In-depth architectural comparison of the Tentra MCP and Excalidraw Architect MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Tentra MCP
Architecture & Design · Local stdio
Quality: 55/100 (Good) | Auth: other
Excalidraw Architect MCP
Architecture & Design · Local stdio
Quality: 64/100 (Good) | Auth: No auth required
Verdict Summary: Choose Tentra MCP if you need specialized Architecture & Design tools running via a local process. Choose Excalidraw Architect MCP if your workspace requires Architecture & Design integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Tentra MCP when:
You need dedicated capabilities in the Architecture & Design domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: other (Freemium).
Primary tools included: Typed architecture diagrams from natural-language descriptions, Persistent code graph with symbol, import, and call-edge queries, Architecture linting and diagram-to-code drift detection.
AI-native architecture platform for engineering teams. Describe a system in natural language (e.g. "payment service with Stripe, Kafka, PostgreSQL") → get an interactive typed diagram with 167 cloud components → export to 14 production frameworks (Java Spring Boot, Python FastAPI, Go chi, Rust Axum, .NET, Kotlin Ktor, Ruby Rails, Elixir Phoenix, Docker Compose, Terraform, Mermaid, ADR, and more). Drift detection (syncarchitecture) scores saved diagrams against live code 0–100 with a structured diff. 9 quality-lint rules catch orphans, SPOFs, god services. Also includes a secondary persistent code-graph layer for AI coding agents (free offline via npx tentra-mcp --local init). Agent-as-LLM pattern — zero LLM cost on our side, zero API key on yours. 35 MCP tools. Works in Cursor, Claude Code, Codex, Windsurf.
Tools & Capabilities Breakdown
Tentra MCP Tools (6)
Typed architecture diagrams from natural-language descriptions
Persistent code graph with symbol, import, and call-edge queries
Architecture linting and diagram-to-code drift detection
Exports to application, infrastructure, diagram, and ADR formats
Git post-commit re-indexing for local repositories
Contracts, domains, ownership, and architecture decision records
Excalidraw Architect MCP Tools (26)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Tentra MCP is categorized under Architecture & Design and uses a local stdio subprocess. In contrast, Excalidraw Architect MCP belongs to Architecture & Design using local stdio subprocess. Select Tentra MCP when you need capabilities focused on architecture & design and Excalidraw Architect MCP when you require tools for architecture & design.
Generate beautiful Excalidraw architecture diagrams with auto-layout, architecture-aware component styling, and stateful editing. 50+ technology mappings including databases, message queues, caches, and more. No API keys required.
Create a new Excalidraw diagram of any supported type.
Two input modes:
1. **Graph types** (``architecture``, ``flowchart``) - pass ``nodes`` and
``connections``. The tool handles layout, styling, and rendering; no
coordinates needed.
2. **Typed diagrams** (every other type) - pass ``diagram_type`` and a
``spec`` object shaped for that type. Call ``list_diagram_types`` to
choose a type and ``get_diagram_schema`` to see its spec shape.
mermaid_to_excalidraw
Convert Mermaid flowchart syntax into an Excalidraw diagram.
Supports the mermaid flowchart subset that AI agents commonly generate:
- Directions: graph TD, LR, BT, RL
- Node shapes: [text], {text}, ((text)), ([text])
- Edge types: -->, ---, -.-> ==> with |label|
- Subgraphs: subgraph Title ... end
Component types are auto-detected from node labels (e.g., a node labeled
"PostgreSQL DB" automatically gets database styling).
modify_diagram
Modify an existing Excalidraw diagram created by this tool.
Supports iterative editing: add components, remove nodes, update labels,
and rewire connections - without recreating the entire diagram.
IMPORTANT: Call get_diagram_info first to understand the current diagram
state before making modifications.
For **typed diagrams** (sequence, pyramid, bar, swimlane, ...) there is a
single operation:
{"op": "update_spec", "patch": {"tiers": [...], "title": "New title"}}
The patch is deep-merged into the stored spec and the diagram re-rendered.
Lists are replaced wholesale, so send the complete list to change one
entry. The node/connection operations below apply to architecture and
flowchart diagrams only.
get_diagram_info
Get a structured summary of an existing Excalidraw diagram.
Call this BEFORE modify_diagram to understand what nodes and connections
currently exist. The summary includes node ids, labels, component types,
and the full connection topology.
export_diagram
Export an .excalidraw file to SVG or PNG image.
Converts an existing .excalidraw diagram into a portable image file
without requiring a browser or the Excalidraw application.
list_diagram_types
List every supported diagram type with guidance on when to use it.
Call this BEFORE create_diagram when the right diagram type isn't obvious.
Picking the wrong type is the most common way a diagram fails - a
swimlane drawn as a flowchart loses the handoffs that were the point.
Two rules worth applying whatever you pick:
- Target density ~4/10. Above 9 nodes it is probably two diagrams.
- Mark only 1-2 elements "focal": true. The accent color is a signal,
and using it everywhere destroys it.
Returns:
A table of type -> family, when to use it, and when not to.
get_diagram_schema
Get the JSON schema and selection guidance for one diagram type.
Call this before passing a `spec` to create_diagram for a type you have
not used yet, so the payload matches on the first attempt.
kg_init
Create a new architecture knowledge graph file (markdown).
The knowledge graph is the persistent source of truth for your system's
services and dependencies. Diagrams are rendered *from* it.
kg_add_service
Add or update a service in the knowledge graph.
kg_remove_service
Remove a service and all dependencies touching it.
kg_link
Add a directed dependency: ``from_id`` depends on / calls ``to_id``.
Both services must already exist (add them with kg_add_service first).
``style`` is one of solid/dashed/dotted/thick.