protogrid
Sign inAdd to your agent

Search / team.golem/defender

Golem Defender

R0· no sign-in

Ledger reads, findings and shadow rules for agents that defend a coding-agent fleet.

v2026.10.25 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality88good
Trust82of 100
Uptime, 30 days93%
Latency p50371 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "defender": {
      "type": "http",
      "url": "https://context.golem.team/defender"
    }
  }
}
claude mcp add --transport http defender https://context.golem.team/defender
[mcp_servers.defender]
url = "https://context.golem.team/defender"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "defender": {
      "type": "remote",
      "url": "https://context.golem.team/defender",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "defender": {
      "type": "http",
      "url": "https://context.golem.team/defender"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=defender&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vY29udGV4dC5nb2xlbS50ZWFtL2RlZmVuZGVyIn0%3D"
}
{
  "servers": {
    "defender": {
      "type": "http",
      "url": "https://context.golem.team/defender"
    }
  }
}
{
  "mcpServers": {
    "defender": {
      "httpUrl": "https://context.golem.team/defender"
    }
  }
}
extensions:
  "defender":
    enabled: true
    name: "defender"
    type: streamable_http
    uri: "https://context.golem.team/defender"
    timeout: 300

Quality 88 / 100good

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list carries no ttlMs, so clients re-fetch it
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 hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dump, tools.hidden_texttool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pull, stability.new_linkstool 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 2026-11-14 06:30 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 82 / 100

no-repository
provenance55
liveness97
freshness100
hygiene80

+dns-namespace +website +reachable +uptime-93% +updated-15d-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://context.golem.team/defender streamable-httpnoneyes93%371 ms2026-07-28, 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-052026-11-14

Tools (0)

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

Schemas: list_tools.

Similar MCP servers

  • The Agent CommonsL0
    io.github.startekenterprises-ai/agent-commons

    Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools.

  • protect-contextL0
    io.github.XJTLUmedia/protect-context

    Agent guardrails: contract, evidence ledger, loop brake, diff-scope warnings, durable journal.

  • okl — Observed Knowledge LedgerL0
    io.github.emeraldleaf/okl

    Keeps your agent true to your rules. Keeps them true to the code. Keeps learning as you build.

  • AgentGuard — security checks for AI agentsL0
    io.github.shuaicongxiaomai/agentguard

    Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

  • tracelane-mcpL0
    io.github.tracelane/tracelane-mcp

    Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

  • AgentLensL0
    io.github.agentkitai/agentlens

    Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.

More from team.golem

  • Golem ContextR0quality 88
    team.golem/context

    Read your Golem fleet's ledger from any MCP client: agents' sessions, live activity, signed record.

  • Golem IntelR0quality 88
    team.golem/intel

    Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects to it.

  • Golem SecurityR0quality 88
    team.golem/security

    Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects to it.

Official server.json
{
  "name": "team.golem/defender",
  "icons": [
    {
      "src": "https://golem.team/icon.png",
      "sizes": [
        "512x512"
      ],
      "mimeType": "image/png"
    }
  ],
  "title": "Golem Defender",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://context.golem.team/defender",
      "type": "streamable-http"
    }
  ],
  "version": "2026.10.25",
  "websiteUrl": "https://golem.team/",
  "description": "Ledger reads, findings and shadow rules for agents that defend a coding-agent fleet."
}