Atlas / MCP servers / warpdev / Hub

HubSAFE

mcp/warpdev/hub-1
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
7 7r · 0w · 0d
Transport
stdio · streamable-http
License
MIT
Stars
61
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://cursor.com/install-mcp?name=mcp-hub&config=eyJjb21tYW5kIjoibnB4IC15IG1jcC1odWItbWNwIC0tY29uZmlnLXBhdGggfi8uY3Vyc29yL21jcC1odWIuanNvbiJ9)

[](https://insiders.vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22mcp-hub%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22mcp-hub-mcp%40latest%22%2C%22--config-path%22%2C%22~%2Fmcp-hub.json%22%5D%7D)

A hub server that connects to and manages other MCP (Model Context Protocol) servers.

Overview

This project builds an MCP hub server that connects to and manages multiple MCP (Model Context Protocol) servers through a single interface. It helps prevent excessive context usage and pollution from infrequently used MCPs (e.g., Atlassian MCP, Playwright MCP) by allowing you to connect them only when needed. This reduces AI mistakes and improves performance by keeping the active tool set focused and manageable.

Key Features

  • Automatic connection to other MCP servers via configuration file
  • List available tools on connected servers
  • Call tools on connected servers and return results

Configuration

Add this to your mcp.json:

Using npx

{
"mcpServers": {
"other-tools": {
"command": "npx",
"args": [
"-y",
"mcp-hub-mcp",
"--config-path",
"/Users/username/mcp.json"
]
}
}
}

Installation and Running

Requirements

  • Node.js 18.0.0 or higher
  • npm, yarn, or pnpm

Installation

# Clone repository
git clone 
cd mcp-hub-mcp

# Install dependencies
npm install
# or
yarn install
# or
pnpm install

Build

npm run build
# or
yarn build
# or
pnpm 
Read from source at commit 0519fbd5346cOBSERVED · 2026-10-07
Advertisement
02

Connect

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-code
claude mcp add mcp-hub-mcp -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-hub-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (7)

7 read · 0 write · 0 destructive.

ToolRiskDescription
call-toolread
find-toolsread
find-tools-in-serverread
get-toolread
list-all-toolsread
list-all-tools-in-serverread
list-serversread
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.releaserc.json
.releaserc.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, zod, @semantic-release/changelog, @semantic-release/git, @types/node, semantic-release, typescript
Why it matters. 7 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 0519fbd5346cfull audit observations/trust-audit/mcp-server/warpdev__hub-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-070519fbd5346cSAFEB89first audit
06

Questions

What tools does Hub expose?

7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Hub 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 Hub need?

No credential environment variables were found in its source, so it appears to need none.

How does Hub run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-hub-mcp at 1.3.1.

How current is this page?

The grade is for one exact copy of the source (0519fbd5346c), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement