trust-ledger-os
This server exposes read-only tools to inspect Trust Ledger OS metadata, roadmap, routes, and package surfaces.
Retrieve the full Trust Ledger OS manifest.
List all roadmap phases.
Fetch a single roadmap phase by its id.
List live application routes.
List distribution packages for npm, PyPI, and MCP.
Trust Ledger OS
Trust Ledger OS is a trust and risk control plane for AI teams. Every high-impact change is reviewed, traced, and recorded before it reaches customers or cash.
Product screenshots
Trust Ledger OS desktop overview explaining the review workflow and its supporting tool stack.

Existing UI capture stored in this repository; displayed values may be demo or sample data.
Related MCP server: agentic-ecos
Overview
The repo combines a public landing page with four scaffolded implementation phases. The same roadmap is mirrored into reusable package boundaries so the app, docs, and future library work stay aligned.
Mirrors:
icohangar-ops/trust-ledger-osCubiczan/trust-ledger-os
Core Roles
PRISM: runtime observability for agent calls, approvals, and latency.
Prelint: pre-merge product review for policy drift, bad defaults, and risky logic.
GIDE: secure offline editing and emergency fixes when the network is not trusted.
What It Does
Capture a code change, spend request, or agent action.
Review it against product policy and trust rules.
Attach a PRISM trace to the runtime decision.
Produce an approve, deny, or counter outcome.
Store the decision in a ledger future runs can reuse.
Live Routes
/landing page and roadmap/foundationphase 1 scaffold/framework-benchmarkphase 2 scaffold/research-reasoningphase 3 scaffold/production-controlsphase 4 scaffold/decisionsdecision ledger (CHP decision substrate) ·GET /api/decisionslive read
Phase Packages
foundation-kit/: shared agent glossary, decision tree, model/tool matrix, and prompt skeletons.framework-benchmark-suite/: framework profiles, comparison cases, and scoring rubric.research-reasoning-kit/: research pipeline stages and reusable reasoning patterns.production-controls-kit/: eval harness, drift monitoring, guardrails, and release gate scaffold.decision-substrate/: CHP decision records — R0 gate, deterministic foundation scoring (guardrails 40 / bounded result 30 / parity 30), configurable per-domain floors (general 70, finance 100, blockchain/DeFi 85), substrate-enforced human locks (TRUST_LEDGER_CHP_REQUIRE_HUMAN_LOCK, default on), and an append-only JSONL ledger sealed with SHA-256body_sha256revalidated on every read. TypeScript port of the primitive proven in erp-control-plane; canonical JSON via@cubiczan/chp.
Distribution Surfaces
packages/npm/: npm-friendly manifest and catalog export, published as@cubiczan/trust-ledger-os@0.1.2.packages/python/: PyPI-friendly manifest and catalog export, published astrust-ledger-os==0.1.2.packages/mcp/: MCP-ready tool and resource catalog, published astrust-ledger-os-mcp@0.1.2.
Package Commands
npm package build:
npm --prefix packages/npm run buildMCP package build:
npm --prefix packages/mcp run buildMCP server run:
npm --prefix packages/mcp startPython CLI:
PYTHONPATH=packages/python/src python3 -m trust_ledger_os.cli --manifestVercel Python entrypoint:
src.trust_ledger_os.vercel_app:appfrompackages/python
Release Workflow
GitHub Actions workflow:
.github/workflows/release.ymlTrigger it with a
v*tag orworkflow_dispatchRequired secrets for publish mode:
NPM_TOKENPYPI_API_TOKEN
The workflow builds the Next app, the npm and MCP packages, and the Python package before publishing.
Demo Assets
The 2-minute video plan and FFmpeg render command are in docs/TRUST_LEDGER_OS_VIDEO.md.
Generated assets live in public/demo:
trust-ledger-os-demo.mp401-hero-desktop.png02-how-it-works.png03-tool-stack.png04-builderbase-fit.png05-demo-deliverables.png06-hero-mobile.png
Implementation Roadmap
Foundation kit: shared agent glossary, model/tool matrix, and when-to-use-an-agent guidance.
Framework benchmark: compare LangGraph, OpenAI Agents SDK, AutoGen, PydanticAI, and LlamaIndex.
Research and reasoning: fundamental analysis, deep search, and reusable reasoning templates.
Production controls: eval harnesses, drift checks, tracing, guardrails, and approval gates.
Getting Started
npm install
npm run devBuild
npm run buildDevelopment Notes
Keep shared data in the package folders, not in the page components.
Import from each package
src/entry until the package exports are formalized.Add new phase work as reusable types and data first, then wire routes and docs.
Treat
README.mdanddocs/TRUST_LEDGER_OS.mdas the roadmap source of truth.
Repo Layout
trust-ledger-os/
├── app/
├── decision-substrate/
├── docs/
├── foundation-kit/
├── framework-benchmark-suite/
├── production-controls-kit/
├── research-reasoning-kit/
├── package.json
├── README.md
└── tsconfig.jsonAvailable Tools
5 toolsget_manifestB
Return the Trust Ledger OS manifest.
Inputs: no named parameters.
get_phaseA
Fetch one roadmap phase by id.
Inputs: id (required).
list_packagesA
List the npm, PyPI, and MCP package surfaces.
Inputs: no named parameters.
list_phasesB
List the roadmap phases.
Inputs: no named parameters.
list_routesA
List the live app routes.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct resource such as manifest, phases, routes, or packages, and get_phase is clearly the single-item counterpart to list_phases. There is only mild overlap potential in get_manifest possibly summarizing other surfaces, but descriptions keep the boundaries clear.
All tool names follow a consistent get_/list_ + noun pattern with snake_case throughout. This makes the tool set predictable and easy to navigate.
Five tools is a well-scoped size for a focused read-only informational server. Each tool covers a distinct surface without unnecessary duplication or bloat.
The core surfaces of the server—manifest, roadmap phases, routes, and packages—are covered with list and detail access where appropriate. Missing route- or package-level detail getters could be a minor gap, but list-level access may be sufficient for the apparent purpose.
Related MCP Connectors
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
Host any HTTP API as MCP tools with a tamper-evident cross-agent settlement ledger.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
Signed, Merkle-proofed, on-chain-anchored trust records for MCP servers. Verify, do not trust.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server exposing AgentForge Trust Score audit tools. Query trust, evaluate policies, list trusted servers, recommend with filter.41MIT
- AlicenseBqualityBmaintenanceMCP server that initializes, manages, and operates traceable agentic infrastructure across your digital ecosystem, serving as a control plane to know project states, health, and initialize missing setups.371MIT
- AlicenseNot gradedqualityDmaintenanceA continuous, out-of-band trust and reliability layer for the MCP ecosystem. It fingerprints MCP server tool definitions, detects and classifies drift (e.g., rug pulls) via a severity taxonomy, maintains a hash-chained evidence ledger, and gates CI with SARIF—while also acting as an MCP server itself so agents can check a server's safety before binding.Apache 2.0
- AlicenseAqualityBmaintenanceA local, read-only MCP server that deterministically validates rights-aware production metadata manifests before delivery or release.1MIT