RMCP
Search remote Model Context Protocol servers and tools discovered by BuiltWith, without an API key.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'compare_mcp_servers' description lacks action verbin compare_mcp_servers
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"rmcp": {
"url": "https://rmcp.dev/mcp"
}
}
}Remote endpoints
https://rmcp.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (8)
🟢search_mcp_servers(query, category, transport, authentication, verified_only, ...)
Search indexed remote MCP servers by intended task, capability, product, category, endpoint metadata, or associated tools.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"category": {
"type": "string"
},
"transport": {
"type": "string",
"enum": [
"streamable-http",
"sse"
]
},
"authentication": {
"type": "string"
},
"verified_only": {
"type": "boolean",
"default": false
},
"online_only": {
"type": "boolean",
"default": true
},
"read_only_only": {
"type": "boolean",
"default": false
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢search_mcp_tools(query, authentication, online_only, read_only_only, limit)
Search individual tool capabilities across every indexed MCP server and identify each matching parent server.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"authentication": {
"type": "string"
},
"online_only": {
"type": "boolean",
"default": true
},
"read_only_only": {
"type": "boolean",
"default": false
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 20
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_mcp_server(id)
Get a complete structured server record, endpoints, tools, evidence-based trust, risks, warnings and install options.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢get_mcp_tool(id)
Get one tool schema, parent server, endpoint, availability, inferred risk and parent installation instructions.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟡get_mcp_endpoint(id)
Get stored transport, authentication, protocol, availability, latency, TLS, redirect and schema-change information for an indexed endpoint.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢get_install_instructions(server_id, client, endpoint_index)
Generate client-specific, copyable installation instructions without embedding credentials.
Input Schema
{
"type": "object",
"properties": {
"server_id": {
"type": "string"
},
"client": {
"type": "string",
"enum": [
"codex",
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"generic-mcp"
]
},
"endpoint_index": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"required": [
"server_id",
"client"
],
"additionalProperties": false
}🟢check_mcp_endpoint(id)
Return the most recently stored check for an indexed endpoint. This never scans an arbitrary URL.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}⚪compare_mcp_servers(ids, query)
Compare two to four known RMCP servers by capabilities, tools, auth, transport, evidence, risk, latency and installation complexity.
Input Schema
{
"type": "object",
"properties": {
"ids": {
"type": "array",
"minItems": 2,
"maxItems": 4,
"items": {
"type": "string"
}
},
"query": {
"type": "string",
"description": "Optional intended capability used to select relevant tools."
}
},
"required": [
"ids"
],
"additionalProperties": false
}Community
Evidence