Memory for AI coding agents. Persistent code graph + AI-generated architecture diagrams — MCP-native. Works in Cursor, Claude Code, Codex, and Windsurf.
Dogfood benchmark on our own monorepo: 99.4% token reduction (156.8× ratio) across 8 "where is X implemented?" queries — 114,644 tokens via file re-read vs 731 tokens via query_symbols. Full write-up →
cd your-repo
npx tentra-mcp init --hookOne command:
- Writes MCP config for Cursor / Claude Code / Codex / Windsurf (whichever are installed)
- Installs a git
post-commithook so the code graph auto-refreshes after every commit — no manual re-indexing - Auto-derives your
repo_idfrom the git remote and saves it to.tentra/metadata.json
Then grab your API key at trytentra.com/settings, replace YOUR_TENTRA_API_KEY in the generated config, reload your IDE, and ask your agent:
Index this codebase with Tentra and list the god-nodes
From here on, every git commit fires a background re-index. Your agents stay caught up automatically.
Skip the hook: drop
--hook— just writes IDE configs. Manual stdio install:npx tentra-mcp(opens browser for GitHub device-flow auth on first tool call). API key instead:npx tentra-mcp --key YOUR_API_KEY.
Tentra is an AI-native architecture platform for engineering teams. Describe a system — get a diagram and 14-framework code exports. Index your repo — agents query a structured graph of files, symbols, imports, and call edges instead of re-grepping source every session.
This MCP server gives your AI assistant 36 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 |
get_spec_alignment |
Mid-implementation drift check — changed files in, spec context + drift signals out |
export_architecture |
Export to 14 frameworks (Java, Python, Go, Rust, etc.) |
create_flow |
Create step-by-step flow visualization |
| 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 |
| Tool | Description |
|---|---|
query_symbols |
Fuzzy trigram search across indexed symbols |
find_references |
Every resolved caller of a symbol — refactor-safety primitive |
safe_rename |
Patch plan (definition + every call site) for renaming a symbol |
explain_codebase |
Agent-ready narrative walkthrough of a whole repo |
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 |
| 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 |
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"
}
}
}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"]
}
}
}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 score
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
- Website: trytentra.com
- Documentation: trytentra.com/docs
- Setup Guide: trytentra.com/docs/setup
- Gallery: trytentra.com/gallery
This repo contains the open-source MCP server. The Tentra API and web app are a separate hosted service at trytentra.com.
npm install --legacy-peer-deps
npm run build # tsc --noEmit + esbuild bundle → dist/index.js
npm start # run the bundled server
npm test # vitestThe published npm package (tentra-mcp) ships only the bundled dist/ — source is here for auditability and community contributions.
MIT