MCP ToolsSAFE
A command-line interface for interacting with MCP (Model Context Protocol) servers using both stdio and HTTP transport.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Swiss Army Knife for MCP Servers
A comprehensive command-line interface for interacting with MCP (Model Context Protocol) servers.
Discover, call, and manage tools, resources, and prompts from any MCP-compatible server.
Supports multiple transport methods, output formats, and includes powerful mock and proxy server capabilities.
[](https://blog.fka.dev/blog/2025-03-27-mcp-inspector-vs-mcp-tools/)
Table of Contents
- Overview
- Difference Between the MCP Inspector and MCP Tools
- Installation
- Using Homebrew
- From Source
- Getting Started
- Features
- Transport Options
- Output Formats
- Commands
- Interactive Shell
- Web Interface
- Project Scaffolding
- Server Aliases
- LLM Apps Config Management
- Server Modes
- Mock Server Mode
- Proxy Mode
- Guard Mode
- Examples
- Basic Usage
- Script Integration
- Debugging
- Contributing
- Roadmap
- License
Overview
MCP Tools provides a versatile CLI for working with Model Context Protocol (MCP) servers. It enables you to:
- Discover and call tools provided by MCP servers
- Access and utilize resources exposed by MCP servers
- Create mock servers for testing client applications
- Proxy MCP requests to shell
c8aa030f2cc1OBSERVED · 2026-09-24Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add PROJECT_NAME -- npx -y [email protected]
{
"mcpServers": {
"PROJECT_NAME": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
TOOL_NAME | read | TOOL_DESCRIPTION |
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 | PASS |
| 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
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.gitmessage
.golangci.yml
.goreleaser.yml
@modelcontextprotocol/sdk, zod, express, @types/node, @types/express, typescript
.github/resources/screenshot.png
Gates applied: no_behavioural_pass.
c8aa030f2cc1full audit observations/trust-audit/mcp-server/f__mcp-tools-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-24 | c8aa030f2cc1 | SAFE | B | 89 | source changed, verdict held |
Questions
What is the MCP Tools MCP server?
A command-line interface for interacting with MCP (Model Context Protocol) servers using both stdio and HTTP transport.
What tools does MCP Tools expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is MCP Tools safe to connect to an agent?
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 server reads B.
What credentials does MCP Tools need?
No credential environment variables were found in its source, so it appears to need none.
How does MCP Tools run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as PROJECT_NAME at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (c8aa030f2cc1), read on 2026-09-24. The repository is watched and re-audited when it changes.