. Runs locally from the web-tools-mcp npm package.

0 yesterday A tokens not measured original MIT