Ternary Intelligence Stack — Claude Code MCP server: setup, 30 tools
Ternary Intelligence Stack — an MCP server with 30 tools that hands your agent a third answer: hold, meaning the evidence is thin and more should be gathered before it acts. No key required.
no license 3,210 installs updated 2026-04-17
claude mcp add --transport http ternlang https://ternlang--rfi-irfos.run.toolsWhat Ternary Intelligence Stack does
Your agent normally chooses between two answers. This server adds a third. hold says the evidence is not enough yet and the agent should collect more before committing. Verdicts come out of numbers: trit_decide converts a float into a trit with a confidence score, trit_vector averages named dimensions by weight, and trit_action_gate vetoes an action as soon as a dimension flagged hard_block:true carries negative evidence.
The tool list goes past routing. moe_orchestrate sends a query to 13 specialist agents and keeps a safety veto at the end, ternlang_run compiles and runs .tern programs on the BET VM, trit_audit scans a decision log for forced yes/no calls and scores it against Article 13 and Article 14 of the EU AI Act. Three memory layers with TTL and a consolidation cycle sit alongside.
Connect over HTTP to https://ternlang--rfi-irfos.run.tools. Nothing to pay to start. The free moe_orchestrate preview returns the verdict plus the voices of three experts only. The whole 13-expert panel, SSE streaming and server-side memory need a paid tier: Tier 2 at €24.99/mo for 10k calls or Tier 3 at €49.99/mo for 20k.
What it helps with
- turn several independent scores into one verdict with a confidence value
- veto an action when a dimension is marked
hard_block - run two conflicting claims past 13 experts and get a synthesis
- spot forced yes/no calls in an agent's decision log
- rewrite
if/elif/elsebranches as.ternwith explicit hold arms
Example prompts for the agent
- Call
trit_decideon 0.62 and 0.58 and tell me whether confidence is high enough to act - Audit the agent's decision log with
trit_auditand list the calls that should have been held - Aggregate three weighted dimensions with
trit_vectorand check if the action is actionable
How to install Ternary Intelligence Stack
Platform CLI: remote server
claude mcp add --transport http ternlang https://ternlang--rfi-irfos.run.toolsPlatform CLI: remote server
codex mcp add ternary-intelligence-stack --url https://ternlang--rfi-irfos.run.toolsConfig file
{
"mcpServers": {
"ternary-intelligence-stack": {
"url": "https://ternlang--rfi-irfos.run.tools"
}
}
}Config file
{
"servers": {
"ternary-intelligence-stack": {
"type": "http",
"url": "https://ternlang--rfi-irfos.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http ternary-intelligence-stack https://ternlang--rfi-irfos.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Ternary Intelligence Stack
How to install Ternary Intelligence Stack in Claude Code?
Run claude mcp add --transport http ternary-intelligence-stack https://ternlang--rfi-irfos.run.tools. The server then shows up in the session with its 30 tools.
What does Ternary Intelligence Stack do?
It gives the agent an outcome other than yes and no: hold, for cases where the data is too thin. Routing decisions, a 13-expert panel, three-layer memory and an EU AI Act audit all build on it.
Do I need an API key?
The 30 tools work without a key over HTTP. The full MoE-13 panel, streaming and server-side memory require a paid Tier 2 or Tier 3 plan.