Security & Testing
verifymcp.io
Provides security and trust assessments for MCP servers, including scores, malware listings, and comparisons.
ENDPOINT 1
https://mcp.verifymcp.io
MCP server metadata
- Name
- mcp
- Version
- 1.0.0
VerifyMCP publishes independent trust scores for MCP servers. Find servers with list_servers (name, ecosystem, product or score); list_products has the product slugs. Use get_server before installing or trusting one: score with per-category verdicts, any malware finding, the tools it exposes with their context cost, and recent changes. Then get_server_diagnostics for the evidence behind a weak score, get_server_comparison or get_server_alternatives to choose between candidates, get_server_tools for a truncated tool list, get_server_install_config once decided, and list_known_malware for everything flagged. A verdict of "unverified" means a check could not be completed. It is not a failure, and should not be reported as one.
Known tools 9
get_serverGet the full VerifyMCP trust report for one MCP server: score with per-category verdicts and reasons, the tools it exposes with their context-token cost, and its recent change history.
Inferred read-onlyget_server_comparisonCompare up to 5 MCP servers side by side: trust scores, per-category breakdown, tool counts and context-token cost.
Inferred read-onlylist_productsList the products MCP servers integrate with, such as github or notion, and how many servers cover each.
Inferred read-onlylist_known_malwareList MCP server components carrying a supply-chain malware finding.
Inferred read-onlyget_server_alternativesOther MCP servers doing a similar job to a given one, with their trust scores.
Inferred read-onlyget_server_diagnosticsThe evidence behind one server's score: TLS, DNSSEC, authorization, redirects, transports, provenance, install scripts, known CVEs and dependency health.
Inferred read-onlyget_server_install_configReady-to-paste install snippets for one MCP server, for every client we support.
Inferred read-onlyget_server_toolsEvery tool one MCP server exposes, with its parameters, output schema and context-token cost.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://mcp.verifymcp.io"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://mcp.verifymcp.io"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: mcp
Remote MCP URL: https://mcp.verifymcp.io
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.verifymcp.io"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.verifymcp.io"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "mcp",
"transport": "streamable-http",
"url": "https://mcp.verifymcp.io"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.