protogrid

Search / io.github.wowcool/agentsafe

Agent Safe

R2· OAuth, once

Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.

v1.0.0 · active · descriptor JSON · versions

An agent can connect after a one-time OAuth consent by a human.Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.
Quality83good
Trust36of 100
Uptime, 30 days63%
Latency p50183 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "agentsafe": {
      "type": "http",
      "url": "https://agentsafe.locationledger.com/mcp",
      "headers": {
        "skyfire-pay-id": "${SKYFIRE_PAY_ID}"
      }
    }
  }
}
claude mcp add --transport http agentsafe https://agentsafe.locationledger.com/mcp --header "skyfire-pay-id: ${SKYFIRE_PAY_ID}"
[mcp_servers.agentsafe]
url = "https://agentsafe.locationledger.com/mcp"
env_http_headers = { "skyfire-pay-id" = "SKYFIRE_PAY_ID" }
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentsafe": {
      "type": "remote",
      "url": "https://agentsafe.locationledger.com/mcp",
      "enabled": true,
      "headers": {
        "skyfire-pay-id": "{env:SKYFIRE_PAY_ID}"
      }
    }
  }
}
{
  "mcpServers": {
    "agentsafe": {
      "type": "http",
      "url": "https://agentsafe.locationledger.com/mcp",
      "headers": {
        "skyfire-pay-id": "${SKYFIRE_PAY_ID}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agentsafe&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnRzYWZlLmxvY2F0aW9ubGVkZ2VyLmNvbS9tY3AiLCJoZWFkZXJzIjp7InNreWZpcmUtcGF5LWlkIjoiJHtTS1lGSVJFX1BBWV9JRH0ifX0%3D"
}
{
  "servers": {
    "agentsafe": {
      "type": "http",
      "url": "https://agentsafe.locationledger.com/mcp",
      "headers": {
        "skyfire-pay-id": "${SKYFIRE_PAY_ID}"
      }
    }
  }
}
{
  "mcpServers": {
    "agentsafe": {
      "httpUrl": "https://agentsafe.locationledger.com/mcp",
      "headers": {
        "skyfire-pay-id": "${SKYFIRE_PAY_ID}"
      }
    }
  }
}
extensions:
  "agentsafe":
    enabled: true
    name: "agentsafe"
    type: streamable_http
    uri: "https://agentsafe.locationledger.com/mcp"
    headers:
      "skyfire-pay-id": "${SKYFIRE_PAY_ID}"
    timeout: 300

Placeholders to fill from your own secret store: ${SKYFIRE_PAY_ID}. The registry never accepts secret values.

Quality 83 / 100good

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorization83 · weight 15
  • pass
    auth.prmProtected Resource Metadata (RFC 9728) published
  • pass
    auth.as_metadataauthorization server metadata reachable
  • warn
    auth.cimdonly Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-10-19 14:42 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 36 / 100

no-repositoryunreachable
provenance35
liveness0
freshness45
hygiene80

-unreachable(11 failures) -stale-251d -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://agentsafe.locationledger.com/mcp streamable-httpoauth2 AS: https://agentsafe.locationledger.comno (11 failures)63%183 ms–2026-09-24

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.wowcool/agentsafe",
  "title": "Agent Safe",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://agentsafe.locationledger.com/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "skyfire-pay-id",
          "isSecret": true,
          "isRequired": true,
          "description": "Your Skyfire PAY token for payment authentication. Get one at skyfire.xyz. Charged $0.02 per email check."
        }
      ]
    }
  ],
  "version": "1.0.0",
  "description": "Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents."
}