Log inSubmit server
T Zero Context Architect logo

T Zero Context Architect

Offline MCP tools for AST context compression, architecture analysis, code search, security checks, memory, and agent workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install T Zero Context Architect

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "toprakahmetaydogmus-tzeroalgorithm": {
      "command": "uvx",
      "args": [
        "-m",
        "tzero_mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

T-Zero Context Architect MCP server analyzes local repositories and code buffers through AST-based context compression, dependency analysis, architecture checks, security scans, and code search. Its 14 tools cover repository context trees, snippet pruning, memory stores, token-cost estimates, multi-agent workflows, and an all-in-one workflow entry point. It runs locally without credentials for its default offline operations and can produce reduced context for coding agents. Reach for it when an agent needs repository structure, refactoring risk, architectural boundaries, or lower-token code context before implementation work.

Use cases

  • Build a reduced repository context before an agent coding session
  • Estimate blast radius before changing a shared symbol
  • Check imports against configured architecture boundaries
  • Search local code by identifiers or natural-language descriptions
  • Scan code and buffers for hardcoded secrets before committing

Key features

  • AST-based repository context compression
  • In-memory snippet and diff pruning
  • Dependency, call-chain, and change-impact analysis
  • Architecture rule management and enforcement
  • Offline code search, quality audits, and secret scanning
  • Local agent memory and multi-agent workflow tools

Tools15

What T Zero Context Architect lets your agent do. Expand a tool for its parameters.

Verified live~9.9k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 19d

What it can do

From the 15 tools this server returned when we ran it; 15 declare their own safety hints.

Runs commands · 3Can delete or modify data · 2Handles credentials · 15Makes network requests · 1Read-only tools · 10
Network at startup2 connections
Files written at startup24

Observed 2026-10-26 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · tzero_mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars11Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Tools exposed15Callable tools this server registers over MCP.

How T Zero Context Architect works

What T-Zero Context Architect MCP server does

T-Zero Context Architect provides a local MCP toolset for turning source repositories and code snippets into structured, reduced context for AI coding workflows. Repository analysis can produce hierarchical architecture trees, compact symbol maps, focus-file skeletons, pruned prompt prefixes, or Git diff context. The focus-file mode keeps the selected file intact while reducing surrounding first-degree dependencies to interfaces such as signatures, types, and docstrings.

The server also covers codebase inspection beyond context generation. It can trace imports and calls, rank dependency centrality, find unreferenced symbols, calculate a target symbol’s change blast radius, search code with keyword and TF-IDF scoring, audit code smells and duplication, and scan for credential-like secrets. Architecture rules can be stored in tzero.rules.json, checked against repository imports, or used to generate Markdown and Mermaid architecture documentation.

How it works

Analysis is performed locally with AST and regex-based parsers. Context and diagnostic results are deterministic for the same workspace state, while in-memory snippet pruning leaves source files untouched. Supported parsing and reduction paths cover Python, TypeScript, Go, Rust, Java, C#, C++, SQL, JSON, and YAML for the relevant tools. Malformed snippets can fall back to regex line pruning, and unparseable binary files are skipped during quality audits.

The toolset includes local semantic memory operations for storing, consolidating, exporting, querying, resetting, and deleting agent memory. orchestrate_agent_swarm dispatches multi-agent tasks, consensus rounds, or self-healing workflows, while execute_codebase_workflow routes broader operations through one entry point. Most operations are read-only, but rule management, memory deletion or reset, pre-commit hook installation, and self-healing workflows can change local state.

Setup and configuration

Install the Python package with:

Terminal
pip install tzero-mcp

The project advertises Python 3.11, 3.12, and 3.13 support. The command-line quickstart can generate a repository tree with tzero --tree . --out context.txt, and tzero init configures Cursor, Claude, Antigravity, Windsurf, and Cline. An official VS Code/Cursor extension can also be installed from the packaged .vsix file.

Default analysis requires no authentication or cloud credentials. Architecture rules are read from or written to tzero.rules.json in the selected project root. Architecture blueprint generation is offline by default; enabling its use_ai option allows an optionally configured AI provider and model to synthesize additional narrative.

Tools and capabilities

  • Build multi-tier repository context, symbol maps, skeletons, and diff-focused prompts.
  • Prune source snippets, schemas, and unified diffs while retaining interfaces.
  • Manage and enforce architectural layer boundaries.
  • Generate Mermaid architecture documentation.
  • Analyze dependencies, call chains, PageRank centrality, dead code, and change impact.
  • Search code, audit quality, scan secrets, estimate token costs, manage memory, and orchestrate workflows.

Limitations and notes

The server is intended for local repository and text analysis rather than remote indexing. Use repository context tools for filesystem-wide structure and snippet pruning for an individual in-memory buffer. Search returns ranked local matches, while memory queries operate on the local memory store rather than source-code search indexes. The optional AI path for architecture blueprints is separate from the default offline analysis and can fall back to local structural mapping.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about T Zero Context Architect

T-Zero Context Architect is an MCP server that connects AI coding clients to local repositories, source buffers, architecture rules, and agent memory. Its main tools build compressed AST context, prune snippets, analyze dependencies and change impact, search code, audit quality, scan secrets, manage memory, and orchestrate codebase workflows entirely offline by default.

Install it with `pip install tzero-mcp`. The quickstart also provides `tzero init` for configuring supported coding clients and `tzero --tree . --out context.txt` for generating a repository context file. Python 3.11, 3.12, and 3.13 are listed as supported versions.

Yes, T-Zero Context Architect works with Cursor. The project names Cursor among its supported MCP clients, and `tzero init` can configure it. An official VS Code/Cursor extension is also available as a `.vsix` package.

No, its default operations require no authentication, API keys, or cloud credentials. Repository analysis, snippet reduction, search, security scans, and most other tools run locally. Architecture blueprint generation can optionally use a configured AI provider when `use_ai` is enabled.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewT Zero Context Architect AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/toprakahmetaydogmus-tzeroalgorithm?style=directory)](https://allmcps.com/mcp/toprakahmetaydogmus-tzeroalgorithm)
HTML Embed
<a href="https://allmcps.com/mcp/toprakahmetaydogmus-tzeroalgorithm"><img src="https://allmcps.com/api/badge/toprakahmetaydogmus-tzeroalgorithm?style=directory" alt="T Zero Context Architect on AllMCPs" /></a>