Scan two public MCP servers for tool poisoning
Check what two public MCP servers tell AI agents before you connect to them. This example connects to the DeepWiki and Cloudflare Docs MCP servers, reads every tool, prompt and resource definition, and flags tool poisoning: hidden instructions in the metadata that agents read and obey but people never see. Add your own server URLs to audit them.
Input
Output fields
Sign up on Apify or log in
The MCP Tool Poisoning Scanner: Audit MCP Servers for Agent Attacks Actor is ready to run with the inputs already set for "Scan two public MCP servers for tool poisoning". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "Scan two public MCP servers for tool poisoning" task
The MCP Tool Poisoning Scanner: Audit MCP Servers for Agent Attacks Actor will start running based on the input automatically. You can also change all the input fields, like MCP server URLs and detect silent changes (rug pulls), to match your specific use case.
Receive the "Scan two public MCP servers for tool poisoning" output
Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as server, name, tools, and more.
Integrate into your workflow
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Scan two public MCP servers for tool poisoning" task via API.

Integrate "Scan two public MCP servers for tool poisoning" into your workflow
Connect "Scan two public MCP servers for tool poisoning" with 100+ integrations, or run it via API or MCP.
Webhook
n8n
Make
Zapier
Airbyte
Keboola
IFTTT
Hubspot
GDrive
Gmail
Apify MCP
GitHub
Slack
LangChain
LlamaIndex
Flowise
Pinecone
OpenAI
Mastra
Clay