MCP Tool Poisoning Scanner

io.github.marcepalacios12Published by GitHub account marcepalacios12v1.1.0Updated Oct 29, 2026

Scan MCP servers for tool poisoning, hidden instructions and silent tool changes. Runs on Apify.

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

Remote Apify-hosted scanner that checks MCP servers for tool poisoning, hidden instructions and silent tool changes.

What you can do
  • Scan MCP servers for tool poisoning and hidden instructions embedded in tool descriptions.
  • Detect silent changes to a server's tools between checks.
  • Run the scans through an Apify-hosted remote endpoint rather than locally.
  • No individual tools are listed in the manifest, so the exact operations are not documented here.
When to use it
Useful when vetting third-party MCP servers before adding them to an assistant, or when re-checking a server you already use to see whether its tools changed unexpectedly.
Requirements
A remote MCP endpoint at mcp.apify.com over streamable HTTP. Authentication is required via OAuth or an Authorization header carrying an Apify API token, obtained from the Apify console. An Apify account is implied.
Before you install
The server requires an Apify API token as a bearer credential in the Authorization header; treat it as a secret and grant only the access needed. Scan targets and results are processed by Apify's hosted service, a third party. No tool list is published, so review what it does before running it against internal servers.

Installation

In SourceWeft

  1. Open MCP Tool Poisoning Scanner in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.marcepalacios12%2Fmcp-poisoning-scanner/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "tool-poisoning-scanner": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=bigochelo/mcp-poisoning-scanner"
    }
  }
}

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.1.0LatestOct 29, 2026

Score

67% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

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

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

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

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.