SCRIPTMASTERLABS — Cascade Graph is answering right now. Last checked 9 min ago. It exposes 4 tools.
Cascade Graph MCP: macro decision capsules + Jev jury review over a hash-chained calibration log.
Today is the operative word: we check SCRIPTMASTERLABS — Cascade Graph every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add cascade-graph --transport http https://sml-portfolio.onrender.com/mcp
https://sml-portfolio.onrender.com/mcp
[mcp_servers.cascade-graph]
url = "https://sml-portfolio.onrender.com/mcp"
{
"mcpServers": {
"cascade-graph": {
"url": "https://sml-portfolio.onrender.com/mcp"
}
}
}
{
"servers": {
"cascade-graph": {
"type": "http",
"url": "https://sml-portfolio.onrender.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
cascade_analyze
cascade_capsule
cascade_review_jev
cascade_status
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://sml-portfolio.onrender.com/mcp | streamable-http | answering | 229 ms | 9 min ago |
Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained log.
A committed markdown dev log and task graph that agents read and write over MCP.
Persistent memory for AI agents — log and recall conversation context over MCP.
Host, Docker, Compose, SSH, logs, ZFS, and file operations over MCP and CLI.
Code graph MCP: 81 languages, 88 frameworks, 72.7% fewer PR-review tokens, comprehension at parity
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
One number per AI agent: route MCP calls to any agent, every call sealed in an on-chain log.
Answers built from our own checks of this server.