tentra-mcp
v1.3.3
Published
Tentra MCP — AI-native architecture platform for engineering teams. Describe systems in natural language, get interactive diagrams, export to 14 frameworks (Spring Boot, FastAPI, Go, Rust, ...), detect drift automatically. Also includes a persistent code
Maintainers
Readme
tentra-mcp
AI-native architecture platform for engineering teams. Describe systems → get diagrams → export to 14 frameworks. Plus a persistent code graph for AI coding agents.
Works in Cursor, Claude Code, Codex, and Windsurf.
Quick Start
npx tentra-mcpOn first use, your browser opens for one-click GitHub sign-in. That's it — no API key needed.
Advanced: If you prefer to use an API key directly, run
npx tentra-mcp --key YOUR_API_KEY. Get your key at trytentra.com/settings.
What is Tentra?
Tentra is an AI-native architecture platform for engineering teams. Describe a system in natural language — get an interactive diagram and production-ready code in 14 frameworks. Keep diagrams in sync with code automatically. Three pillars:
- AI-native architecture generation. Describe a system in plain English → interactive diagram with services, connections, and zones. 167 drag-drop cloud components (AWS, GCP, Azure, Kubernetes). Versioned, shareable artifacts. Works inside Cursor, Claude Code, Codex, Windsurf via MCP.
- Export to real production code (14 frameworks). Java Spring Boot, Node.js, Python FastAPI, Go chi, Rust Axum, .NET ASP.NET, Kotlin Ktor, PHP Laravel, Ruby Rails, Elixir Phoenix, Docker Compose, Terraform, Mermaid, ADR docs. Real project scaffolds with service definitions, connections, and health checks — not boilerplate.
- Drift detection: diagram vs code. Saved architecture vs current codebase → accuracy score + diff. Runs any time, in CI, or during review. Architecture that stays in sync with reality, automatically.
Also included — a persistent code graph for AI coding agents. index_code walks your repo with Tree-sitter, storing files, symbols, imports, call edges, and semantic annotations as a queryable graph. Agents get structural answers across sessions — call graphs, fan-in, shortest path between two symbols, god-nodes, churn × complexity hotspots. Free in local mode (npx tentra-mcp --local init), complementing the architecture workspace.
This MCP server gives your AI assistant 35 tools:
Architecture (9 tools)
| Tool | Description |
|------|-------------|
| create_architecture | Design a new system from a description |
| update_architecture | Modify an existing architecture |
| get_architecture | Read architecture details |
| list_architectures | Browse all saved designs |
| analyze_codebase | Scan local code and generate diagram |
| lint_architecture | Quality checks (9 rules: orphans, SPOFs, god services) |
| sync_architecture | Detect drift between diagram and code |
| export_architecture | Export to 14 frameworks (Java, Python, Go, Rust, etc.) |
| create_flow | Create step-by-step flow visualization |
Code Graph — Write (4 tools)
| Tool | Description |
|------|-------------|
| index_code | Walk a repo, Tree-sitter locally, start a semantic indexing job |
| index_code_continue | Resume an in-progress indexing job |
| record_semantic_node | Persist an agent-extracted semantic annotation |
| get_index_job | Check status of an indexing job |
Code Graph — Read (12 tools)
| Tool | Description |
|------|-------------|
| query_symbols | Fuzzy trigram search across indexed symbols |
| find_references | Every resolved caller of a symbol (refactor-safety) |
| safe_rename | Patch plan for renaming a symbol — definition + every call site, no files written |
| get_symbol_neighbors | BFS traversal in the call/import graph |
| get_service_code_graph | Subgraph for a canvas service |
| explain_code_path | Shortest path between two symbols with semantic context |
| find_similar_code | pgvector cosine ANN over agent-generated embeddings |
| record_embedding | Persist an agent-generated embedding vector |
| list_god_nodes | Highest fan-in/out symbols (architectural smells) |
| get_quality_hotspots | Churn × complexity ranking |
| list_snapshots | Time-travel listing of indexed snapshots |
| diff_snapshots | Files / symbols / god-nodes added/removed between snapshots |
Enrichment — Contracts, Decisions, Ownership, Domains (9 tools)
| Tool | Description |
|------|-------------|
| set_service_mapping | Link an indexed file or symbol to a canvas service |
| set_domain_membership | Assign a service or file to a domain (bounded context) |
| record_contract | Store a parsed API contract payload (OpenAPI, GraphQL, Protobuf) |
| bind_contract | Link a contract to the symbol that implements it |
| record_decision | Create an Architecture Decision Record, optionally linking code |
| link_decision | Append a link from an ADR to another symbol, file, or service |
| get_ownership | Resolve the owner (team or person) for a file or service |
| get_decisions_for | List ADRs linked to a given entity |
| get_contracts | List contracts, optionally filtered by kind or service |
Setup
Option 1: SSE (zero install)
Add to your IDE's MCP config — no local install needed:
Cursor (Settings > Features > MCP > Add Server):
{
"tentra": {
"type": "sse",
"url": "https://trytentra.com/api/mcp?key=YOUR_API_KEY"
}
}Claude Code (.mcp.json in project root):
{
"mcpServers": {
"tentra": {
"type": "sse",
"url": "https://trytentra.com/api/mcp?key=YOUR_API_KEY"
}
}
}Option 2: Local install (needed for codebase scanning)
npx tentra-mcpAuthenticates automatically via GitHub on first use. Credentials are saved to ~/.tentra/credentials.
Cursor config for local server:
{
"tentra": {
"command": "npx",
"args": ["tentra-mcp"]
}
}Claude Code (.mcp.json):
{
"mcpServers": {
"tentra": {
"command": "npx",
"args": ["tentra-mcp"]
}
}
}Usage Examples
Once connected, just talk to your AI:
"Design a payment system with Stripe, Kafka, and PostgreSQL"
→ AI calls create_architecture → diagram at trytentra.com/arch/xxx
"Scan this codebase and generate the architecture"
→ AI calls analyze_codebase → detects services, DBs, queues
"Export this architecture to Java Spring Boot"
→ AI calls export_architecture → downloads zip with project scaffold
"What changed since last time? Is my diagram outdated?"
→ AI calls sync_architecture → drift report with accuracy scoreExport Formats
Java (Spring Boot), Node.js (Fastify), Python (FastAPI), Go (chi), Rust (Axum), .NET (ASP.NET), Kotlin (Ktor), PHP (Laravel), Ruby (Rails), Elixir (Phoenix), Docker Compose, Mermaid, ADR, Terraform
Links
- Website: trytentra.com
- Documentation: trytentra.com/docs
- Setup Guide: trytentra.com/docs/setup
- Gallery: trytentra.com/gallery
License
MIT
