Golem Defender is answering right now. Last checked 2 min ago.
Ledger reads, findings and shadow rules for agents that defend a coding-agent fleet.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add defender --transport http https://context.golem.team/defender
https://context.golem.team/defender
[mcp_servers.defender]
url = "https://context.golem.team/defender"
{
"mcpServers": {
"defender": {
"url": "https://context.golem.team/defender"
}
}
}
{
"servers": {
"defender": {
"type": "http",
"url": "https://context.golem.team/defender"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://context.golem.team/defender | streamable-http | answering | 242 ms | 2 min ago |
A .NET architecture checker that enforces one C# spec and renders the same rules for coding agents.
Impact analysis, architecture rules and a tamper-evident ledger for AI coding agents.
Governed skills, rules and commands for AI coding agents, served by a read-only MCP server.
Merget for coding agents: set up the merge queue, operate it, and read its findings and code graphs.
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
Checks the context files a coding agent reads against the git index, and reports what drifted.
Local code-quality rules, findings, preview-first safe fixes and gate results for coding agents.
The WunderUI design system for coding agents: components, props, tokens, rules and skills.
Answers built from our own checks of this server.