SL

SLF Guardian MCP

Pre-action security for coding agents: check packages, commands, code and untrusted prompts before use. Six MCP tools; 1,000 free API calls per key, then $0.01/call.

Grade A Local · stdio API key 6 tools v1.2.2 · 21 Nov 2026 MIT
No reviews yet by slfguardianPyPI 980 Runs on your machine, nothing hosted
100/100
trust score
3
downloads a day
local
runs on your machine
71
downloads in 30d

What it does

SLF Guardian adds six evidence-backed checks to a coding agent workflow, before it acts: check_package checks PyPI/npm dependencies before installation; check_command reviews shell/SQL before execution; audit_code examines source before delivery; check_prompt looks for instruction injection in untrusted text; check_domain checks a domain before opening; scan_site performs a passive outside-in check only for sites you own or are authorized to test. Results are pass, warn, review or block with findings; a pass is not proof of safety. The MCP server runs locally over stdio and calls SLF Guardian API. No submitted code or command is executed. Each API key starts with 1,000 free calls; subsequent calls cost $0.01 each. Rate limit: 20 calls per minute. The host agent must call the tool and honor its result; SLF Guardian is a policy signal, not an enforcement layer.

Quickstart

# 1 — add it to Claude Code claude mcp add --scope user --env 'SLF_API_KEY=${SLF_API_KEY}' --transport stdio slf-guardian-mcp '--' uvx slf-guardian-mcp # 2 — ask your agent for something these tools do # audit_code, check_package, check_prompt and 3 more

It needs SLF_API_KEY: this reads it from your environment, so export it first.

SLF Guardian costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher
SL
slfguardian1 server
1 category
All 1 server
More in this category

See also

See all