Strawbery Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Strawbery Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP (Model Context Protocol) server that provides a tool to count the correct number of R's in "strawberry".
<img src="docs/images/opencode.png" width="750">
input (string, required): The string to search incharacter (string, required): The single character to count (must be exactly one Unicode rune){
"character": "r",
"input": "strawberry"
}JSON object with:
count (int): Number of occurrencespositions (array of int): 1-indexed positions where the character appears{
"count": 3,
"positions": [
3,
8,
9
]
}{"input": "strawberry", "character": "r"} → {"count": 3, "positions": [3,6,8]}{"input": "你好", "character": "你"} → {"count": 1, "positions": [1]}This server uses SSE for MCP communication.
go run main.godocker build -t strawbery-mcp . && docker run -p 3001:3001 strawbery-mcpAdd to the $.mcp block of your opencode.jsonc
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"strawbery": {
"type": "remote",
"url": "http://localhost:3001/sse",
"enabled": true
}
}
}~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.