Developer Tools

cracked.ai

It routes AI agents to thousands of tools and data endpoints with measured success rates, latency, and pricing.

x402 supported2 endpoints8 known toolsFirst detected September 3, 2026Last detected September 15, 2026

ENDPOINT 1

https://cracked.ai/mcp

Auth required

Known tools 0

No tool metadata was available in the registry cache.

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.cracked-ai]
url = "https://cracked.ai/mcp"
enabled = true
bearer_token_env_var = "MCP_BEARER_TOKEN"

Authentication is required. Replace the placeholder locally and never commit a secret.

Claude Code

.mcp.json

{
  "mcpServers": {
    "cracked-ai": {
      "type": "http",
      "url": "https://cracked.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_BEARER_TOKEN"
      }
    }
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Claude Desktop

Settings → Connectors → Add custom connector

Name: cracked-ai
Remote MCP URL: https://cracked.ai/mcp

Add the URL as a custom connector, then complete its supported authorization flow. Claude Desktop remote connectors are configured in the UI.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "cracked-ai": {
      "url": "https://cracked.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_BEARER_TOKEN"
      }
    }
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Visual Studio Code

.vscode/mcp.json

{
  "servers": {
    "cracked-ai": {
      "type": "http",
      "url": "https://cracked.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${input:mcp-token}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "mcp-token",
      "description": "cracked-ai bearer token",
      "password": true
    }
  ]
}

Authentication is required. Replace the placeholder locally and never commit a secret.

Generic MCP

Client-specific MCP configuration

{
  "name": "cracked-ai",
  "transport": "streamable-http",
  "url": "https://cracked.ai/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_BEARER_TOKEN"
  }
}

Authentication is required. Replace the placeholder locally and never commit a secret.

MCP Inspector

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

ENDPOINT 2

https://cracked.ai/mcp/public

No auth detected

MCP server metadata

Name: cracked-public
Version: 0.6.0

Capabilities

tools.listChanged

Server instructions

This is the public Cracked server: discover_tools and inspect_tool are free with no account. Your first call is your signup: run_tool or run_capability with no key creates a workspace for you with $2 of trial credit, runs the request and returns onboarding.key once; store it as CRACKED_API_KEY and connect to /mcp with Authorization: Bearer <key> for every later call (never run keyless twice). register_agent does the signup without a run. bounty_program explains how to earn credit; recruit_agent returns an onboarding prompt for another agent (pass your referral code as ref: $5 of credit to both sides per claimed workspace).

Known tools 8

discover_tools

Search 71,000+ tools and data endpoints in natural language.

Inferred read-only

inspect_tool

Input schema, price, health and docs for one endpoint.

Inferred read-only

verify_receipt

Verify a signed Cracked receipt (proof of work for one run: tool, hashes of input and output, status, latency, price, timestamp; never the data).

Inferred read-only

run_tool

Run an endpoint with no key.

Inferred read-only

run_capability

Run a capability (instagram-profile, web-search, youtube-transcript, ...) with no key.

Inferred read-only

register_agent

Create a Cracked workspace for this agent right now.

Potential side effects

recruit_agent

A ready-to-paste onboarding prompt for another agent: register (POST /v1/agents/register), first run, claim link flow.

Potential side effects

bounty_program

The bounty program: credit for referrals, backlinks, listings, tool requests and run feedback.

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.cracked-public]
url = "https://cracked.ai/mcp/public"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "cracked-public": {
      "type": "http",
      "url": "https://cracked.ai/mcp/public"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: cracked-public
Remote MCP URL: https://cracked.ai/mcp/public

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": {
    "cracked-public": {
      "url": "https://cracked.ai/mcp/public"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "cracked-public": {
      "type": "http",
      "url": "https://cracked.ai/mcp/public"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "cracked-public",
  "transport": "streamable-http",
  "url": "https://cracked.ai/mcp/public"
}

MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

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