AI & Machine Learning

universalnaturalintelligence.com

Simulates active-inference episodes in maze environments for research and experimentation.

1 endpoint27 known toolsFirst detected July 19, 2026Last detected August 28, 2026

ENDPOINT 1

https://universalnaturalintelligence.com/api/mcp

No auth detected

MCP server metadata

Name: uni-lab
Version: 0.2.0

Capabilities

tools.listChanged

Known tools 27

list_labs

Return the two labs (Precision, Echo), their observation models, and their production URLs.

Inferred read-only

list_mazes

Return all six mazes with ASCII art, size, and a short description.

Inferred read-only

describe_dial

Explain γ_A / γ_B / T at a given value, in behavioural terms.

Inferred read-only

run_episode

Simulate an active-inference episode server-side and return the full trajectory (positions, beliefs, policy posterior, EFE breakdown per step).

Inferred read-only

run_sweep

Run multiple episodes varying a single dial; return one summary row per value (reached goal?

Inferred read-only

compare_labs

Run the same maze at the same dials in both Precision and Echo labs, return both trajectories plus a diff summary.

Inferred read-only

list_patient_archetypes

Return the four patient archetypes (Acute, Chronic, Anxiety, Resilient) with their parameter presets and the story shown in the reading panel.

Inferred read-only

apply_protocol

Simulate one trauma_loop episode under a named treatment protocol (wait, pure_exposure, pure_grounding, sequenced) or a custom protocol object.

Inferred read-only

compare_protocols

Run multiple Loop Lab protocols against a single patient archetype with a fixed seed, return per-protocol outcomes plus a narrative diff summary.

Inferred read-only

compute_bifurcation_map

Sweep a 2D parameter grid for a given archetype, running 8-16 seeded trajectories per cell.

Inferred read-only

analyze_outcome

Re-run the given (archetype, protocol_id) pair and return a natural-language explanation keyed to the Five Phenomena (The Trap, Exposure Without Grounding, Grounding First, etc.).

Inferred read-only

attach_session

Validate that a `pair-XXXX` code shown on the user's open lab tab is alive.

Inferred read-only

detach_session

Acknowledgement that you have stopped tracking this session.

Inferred read-only

set_dial

Set γ_A, γ_B, or T on the user's open lab tab.

Inferred read-only

switch_maze

Load one of the six mazes into the lab the user is watching.

Inferred read-only

set_planning_depth

Set policy depth to 2 or 3 on the open lab.

Inferred read-only

set_action_mode

Switch between deterministic argmax and stochastic sampling on the open lab.

Inferred read-only

step_agent

Advance the agent n steps on the open lab.

Inferred read-only

auto_run

Turn the lab's auto-step loop on or off, with an interval in ms.

Inferred read-only

reset

Restart the agent at the start tile on the open lab.

Inferred read-only

read_state

Return the latest APP snapshot the open lab pushed: position, dial values, current maze, step count, belief entropy.

Inferred read-only

cookbook_list

Return every published cookbook page (13 L0-L12 recipes plus front matter, kitchen rules, pantry, continuity substrate, closing) with its honest fence status, word count and URL, plus the four-value fence vocabulary and what each value means.

Inferred read-only

cookbook_get

Fetch one cookbook page in full by rung (L0-L12) or slug (e.g.

Inferred read-only

cookbook_search

Full-text search across every published cookbook page.

Inferred read-only

cookbook_ledger_status

Return the CLAIM-LEDGER rows governing a developmental rung (L0-L12), including the explicit 'what is NOT claimed' fence.

Inferred read-only

cookbook_verify_fence

Cross-check what a recipe claims (its honest fence) against what the claim ledger actually records for that rung, and report consistent true/false with the reasoning.

Inferred read-only

cookbook_integrity

Return the SHA-256 of the authored markdown behind every cookbook page, so a caller can confirm the MCP corpus and the published site were generated from the same sources and have not drifted.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.uni-lab]
url = "https://universalnaturalintelligence.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "uni-lab": {
      "type": "http",
      "url": "https://universalnaturalintelligence.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: uni-lab
Remote MCP URL: https://universalnaturalintelligence.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "uni-lab": {
      "url": "https://universalnaturalintelligence.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "uni-lab": {
      "type": "http",
      "url": "https://universalnaturalintelligence.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "uni-lab",
  "transport": "streamable-http",
  "url": "https://universalnaturalintelligence.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for universalnaturalintelligence.com was fetched 2026-08-03T19:30:32.741Z and is being refreshed.

Trust status Neutral

universalnaturalintelligence.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.