Mcp Safeguard

com.cognivatorsPublished by cognivators.comv0.3.2Updated Oct 24, 2026

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

The publisher's own server: Safeguard

VerifiedSTDIODesktop onlySecurity & Monitoring

Overview

AI-generated overview

A local MCP server that scans MCP servers for security problems such as prompt injection, credential leaks, SSRF and tool poisoning.

What you can do
Scan MCP servers for prompt injection and tool poisoning risks, based on the registry description. Detect credential leaks and SSRF issues in server configurations. Runs as a local process on the user's machine over stdio; no tool list is published, so the exact scanning commands are not documented here.
When to use it
Worth considering when you are evaluating or installing third-party MCP servers and want a security check before trusting them with credentials or data.
Requirements
A local Python runtime able to install the mcp-safeguard package from PyPI; runs as a stdio process on a desktop machine. No authentication, environment variables or headers are declared.
Before you install
The tool list and documentation are not published, so what it scans and what it reports cannot be verified from this entry. It is a scanner, not a guarantee: findings may be incomplete, and it does not replace reviewing a server's permissions yourself.

Installation

In SourceWeft

  1. Open Mcp Safeguard in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.2LatestSep 16, 2026

Score

15% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Safeguard integrations

Safeguard

sh.safeguardOfficial publisher

Remote MCP server from Safeguard that gives an assistant access to software supply chain security data: SBOMs, vulnerabilities, fixes, policies and compliance.

Streamable HTTPWeb executableAuth
Security & MonitoringCredential requiredOct 27, 2026