INDIVIDUAL MCP TOOL
compare_tools
Put 2 to 5 products side by side: overall score, coverage and each criterion of their primary surface.
LIVE ENDPOINT
https://agentsco.re/mcp
Connect to this endpoint to inspect the live schema for compare_tools and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT 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.agentscore]
url = "https://agentsco.re/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agentscore": {
"type": "http",
"url": "https://agentsco.re/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agentscore
Remote MCP URL: https://agentsco.re/mcp
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": {
"agentscore": {
"url": "https://agentsco.re/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agentscore": {
"type": "http",
"url": "https://agentsco.re/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agentscore",
"transport": "streamable-http",
"url": "https://agentsco.re/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
list_categories— List the API categories AgentScore ranks (e.g.get_category_ranking— Rank every API surface of one category by its AgentScore (0-100, higher is better for an agent).get_tool— Full record of one product: every API surface, its overall score, coverage, per-criterion scores, measurement date and docs URL.search_tools— Find products by name, category or description keyword (case-insensitive), e.g.