← crawldex.com
INDIVIDUAL MCP TOOL
get_success_signals
Return success signals and guardrails an agent should verify for an origin/task pair.
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 endpoint
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.crawldex-com]
url = "https://crawldex.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"crawldex-com": {
"type": "http",
"url": "https://crawldex.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: crawldex-com
Remote MCP URL: https://crawldex.com/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": {
"crawldex-com": {
"url": "https://crawldex.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"crawldex-com": {
"type": "http",
"url": "https://crawldex.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "crawldex-com",
"transport": "streamable-http",
"url": "https://crawldex.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
check_site_task— Growth-plan alias for preflight: check whether an agent should attempt a task on a site and what will block it.get_agent_blockers— Return observed blocker codes, severity, ownership, and recipe guards for an origin/task pair.get_scoring_rubric— Return the canonical CrawlDex agent experience scoring rubric, including AES bands, freshness gates, confidence gates, friction penalties, and reporting fields.preflight— Check task reliability before an agent attempts a site task; includes reporting guidance for local and hosted submissions.get_recipe— Fetch a known-good or inferred task recipe for an origin/task.get_alternatives— Find alternative origins for a task or natural-language task query.resolve_intent— Resolve a natural-language task query to operating-map task candidates.list_tasks— List compact operating-map task summaries, optionally within one category.