Live public MCP Index. Search, recommend, and call healthy MCP servers.
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.
Run a tool on a public MCP server from the full AgentStatus Index. This connection does not list those servers. Call search_records or recommend_records first, then pass that slug and tool. The call is sent to that server and its result is returned here.
Index slug, such as trip-logistics.
Tool name on that server.
Arguments for that tool.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http mcp-index https://index.mcp.agentstatus.dev/mcp
Run a tool on a public MCP server from the full AgentStatus Index. This connection does not list those servers. Call search_records or recommend_records first, then pass that slug and tool. The call is sent to that server and its result is returned here.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Index slug, such as trip-logistics. |
| tool* | string | Tool name on that server. |
| arguments | object | Arguments for that tool. |
{
"type": "object",
"required": [
"slug",
"tool"
],
"properties": {
"slug": {
"type": "string",
"description": "Index slug, such as trip-logistics."
},
"tool": {
"type": "string",
"description": "Tool name on that server."
},
"arguments": {
"type": "object",
"description": "Arguments for that tool.",
"additionalProperties": true
}
}
}Compare two to five directory items by id, slug, or exact name. Returns stored details and the fields that differ.
| Argument | Type | Description |
|---|---|---|
| records* | array | Two to five record ids, slugs, or exact titles. |
{
"type": "object",
"required": [
"records"
],
"properties": {
"records": {
"type": "array",
"items": {
"type": "string"
},
"example": [
"ipnex",
"remember-me-collections"
],
"maxItems": 5,
"minItems": 2,
"description": "Two to five record ids, slugs, or exact titles."
}
}
}Look up one directory item by id, slug, or exact name.
| Argument | Type | Description |
|---|---|---|
| id* | string | Record id, slug, or exact title. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"example": "ipnex",
"description": "Record id, slug, or exact title."
}
}
}Show the sections in MCP for AgentStatus MCP Index.
No arguments.
{
"type": "object",
"properties": {}
}Pick public MCP servers from the full Index for a need. Each line names the slug and tool to pass to call_indexed_tool. Search here before calling a server.
| Argument | Type | Description |
|---|---|---|
| host | string | Optional product host, same as search_records: cursor, copilot, vscode. |
| need* | string | What the agent is looking for. |
| limit | integer | How many recommendations to return. Default 5, maximum 10. |
| status | string | Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated. |
| section | string | Optional section or partial section name. |
{
"type": "object",
"required": [
"need"
],
"properties": {
"host": {
"type": "string",
"description": "Optional product host, same as search_records: cursor, copilot, vscode."
},
"need": {
"type": "string",
"example": "remember me collections",
"description": "What the agent is looking for."
},
"limit": {
"type": "integer",
"description": "How many recommendations to return. Default 5, maximum 10."
},
"status": {
"enum": [
"operational",
"degraded",
"down",
"auth_required",
"unrated"
],
"type": "string",
"description": "Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated."
},
"section": {
"type": "string",
"description": "Optional section or partial section name."
}
}
}Search the full public MCP Index. The tools on this connection are only the Index, not the catalog. Pass the job as query. Optional host is cursor, copilot, or vscode. Each match includes a slug and tool names. Run one with call_indexed_tool.
| Argument | Type | Description |
|---|---|---|
| host | string | Optional product host, same as the public Index query: cursor, copilot, vscode. |
| limit | integer | How many matches to return. Default 20, maximum 50. |
| query | string | Words an agent would type. Empty returns the directory in stored order. |
| offset | integer | How many matches to skip. |
| status | string | Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated. |
| section | string | Section name from list_sections. Partial names match. |
{
"type": "object",
"properties": {
"host": {
"type": "string",
"description": "Optional product host, same as the public Index query: cursor, copilot, vscode."
},
"limit": {
"type": "integer",
"description": "How many matches to return. Default 20, maximum 50."
},
"query": {
"type": "string",
"example": "remember me collections",
"description": "Words an agent would type. Empty returns the directory in stored order."
},
"offset": {
"type": "integer",
"description": "How many matches to skip."
},
"status": {
"enum": [
"operational",
"degraded",
"down",
"auth_required",
"unrated"
],
"type": "string",
"description": "Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated."
},
"section": {
"type": "string",
"description": "Section name from list_sections. Partial names match."
}
}
}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 Oct 31, 2026.