TrustScan MCP
TrustScan is a security scanner for MCP servers and AI skills that detects invisible Unicode prompt-injection, dangerous code patterns, hardcoded secrets, and typosquat package names to provide a trust score before trusting an agent.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://trust-scan-production.up.railway.app/mcp/What its tools do
4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (2)
Not annotated (2)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Security scan an MCP server or skill package before trusting it
- Security scan a single file for invisible Unicode, dangerous patterns, and secrets
- Run typosquat check when package_name is given
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- trust-scan 4.1.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 4 advertised
- Resources
- 1 advertised
- Resource templates
- 0 advertised
- Prompts
- 0 advertised
{
"tools": {
"listChanged": true
},
"logging": {},
"prompts": {
"listChanged": true
},
"resources": {
"subscribe": false,
"listChanged": true
}
}Tools
4 advertised
trust_scan_server — Scan MCP Server or Skill Package
Security-scan an MCP server or skill package before trusting it. Runs all four checks — invisible Unicode prompt-injection, dangerous code patterns (MCP001–006), hardcoded secrets, typosquat package names — and returns a 0-100 score, letter grade, and detailed findings. Run this on any directory BEFORE wiring it into your agent. Read-only: never modifies the scanned target.
{
"type": "object",
"required": [
"path"
],
"properties": {
"path": {
"type": "string",
"description": "directory or file path to scan (on the TrustScan host)"
},
"package_name": {
"type": "string",
"default": "",
"description": "package name for typosquat detection (e.g. \"mcp-server\")"
}
},
"additionalProperties": false
}{
"type": "object",
"additionalProperties": true
}{
"title": "Scan MCP Server or Skill Package",
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}trust_scan_file — Scan Single File
Security-scan a single file for invisible Unicode, dangerous patterns, and secrets. Returns a severity-weighted score and per-finding detail (rule, severity, location). Read-only: the file is never modified.
{
"type": "object",
"required": [
"filepath"
],
"properties": {
"filepath": {
"type": "string",
"description": "absolute path of the file to scan"
}
},
"additionalProperties": false
}{
"type": "object",
"additionalProperties": true
}{
"title": "Scan Single File",
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}skills_list_tool — Skills List Tool
List this product's skills. Each entry carries the SKILL.md URI, its name and description, verbatim frontmatter, and a per-file sha256 manifest. Read a body with `read_skill`.
{
"type": "object",
"properties": {},
"additionalProperties": false
}{
"type": "object",
"additionalProperties": true
}read_skill — Read Skill
Read a product skill file by its skill:// URI.
{
"type": "object",
"required": [
"uri"
],
"properties": {
"uri": {
"type": "string",
"description": "e.g. skill://<product>/<skill-name>/SKILL.md\n Get valid URIs from `skills_list_tool`."
}
},
"additionalProperties": false
}{
"type": "object",
"additionalProperties": true
}Prompts
0 advertised
Resources
1 advertised
trust-scan
Use before installing or trusting an MCP server or a skill package. TrustScan runs four checks — invisible Unicode, dangerous patterns, secrets, and supply-chain signals — on a single file or a whole server/skill package, and returns a verdict. The pre-install gate for anything you did not write yourself.
skill://trust-scan/trust-scan/SKILL.md30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 1602 ms
- 95th percentile latency
- 1602 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 1602 ms · metadata changed · 4 tool(s), 1 resource(s), 0 resource template(s), 0 prompt(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http trustscan-mcp https://trust-scan-production.up.railway.app/mcp/Codex
codex mcp add trustscan-mcp --url https://trust-scan-production.up.railway.app/mcp/Cursor
{
"mcpServers": {
"trustscan-mcp": {
"url": "https://trust-scan-production.up.railway.app/mcp/"
}
}
}Cline
{
"mcpServers": {
"trustscan-mcp": {
"type": "streamableHttp",
"url": "https://trust-scan-production.up.railway.app/mcp/",
"disabled": false
}
}
}VS Code
{
"servers": {
"trustscan-mcp": {
"type": "http",
"url": "https://trust-scan-production.up.railway.app/mcp/"
}
}
}Gemini CLI
gemini mcp add --transport http trustscan-mcp https://trust-scan-production.up.railway.app/mcp/Claude Desktop
https://trust-scan-production.up.railway.app/mcp/Windsurf
{
"mcpServers": {
"trustscan-mcp": {
"serverUrl": "https://trust-scan-production.up.railway.app/mcp/"
}
}
}Let your agent find its tools
Find servers like TrustScan MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.