protogrid
Sign inAdd to your agent

Search / org.448c/sentinel

Sentinel

R0· no sign-in

Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.

v0.0.1 · active · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality85good
Trust73of 100
Uptime, 30 days100%
Latency p50523 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "sentinel": {
      "type": "http",
      "url": "https://448c.org/mcp"
    }
  }
}
claude mcp add --transport http sentinel https://448c.org/mcp
[mcp_servers.sentinel]
url = "https://448c.org/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sentinel": {
      "type": "remote",
      "url": "https://448c.org/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "sentinel": {
      "type": "http",
      "url": "https://448c.org/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=sentinel&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vNDQ4Yy5vcmcvbWNwIn0%3D"
}
{
  "servers": {
    "sentinel": {
      "type": "http",
      "url": "https://448c.org/mcp"
    }
  }
}
{
  "mcpServers": {
    "sentinel": {
      "httpUrl": "https://448c.org/mcp"
    }
  }
}
extensions:
  "sentinel":
    enabled: true
    name: "sentinel"
    type: streamable_http
    uri: "https://448c.org/mcp"
    timeout: 300

Quality 85 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations2 of 2 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_address (destructiveHint, idempotentHint); check_url (destructiveHint, idempotentHint)
  • pass
    tools.token_costabout 277 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 277 tokens to load them all · tool set 0b5887645cf2 · checked 2026-10-19 10:20 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 73 / 100

no-repository
provenance45
liveness100
freshness65
hygiene80

+dns-namespace +reachable +uptime-100% ~updated-107d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://448c.org/mcp streamable-httpnoneyes100%523 ms2025-11-252026-10-19

Tools (2)

check_addressread-onlyCheck whether a crypto address is safe to transact with. Screens OFAC sanctions + community scam lists and flags contract-vs-wallet. Returns verdict (safe/caution/avoid), 0-100 risk score, reasons, and sources.
check_urlread-onlyCheck whether a URL or domain is a scam/phishing site. Screens the MetaMask crypto-phishing blocklist, domain age (RDAP), and lexical red flags. Returns verdict (safe/caution/avoid), 0-100 risk score, reasons, and sources.

Schemas: list_tools.

Similar MCP servers

  • amlR0quality 85
    com.oceanalt/aml

    Screen a payee address before an AI agent pays: sanctions, mixers, scam lists, on-chain risk.

  • Token risk x402R0quality 91
    com.ogenalabs/token-risk-x402

    Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.

  • AgentTrust — Pre-Invocation AI Agent Trust & Reliability ChecksR0quality 90
    io.github.agenttrust-ai/agenttrust

    Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

  • vetagentR0quality 88
    dev.vetagent/vetagent

    Pre-trade safety check for AI agents: honeypot, tax, liquidity and rug risk before you buy.

  • safe4R0quality 76
    ai.safe4/safe4

    Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.

  • toolsR0quality 79
    dev.workers.sebastiaan-ba3.mcpgateway/tools

    Doormat Capital's paid x402 safety tools (token scan, HTTP security headers) for AI agents.

Official server.json
{
  "name": "org.448c/sentinel",
  "title": "Sentinel",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://448c.org/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.0.1",
  "description": "Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact."
}