@collapseindex/ci1t-mcp
Advanced tools
MCP server for CI-1T — prediction stability engine. Evaluate model stability, detect ghosts, monitor fleet drift. 20 tools for AI agents.
Version: 1.7.0
Last Updated: February 27, 2026
License: Proprietary
MCP (Model Context Protocol) server for the CI-1T prediction stability engine. Lets AI agents — Claude Desktop, Cursor, Windsurf, VS Code Copilot, and any MCP-compatible client — evaluate model stability, manage fleet sessions, and control API keys directly.
One credential. One env var. That's it.
| Tool | Description | Auth |
|---|---|---|
evaluate | Evaluate prediction stability (floats or Q0.16) | API key |
fleet_evaluate | Fleet-wide multi-node evaluation (floats or Q0.16) | API key |
probe | Probe any LLM for instability (3x same prompt). BYOM mode: bring your own model via OpenAI-compatible API | API key or BYOM |
health | Check CI-1T engine status | API key |
fleet_session_create | Create a persistent fleet session | API key |
fleet_session_round | Submit a scoring round | API key |
fleet_session_state | Get session state (read-only) | API key |
fleet_session_list | List active fleet sessions | API key |
fleet_session_delete | Delete a fleet session | API key |
list_api_keys | List user's API keys | API key |
create_api_key | Generate and register a new API key | API key |
delete_api_key | Delete an API key by ID | API key |
get_invoices | Get billing history (Stripe) | API key |
onboarding | Welcome guide + setup instructions | None |
interpret_scores | Statistical breakdown of scores | None |
convert_scores | Convert between floats and Q0.16 | None |
generate_config | Integration boilerplate for any framework | None |
compare_windows | Compare baseline vs recent episodes for drift detection | None |
alert_check | Check episodes against custom thresholds, return alerts | None |
visualize | Interactive HTML visualization of evaluate results | None |
| Resource | URI | Description |
|---|---|---|
tools_guide | ci1t://tools-guide | Full usage guide: response schemas, chaining patterns, fleet workflow, thresholds, example pipelines |
New users get guided setup automatically. If no API key is configured:
onboarding tool returns a full welcome guide with account status, setup steps, config examples, available tools, and pricinginterpret_scores, convert_scores, generate_config) always work — no auth, no creditsEvery new account gets 1,000 free credits (no credit card required), enough for 1,000 evaluation episodes.
| Variable | Required | Description |
|---|---|---|
CI1T_API_KEY | Yes | Your ci_... API key — single credential for all tools |
CI1T_BASE_URL | No | API base URL (default: https://collapseindex.org) |
Add to claude_desktop_config.json:
{
"mcpServers": {
"ci1t": {
"command": "docker",
"args": ["run", "-i", "--rm", "collapseindex/ci1t-mcp"],
"env": {
"CI1T_API_KEY": "ci_your_key_here"
}
}
}
}
Add to .cursor/mcp.json or equivalent:
{
"mcpServers": {
"ci1t": {
"command": "docker",
"args": ["run", "-i", "--rm", "collapseindex/ci1t-mcp"],
"env": {
"CI1T_API_KEY": "ci_your_key_here"
}
}
}
}
Add to .vscode/mcp.json:
{
"servers": {
"ci1t": {
"type": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "collapseindex/ci1t-mcp"],
"env": {
"CI1T_API_KEY": "ci_your_key_here"
}
}
}
}
git clone https://github.com/collapseindex/ci1t-mcp.git
cd ci1t-mcp
npm install
npm run build
# Set env var and run
CI1T_API_KEY=ci_xxx node dist/index.js
docker build -t collapseindex/ci1t-mcp .
Once connected, an AI agent can:
"Evaluate these prediction scores: 45000, 32000, 51000, 48000, 29000, 55000"
The agent calls evaluate with scores: [45000, 32000, 51000, 48000, 29000, 55000] and gets back stability metrics per episode, including credits used and remaining.
"Create a fleet session with 4 nodes named GPT-4, Claude, Gemini, Llama"
"List my API keys"
"Probe this prompt for stability: What is the capital of France?"
"Probe my local Ollama llama3 model with: What is the meaning of life?"
The agent calls probe in BYOM mode — sends the prompt 3x to http://localhost:11434/v1 and scores the responses locally. No CI-1T credits used.
"Interpret these scores: 0.12, 0.45, 0.88, 0.03, 0.67"
The agent calls interpret_scores locally (no API call, no credits) and returns mean, std, min/max, and normalized values. For full stability classification, use evaluate.
"Convert these probabilities to Q0.16: 0.5, 0.95, 0.01"
"Generate a FastAPI integration for CI-1T with guardrail pattern"
| Metric | Description |
|---|---|
| CI (Collapse Index) | Primary stability metric (Q0.16: 0–65535). Lower = more stable |
| AL (Authority Level) | Engine trust level for the model (0–4) |
| Ghost | Model appears stable but may be silently wrong |
| Warn / Fault | Threshold and hard-failure flags |
Classification labels (Stable / Drift / Flip / Collapse) are determined by the engine. Use the evaluate tool to get exact classifications — thresholds are configurable via the API.
┌──────────────────────┐ stdio ┌───────────────────────┐
│ Claude Desktop / │◄──────────────►│ ci1t-mcp server │
│ Cursor / VS Code │ │ (Node.js / Docker) │
└──────────────────────┘ └──────────┬────────────┘
│ HTTPS
│ X-API-Key
┌──────────────┼──────────────┐
│ │ │
┌────▼───┐ ┌─────▼────┐ ┌─────▼─────┐
│Evaluate│ │Fleet API │ │Dashboard │
│ API │ │Sessions │ │API Keys │
│ │ │ │ │Billing │
└────────┘ └──────────┘ └───────────┘
collapseindex.org
probe tool now supports Bring Your Own Model modebase_url + model (+ optional model_api_key) to probe any OpenAI-compatible endpoint directlycrypto.randomBytes() instead of Math.random()toQ16() decimal heuristic prevents integer arrays [0, 1] from being misclassified as floatscompare_windows severity messagetools_guide MCP resource (ci1t://tools-guide): comprehensive usage guide with response schemas, chaining patterns, fleet session workflow, classification thresholds, and example pipelinescompare_windows tool: compare baseline vs recent episodes — drift delta, trend direction, degradation detectionalert_check tool: check episodes against custom thresholds (CI, EMA, AL, ghost, fault) with severity levelsvisualize tool: generates self-contained interactive HTML with Canvas 2D bar chartsCI1T_API_KEY — no Bearer token neededCI1T_TOKEN env var entirelyonboarding tool: welcome guide with account status, setup steps, config examples, pricing, and available toolsinterpret_scores, convert_scores, generate_config (local, no auth, no credits)evaluate and fleet_evaluate now auto-detect floats (0–1) vs Q0.16 (0–65535) — no manual conversion needed© 2026 Collapse Index Labs™ — Alex Kwon
collapseindex.org · ask@collapseindex.org
FAQs
MCP server for CI-1T — prediction stability engine. Evaluate model stability, detect ghosts, monitor fleet drift. 20 tools for AI agents.
We found that @collapseindex/ci1t-mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
A misconfiguration gave three Anthropic models internet access, and one, believing it was in a simulation, shipped a credential-stealing package to PyPI.
Security News
/Company News
Socket has joined the new Composer and Packagist sponsorship program as a launch sponsor, supporting the team that keeps PHP's package ecosystem secure.
Research
/Security News
Benign-looking npm packages split malicious functionality across a dependency chain that deploys a cross-platform RAT targeting Alibaba developers.