Cited checks for one MCP tool or a tools list, plus a called-or-ignored tally.
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 every tool in a tools/list result or a server card. Returns per-tool findings plus duplicate-name, overlapping-descriptions, and too-many-tools. Those three omit resource. Does not store the tools.
Tools from a tools/list result or a server card. Each item has name, description, and inputSchema.
JSON-RPC tools/list result. Used only when tools is omitted. The array is result.tools.
Check every tool in a tools/list result or a server card. Returns per-tool findings plus duplicate-name, overlapping-descriptions, and too-many-tools. Those three omit resource. Does not store the tools.
| Argument | Type | Description |
|---|---|---|
| tools | array | Tools from a tools/list result or a server card. Each item has name, description, and inputSchema. |
| result | object | JSON-RPC tools/list result. Used only when tools is omitted. The array is result.tools. |
{
"type": "object",
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object"
},
"description": "Tools from a tools/list result or a server card. Each item has name, description, and inputSchema."
},
"result": {
"type": "object",
"description": "JSON-RPC tools/list result. Used only when tools is omitted. The array is result.tools."
}
}
}Check one MCP tool name, description, and input schema against Toolcard cited rules. Returns findings. A finding with an answer page includes resource, a toolcard://answers URI to pass to resources/read. Does not store the tool.
| Argument | Type | Description |
|---|---|---|
| name* | string | Tool name, for example manage_user |
| description | string | Description shown to the model |
| inputSchema | object | JSON Schema object for the tool arguments |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Tool name, for example manage_user"
},
"description": {
"type": "string",
"description": "Description shown to the model"
},
"inputSchema": {
"type": "object",
"description": "JSON Schema object for the tool arguments"
}
}
}Return the anonymous tally of called versus ignored reports on this server. Not a representative sample.
No arguments.
{
"type": "object",
"properties": {}
}Record whether an agent called or ignored a tool. Stores the name, a SHA-256 of the description, and the result. Does not store the raw description.
| Argument | Type | Description |
|---|---|---|
| name* | string | Tool name that was offered to the agent |
| client | string | Optional short label such as cursor. No account ids. |
| result* | string | Whether an agent called the tool |
| report_id | string | Optional idempotency key, 8 to 80 letters, digits, underscore or hyphen |
| description | string | Hashed with SHA-256 and not stored |
{
"type": "object",
"required": [
"name",
"result"
],
"properties": {
"name": {
"type": "string",
"description": "Tool name that was offered to the agent"
},
"client": {
"type": "string",
"description": "Optional short label such as cursor. No account ids."
},
"result": {
"enum": [
"called",
"ignored"
],
"type": "string",
"description": "Whether an agent called the tool"
},
"report_id": {
"type": "string",
"description": "Optional idempotency key, 8 to 80 letters, digits, underscore or hyphen"
},
"description": {
"type": "string",
"description": "Hashed with SHA-256 and not stored"
}
}
}