tibet-triage-mcp
MCP server for tibet-triage — process triage, flare rescue & reproducibility bundles with TIBET provenance.
README
tibet-triage-mcp
MCP server for tibet-triage — process triage, flare rescue & reproducibility bundles with TIBET provenance.
Run commands in airlock sandboxes, rescue crashed APIs with GPU flare nodes, and bundle team work into verified archives. Every decision is signed with TIBET tokens.
Part of the TIBET ecosystem by HumoticaOS.
Install
pip install tibet-triage-mcp
Claude Code / Claude Desktop Config
{
"mcpServers": {
"triage": {
"command": "tibet-triage-mcp",
"env": {
"IPOLL_URL": "https://brein.jaspervandemeent.nl/api/ipoll"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
triage_run |
Execute command in airlock sandbox with risk evaluation |
triage_pending |
List items awaiting human decision |
triage_review |
Review a triage evidence bundle |
triage_approve |
Approve a pending bundle |
triage_reject |
Reject a pending bundle |
triage_rules |
Show active trigger rules |
flare_send |
SOS — route inference to GPU rescue node |
zip_create |
Bundle team work into verified .tibet.zip |
zip_verify |
Verify bundle integrity (SHA256 manifest) |
upip_export |
5-layer process integrity snapshot |
Triage Levels
L0 AUTO — Low risk, proceeds automatically
L1 OPERATOR — Needs operator approval
L2 SENIOR — Needs senior review
L3 CEREMONY — Needs multi-party ceremony
Flare Rescue
When your API crashes (rate limit, timeout, credits exhausted), flare routes to a GPU rescue node:
flare_send(
prompt="Summarize this article about AI safety",
target="hackaway_gpu",
model="humotica-7b"
)
# → P520 GPU handles inference → result returned
TIBET ZIP Bundle
Bundle all team work into a verified archive:
zip_create(agent="team_alpha", event="hackathon-2026")
# → team_alpha.tibet.zip with MANIFEST.json (SHA256 per file)
zip_verify("team_alpha.tibet.zip")
# → VERIFIED or FAILED (even 1 byte change detected)
UPIP — 5-Layer Reproducibility
L1 STATE → Git commit, file manifest, directory hash
L2 DEPS → Python version, pip freeze, system packages
L3 PROCESS → Command, intent, actor identity
L4 RESULT → Exit code, stdout/stderr, file diff
L5 VERIFY → Machine identity, timestamp, reproduction proof
Related TIBET Packages
tibet-audit— Core TIBET provenancetibet-triage— CLI/Python API (dependency)tibet-phantom-mcp— Cross-device AI sessionstibet-ipoll-mcp— AI-to-AI messagingtibet-pol-mcp— Machine health monitoring
License
MIT — HumoticaOS
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.