Developer Tools

crawldex.com

Provides preflight checks and scoring for agent tasks on websites.

1 endpoint13 known toolsFirst detected June 26, 2026Last detected September 15, 2026

ENDPOINT 1

https://crawldex.com/mcp

No auth detected

MCP server metadata

Name: crawldex
Version: 0.1.0

Capabilities

tools

Known tools 13

get_trust_record

Call BEFORE an agent attempts any public website task to retrieve the Agent Trust Record verdict, confidence, blockers, user-present requirements, evidence links, and dispute link.

Inferred read-only

check_site_task

Alias for preflight.

Inferred read-only

get_agent_blockers

Call this BEFORE browser execution when a site-task may involve login, checkout, cancellation, refund, form submission, booking, support, or account changes.

Potential side effects

get_success_signals

Call this BEFORE and DURING a website task to know which public success signals and guardrails prove the agent is still on the right route.

Inferred read-only

get_scoring_rubric

Call this when an agent or developer needs to justify CrawlDex verdicts.

Inferred read-only

preflight

Call this BEFORE attempting any public website task.

Inferred read-only

get_recipe

Call this BEFORE executing a known site-task to fetch recipe hints, guardrails, and success signals if CrawlDex has a known-good route.

Inferred read-only

get_alternatives

Call this when preflight says avoid, user-present, stale, blocked, or low confidence.

Inferred read-only

resolve_intent

Call this FIRST when the user gives a plain-language web task.

Inferred read-only

list_tasks

Call this when an agent needs to discover which website task keys CrawlDex can preflight, optionally by category.

Inferred read-only

describe_task

Call this BEFORE choosing a website for a task.

Inferred read-only

check_protocol_support

Call this before integrating with a site through protocols instead of browser automation.

Inferred read-only

explain_blockers

Call this when preflight returns blockers or a human-present recommendation.

Inferred read-only

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]
url = "https://crawldex.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "crawldex": {
      "type": "http",
      "url": "https://crawldex.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: crawldex
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": {
      "url": "https://crawldex.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "crawldex": {
      "type": "http",
      "url": "https://crawldex.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "crawldex",
  "transport": "streamable-http",
  "url": "https://crawldex.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for crawldex.com was fetched 2026-07-28T11:36:41.435Z and is being refreshed.

Trust status Neutral

crawldex.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.