T-Zero Context Architect • v7.3.0
Enterprise Codebase Context Engine & 47-Tool Autonomous MCP Server
Cuts LLM context ingestion overhead by up to 94.9% across 10+ programming languages while preserving complete type signatures, symbol hierarchy, and cross-file dependencies.
Quickstart • Superdesign MCP • MCP Tools • Benchmarks • Architecture • Türkçe Dokümantasyon
Overview
Modern AI coding agents (Cursor, Claude Code, Antigravity IDE, Windsurf, Cline) suffer from severe context bloat when reading entire codebases, leading to high token costs, lost instructions, and hallucinations.
T-Zero solves this by acting as an intelligent context layer:
- AST Signature Pruning: Strips internal routine function and method implementation bodies while preserving every class definition, typed signature, docstring, and return type.
- Polyglot Parsing: Zero-dependency offline support for Python, TypeScript, JavaScript, Go, Rust, Java, C#, C++, PHP, and Ruby.
- Native Superdesign Orchestrator: Brings the open-source Superdesign AI design methodology to Claude Code and Cursor with 5 native tools and interactive HTML galleries.
- Zero-Leak Security: Guaranteed 100% offline execution with zero hardcoded API keys, telemetry, or remote relay servers.
Quickstart
1. Instant Run via uvx (Zero Installation)
uvx tzero-mcp
2. Install via pip / pipx
pip install tzero-mcp
3. Connect to Your IDE (Cursor / Claude Desktop / Antigravity / Windsurf)
Add the following to your mcp-settings.json or IDE MCP configuration:
{
"mcpServers": {
"tzero": {
"command": "tzero-mcp"
}
}
}
4. Claude Code CLI Integration
claude mcp add --scope user tzero uvx tzero-mcp
5. Launch the Local Web Console
tzero --dashboard
Opens the modern slate control console on http://localhost:8421 featuring the live AST reducer sandbox, 4D Causal-Temporal Graph, and Superdesign Canvas.
Reproducible Benchmarks
| Analysis Target | Raw Context Volume | T-Zero Pruned Payload | Token Reduction | Query Cost Delta |
|---|---|---|---|---|
| Full Repository Scan | 166,996 tokens |
8,465 tokens |
-94.9% | -$0.3963 / query |
| Large Backend Module | 42,180 tokens |
2,410 tokens |
-94.3% | -$0.0994 / query |
| Micro-Patch Diff Stream | 18,450 tokens |
1,120 tokens |
-93.9% | -$0.0433 / query |
Verify locally offline ($0 cost):
python tzero.py --savings
Superdesign MCP Orchestrator
T-Zero v7.1.0 natively embeds the Superdesign AI design agent orchestrator (inspired by @jasonzhou1993 and @jackjack_eth), bringing sophisticated design capabilities directly to Claude Code, Cursor, and Antigravity IDE without external API keys.
User Prompt: "Create a modern analytics dashboard"
│
▼
[tzero_mcp: superdesign_generate]
│
├─► Returns structured specs, design system tokens, and exact file paths
│
▼
[Claude Code / Cursor LLM]
│
├─► Generates production HTML/CSS/React/SVG into superdesign/design_iterations/
│
▼
[tzero_mcp: superdesign_gallery]
│
└─► Auto-discovers files and opens interactive responsive canvas gallery
Superdesign Tools
| Tool | Purpose | Parameters |
|---|---|---|
superdesign_generate |
Generates structured specifications for UI, wireframes, components, SVG logos, and icons. | prompt, design_type (ui, wireframe, component, logo, icon), variations (1-5), framework (html, react, vue) |
superdesign_iterate |
Generates surgical iteration instructions to refine existing design files preserving design tokens. | design_file, feedback, variations |
superdesign_extract_system |
Extracts and writes reusable design token schemas (superdesign/design_system/<name>.json). |
input_path_or_description, system_name |
superdesign_list |
Lists all created design iterations and extracted systems in the workspace. | workspace_path |
superdesign_gallery |
Generates a responsive, browser-based HTML gallery (superdesign/gallery.html) with live card previews and modal inspection. |
workspace_path |
MCP Tools Reference (47 Tools)
T-Zero exposes 47 specialized tools with TDQS 5.0/5.0 Anchor Certification (typed fields, explicit behavior contracts, usage guidelines, and return specifications).
1. Context & AST Pruning (6 Tools)
get_project_context_tree: Multi-tier hierarchical AST context tree (T-1 to T-4).prune_code_snippet: Strips implementation bodies from in-memory snippets or diff streams.prune_schema_definition: Compresses database schemas, OpenAPI specs, and protobuf definitions.get_smart_skeleton_context: Focus-file implementation with 1st-degree caller/callee skeletons.get_incremental_diff_context: Git diff context pruned with AST signatures.generate_zero_waste_prompt_context: Token-optimized prompt preamble for coding agents.
2. Architecture & Rules (5 Tools)
query_architecture_boundaries: Inspects active T-4 architectural layer constraints.enforce_architecture_boundaries: Validates import boundaries defined intzero.rules.json.generate_architecture_blueprint: Synthesizes complete system specification with live Mermaid diagrams.generate_repo_map: Ultra-compact AST symbol token map for chat context windows.export_agent_rules: Exports AI rule specifications (.cursorrules,.clinerules,.cursor/rules/*.mdc).
3. Dependencies & Reachability (6 Tools)
query_module_dependencies: Analyzes import/export graphs across 10+ programming languages.analyze_code_dependencies: Deep dependency mapping, call chains, PageRank, and dead code.analyze_change_impact: Calculates change blast radius (0-100) and downstream dependents.rank_repository_pagerank: Identifies architectural backbone files by network centrality.trace_symbol_call_chain: Traces cross-file execution flow from caller to callee.find_dead_code: Detects unreferenced, unreachable, or orphaned functions.
4. Memory & Knowledge Graph (8 Tools)
query_memory_store: Queries semantic triples, causal graphs, and MinHash entity clusters.manage_memory_store: Consolidates, exports, lists, resets, or compresses memory stores.jarvis_query_knowledge_graph: Graph query engine for entity-relationship triples.jarvis_consolidate_memory: Consolidates short-term episodic memory into long-term memory.jarvis_compress_semantic_memory: Compresses text into semantic triples.jarvis_decompress_semantic_memory: Reconstitutes compressed triples into coherent context.jarvis_compress_document: Compresses long documents while preserving critical facts.jarvis_export_memory_store: Exports agent knowledge stores to JSON or HTML visualizations.
5. Swarm & Multi-Agent Orchestration (6 Tools)
orchestrate_agent_swarm: Coordinates multi-agent workflows, PBFT consensus, and self-healing.jarvis_orchestrate_goal: Decomposes high-level objectives into phased execution plans.jarvis_swarm_orchestrate: Coordinates collaborative multi-agent execution.jarvis_bft_swarm_consensus: Byzantine fault-tolerant voting with 3f+1 quorum.jarvis_self_healing_execute: Runs shell commands with automated AST failure healing.generate_smart_micro_patch: Generates surgical git-compatible diff patches.
6. Superdesign Orchestration (5 Tools)
superdesign_generate: Structured specifications for UI, wireframe, component, logo, and icon creation.superdesign_iterate: Structured instructions to iterate on existing design files with feedback.superdesign_extract_system: Extracts structured design token JSON schemas.superdesign_list: Enumerates all design iterations and systems in workspace.superdesign_gallery: Builds interactive HTML gallery with live previews and modal zoom.
7. Security & Code Quality (6 Tools)
verify_security_guard: 100% Zero-Leak scan for hardcoded credentials and secrets.verify_zero_leak_security: Validates that files adhere to the Zero-Leak security policy.install_git_security_guard: Installs pre-commit hooks preventing credential leaks.audit_code_quality: Static AST analysis, cyclomatic complexity, and code smell audits.audit_codebase_quality: Static code audit across workspace files.verify_hallucination_guard: Ground-truth verifier detecting hallucinated imports and types.
8. Economic ROI & Search (5 Tools)
estimate_token_cost: Real-time cost comparisons across OpenAI, Anthropic, Gemini, and DeepSeek.get_token_savings_metrics: Quantitative token compression metrics and monthly ROI savings.compress_stream_tokens: Compresses live text streams using localized codebooks.search_codebase: Local BM25 hybrid semantic and lexical code search.search_codebase_semantic: 100% private semantic search without cloud embedding APIs.
System Architecture
graph TD
A[Source Code Repository] --> B[AST Parser & Visitor Engine]
B --> C[Polyglot Token Reducer]
C --> D[T-Zero Core: Signatures & Hierarchy]
D --> E[tzero_mcp.py Stdio Server]
D --> F[tzero_superdesign.py Orchestrator]
F --> G[superdesign/design_iterations/]
F --> H[superdesign/gallery.html]
E --> I[Cursor IDE]
E --> J[Claude Code]
E --> K[Antigravity IDE]
E --> L[Windsurf / Cline]
Security Architecture
100% Zero-Leak Guarantee: T-Zero strictly contains ZERO hardcoded, personal, or public API keys or credentials anywhere in the repository. All operations run 100% locally and offline without external telemetry.
🇹🇷 Türkçe Dokümantasyon
T-Zero Context Architect v7.1.0
Yapay zeka kodlama ajanları (Cursor, Claude Code, Antigravity IDE, Windsurf, Cline) için geliştirilmiş, kod tabanı bağlamını yapısal olarak koruyarak token tüketimini %94.9'a kadar azaltan kurumsal bağlam motoru ve 47 araçlı Model Context Protocol (MCP) sunucusu.
Öne Çıkan Özellikler
- AST İmza Budama: Fonksiyon ve metotların gövdelerini çıkarır; sınıf yapılarını, tip tanımlarını, docstring'leri ve bağımlılıkları korur.
- Superdesign MCP Entegrasyonu: Açık kaynak Superdesign metodolojisini yerel 5 araçla Claude Code ve Cursor'a taşır.
- %100 Çevrimdışı ve Sıfır Sızıntı: API anahtarı veya harici bulut bağımlılığı gerektirmez.
Hızlı Kurulum
# uvx ile doğrudan çalıştırın
uvx tzero-mcp
# veya pip ile kurun
pip install tzero-mcp
# Yerel konsolu başlatın
tzero --dashboard
Lisans & İletişim
- Geliştirici: Toprak Ahmet Aydoğmuş
- LinkedIn: Toprak Ahmet Aydoğmuş
- Bio & Hub: hopp.bio/siberegitim
- Lisans: MIT License
Metadata
Release files for tzero-mcp 7.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| tzero_mcp-7.3.0.tar.gz | 281.6 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tzero_mcp-7.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 504.7 kB
Release files / tzero_mcp-7.3.0.tar.gz
| Download URL | tzero_mcp-7.3.0.tar.gz |
|---|---|
| Size | 281.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3a961b4ac4d1241592f37aa0ebf4e933e7d38347b81a3568d33c809d82b25971
|
|
BLAKE2b-256 checksum How to use checksums |
b7d5b15b11b71355028fee3bb252a9d042c4b102d56368200903b4677180b320
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / tzero_mcp-7.3.0-py3-none-any.whl
| Download URL | tzero_mcp-7.3.0-py3-none-any.whl |
|---|---|
| Size | 223.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
42b80315e667daec25ba32446ae2df0becf4e2ce2b8771d487cfd038d0b4a8da
|
|
BLAKE2b-256 checksum How to use checksums |
34cbb06434587e1ad57bb4774eba1afcfc6b2440df73bfeeaaf27b69c7b940ea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logSecurity for tzero-mcp 7.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for tzero_mcp-7.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.