Score any remote MCP server for Claude, ChatGPT, Gemini and MCP Registry readiness.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Check a public remote MCP server URL (Streamable HTTP) for readiness for the Claude Directory, ChatGPT Apps, Gemini Connected Apps and the MCP Registry. Returns the 0-100 score, A-F grade, readiness per store, every failing or warning check with its fix, the report URL and README badge markdown. Results are cached for 10 minutes; set fresh to true to force a new check.
The https URL of the MCP endpoint, for example https://example.com/mcp
Run a new check even when a result from the last 10 minutes exists. Default false.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http mcpstamp-check https://mcp.zovo.one/stamp/mcp
Tool list last changed Nov 2, 2026.
Check a public remote MCP server URL (Streamable HTTP) for readiness for the Claude Directory, ChatGPT Apps, Gemini Connected Apps and the MCP Registry. Returns the 0-100 score, A-F grade, readiness per store, every failing or warning check with its fix, the report URL and README badge markdown. Results are cached for 10 minutes; set fresh to true to force a new check.
| Argument | Type | Description |
|---|---|---|
| url* | string | The https URL of the MCP endpoint, for example https://example.com/mcp |
| fresh | boolean | Run a new check even when a result from the last 10 minutes exists. Default false. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The https URL of the MCP endpoint, for example https://example.com/mcp"
},
"fresh": {
"type": "boolean",
"description": "Run a new check even when a result from the last 10 minutes exists. Default false."
}
},
"additionalProperties": false
}Explain one McpStamp Check rule by its id (for example tool_annotations or auth_prm): what it tests, why stores need it, which stores it blocks, its weight and the store or spec documents it comes from. Use it after check_mcp_server to understand a failing check.
| Argument | Type | Description |
|---|---|---|
| check_id* | string | Check id from a check_mcp_server result. |
{
"type": "object",
"required": [
"check_id"
],
"properties": {
"check_id": {
"enum": [
"https",
"initialize",
"protocol_version",
"content_type",
"jsonrpc_errors",
"get_stream",
"latency",
"server_info",
"instructions",
"capabilities_tools",
"auth_method",
"auth_challenge",
"auth_prm",
"auth_resource",
"auth_as_metadata",
"auth_gemini_discovery",
"auth_chatgpt_metadata",
"auth_pkce",
"auth_registration",
"auth_refresh",
"tools_list",
"tool_schema",
"tool_names",
"tool_annotations",
"tool_open_world",
"tool_titles",
"tool_descriptions"
],
"type": "string",
"description": "Check id from a check_mcp_server result."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
{
"type": "object",
"required": [
"check_id"
],
"properties": {
"check_id": {
"enum": [
"https",
"initialize",
"protocol_version",
"content_type",
"jsonrpc_errors",
"get_stream",
"latency",
"server_info",
"instructions",
"capabilities_tools",
"auth_challenge",
"auth_prm",
"auth_resource",
"auth_as_metadata",
"auth_pkce",
"auth_registration",
"auth_refresh",
"tools_list",
"tool_schema",
"tool_names",
"tool_annotations",
"tool_open_world",
"tool_titles",
"tool_descriptions"
],
"type": "string",
"description": "Check id from a check_mcp_server result."
}
},
"additionalProperties": false
}{
"type": "object",
"required": [
"check_id"
],
"properties": {
"check_id": {
"enum": [
"https",
"initialize",
"protocol_version",
"content_type",
"jsonrpc_errors",
"get_stream",
"latency",
"server_info",
"instructions",
"capabilities_tools",
"auth_method",
"auth_challenge",
"auth_prm",
"auth_resource",
"auth_as_metadata",
"auth_gemini_discovery",
"auth_chatgpt_metadata",
"auth_pkce",
"auth_registration",
"auth_refresh",
"tools_list",
"tool_schema",
"tool_names",
"tool_annotations",
"tool_open_world",
"tool_titles",
"tool_descriptions"
],
"type": "string",
"description": "Check id from a check_mcp_server result."
}
},
"additionalProperties": false
}