Mcp Grep CodeSAFE
High-performance AI coding agent CLI written in Rust with zero unsafe code
Overview
High-performance AI coding agent CLI written in Rust with zero unsafe code
46a2537504c9OBSERVED · 2026-10-10What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: mcp-grep-code
description: Search real-world code examples from over a million public GitHub repositories. Use when finding code patterns, implementation examples, or how libraries are used in practice. Triggers on "find code examples", "how is [library] used", "search GitHub code", "grep.app search", "code pattern".
---
# Grep.app Code Search
MCP service at `https://mcp.grep.app` (http) with 1 tool.
## Requirements
- `mh` CLI must be installed. If not available, install with:
```bash
curl -fsSL https://raw.githubusercontent.com/vaayne/mcphub/main/scripts/install.sh | sh
```
## Usage
List tools: `mh -u https://mcp.grep.app -t http list`
Get tool details: `mh -u https://mcp.grep.app -t http inspect searchGitHub`
Invoke tool: `mh -u https://mcp.grep.app -t http invoke searchGitHub '{"query": "pattern"}'`
## Notes
- Run `inspect` before invoking unfamiliar tools to get full parameter schema
- Timeout: 30s default, use `--timeout <seconds>` to adjust
- **Important**: This searches for literal code patterns (like grep), NOT keywords
- Use actual code that would appear in files, not descriptions
## Tools
| Tool | Description |
| -------------- | --------------------------------------------------------------------------------------------------------------------------- |
| `searchGitHub` | Find real-world code examples from public GitHub repositories. Searches for literal code patterns across millions of repos. |
## Search Tips
**Good queries** (literal code patterns):
- `useState(`
- `import React from`
- `async function`
- `(?s)try {.*await`
**Bad queries** (keywords - won't work well):
- `react state management`
- `how to use hooks`
## Examples
```bash
# Find useState usage patterns
mh -u https://mcp.grep.app -t http invoke searchGitHub '{"query": "useState("}'
# Find async/await patterns
mh -u https://mcp.grep.app -t http invoke searchGitHub '{"query": "async function fetch"}'
# Find import patterns
mh -u https://mcp.grep.app -t http invoke searchGitHub '{"query": "from \"openai\""}'
```Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
.beads/beads.jsonl
curl -fsSL https://raw.githubusercontent.com/vaayne/mcphub/main/scripts/install.sh | sh
Gates applied: no_behavioural_pass.
46a2537504c9full audit observations/trust-audit/skill/dicklesworthstone__mcp-grep-code.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 46a2537504c9 | SAFE | B | 89 | first audit |
Questions
What does the Mcp Grep Code skill do?
High-performance AI coding agent CLI written in Rust with zero unsafe code
Is Mcp Grep Code safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Mcp Grep Code access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (46a2537504c9), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.