Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
ToolTrust Scanner MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
Static security scanner for MCP tool definitions
Once ToolTrust Scanner is connected, these are the calls the assistant has available:
tooltrust_scan_config — Scan all MCP servers in your .mcp.json or ~/.claude.jsontooltrust_scan_server — Launch and scan a specific MCP server by commandtooltrust_scanner_scan — Scan a raw JSON blob of tool definitionstooltrust_lookup — Look up a server's trust grade from the ToolTrust Directorytooltrust_list_rules — List all built-in security rulesBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. ToolTrust Scanner's toolset — tooltrust_scan_config, tooltrust_scan_server, tooltrust_scanner_scan and 2 more — is a fair guide to whether it matches your workflow. It is maintained by AgentSafe-AI; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| tooltrust_scan_config | Scan all MCP servers in your .mcp.json or ~/.claude.json |
| tooltrust_scan_server | Launch and scan a specific MCP server by command |
| tooltrust_scanner_scan | Scan a raw JSON blob of tool definitions |
| tooltrust_lookup | Look up a server's trust grade from the ToolTrust Directory |
| tooltrust_list_rules | List all built-in security rules |
{
"mcpServers": {
"tooltrust": {
"command": "npx",
"args": ["-y", "tooltrust-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.