← sentinelsignal.io

INDIVIDUAL MCP TOOL

get_drift_report

Agent Sprawl Radar: return agent drift events across latest snapshots.

sentinelsignal.ionone authenticationAvailability not checked

LIVE ENDPOINT

https://verify.sentinelsignal.io/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_drift_report 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

sentinelsignal.io

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.mcp-verify]
url = "https://verify.sentinelsignal.io/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "mcp-verify": {
      "type": "http",
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: mcp-verify
Remote MCP URL: https://verify.sentinelsignal.io/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": {
    "mcp-verify": {
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "mcp-verify": {
      "type": "http",
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "mcp-verify",
  "transport": "streamable-http",
  "url": "https://verify.sentinelsignal.io/mcp"
}
MCP Inspector

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

Related tools

  • search — ChatGPT-compatible read-only search alias.
  • fetch — ChatGPT-compatible read-only fetch alias.
  • search_servers — Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.
  • recommend_servers — Recommend MCP servers for a plain-language task and return ranked matches with install config.
  • get_server_report — Return the full machine-readable verify report for a specific MCP server identifier.
  • compare_servers — Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.
  • route_task — Choose the best MCP server/tools for a task.
  • decide_agent_call — Verify Gateway decision point.