AURON MCP
Resolves AURON principal identity and RBAC permissions via GET /api/auth/verify/ and GET /api/tenants/current/, mirroring AURON's canonical roles for fail-closed authorization.
Mentioned as a test runner for the server's 78 tests covering policy, RBAC, audit, rate limiting, adapters, identity provider, tools, and MCP handshake.
The MCP server is implemented in Python and uses Python tools like pytest for testing and ruff for linting.
Used as a code linter/formatter for Python source code in the project.
Not identified as a target service; mentioned only as an implementation dependency (e.g., Ruff is built in Rust).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AURON MCPwhat's today's sales summary?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AURON MCP — v1 (read-only, multi-tenant, production-lean)
MCP gateway between AI hosts/agents and the AURON Suite backend
(api_peluqueria). Identity, tenancy, and RBAC are resolved from the real
AURON REST API — the model can never steer them.
What this is
Read-only: every tool is a GET against a verified AURON endpoint. No create/update/delete is exposed.
Real identity: resolves the authenticated AURON principal via
GET /api/auth/verify/+GET /api/tenants/current/(Bearer token or the httpOnly auth cookies that/api/auth/login/issues).Fail-closed RBAC: role → permission mirror (
policy/roles.py) derived from AURON's canonical roles. Unknown roles get zero permissions; AURON's own authorization (403) still overrides the table.Tenancy delegated to AURON: the adapter NEVER sends
tenant_idor anX-Auron-Tenantheader. The upstream derives the tenant from the session via itsTenantMiddleware, exactly like AURON's own clients.Error boundary: nothing internal (messages, tokens, upstream bodies, stack traces) reaches the model — see
errors/normalize_error.Per-call audit: every tool call (success or denied) is written to an append-only JSONL audit log and stdout.
Rate limiting: per-(user, tool) sliding-window limiter checked before policy on every call.
Related MCP server: FinOps AI Copilot MCP Server
Tools
Tool | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Compound: sales + appointments + inventory + employee performance |
| Compound: products + low-stock alerts |
| Compound: dashboard stats + today's sales |
| Compound: performance + employee roster |
|
|
Plus a auron://context/current resource and a daily_business_review prompt.
Quick start
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"Copy .env.example to .env and set the real values:
AURON_ADAPTER=http
AURON_API_BASE_URL=http://localhost:8000Authenticate once (this stores AURON's httpOnly auth cookies for the gateway):
auron-manage login --email caja@salon.test --subdomain salon-uno
auron-manage status # verify the resolved identity/roleRun the server:
auron-mcp # stdio (default; what local MCP hosts expect)Run over Streamable HTTP (spec 2026-07-28) instead:
AURON_MCP_TRANSPORT=streamable-http \
AURON_MCP_HTTP_HOST=127.0.0.1 \
AURON_MCP_HTTP_PORT=8765 \
auron-mcp # serves the MCP endpoint at http://127.0.0.1:8765/mcpThe HTTP deployment validates the MCP-Protocol-Version / Mcp-Method /
Mcp-Name request headers against the JSON-RPC body (400 + -32020
HeaderMismatch), rejects non-POST with 405, and enables DNS-rebinding
protection. See docs/CONNECTING.md for the full endpoint contract and
src/auron_mcp/http_app.py for the spec layer on top of the SDK transport.
With AURON_ADAPTER=mock (default) the server works offline with a fixed
dev identity (u-mock-1 / t-mock-1 / CLIENT_ADMIN) for development and
testing only.
Tests
pytest -q # 78 tests: policy, rbac, audit, ratelimit, adapters,
# identity provider, tools, MCP stdio handshake, and the
# 2026-07-28 Streamable HTTP header rules
ruff check src testsLayout
src/auron_mcp/
auth/ identity.py (AuronIdentity) + provider.py (resolve via AURON)
policy/ roles.py (RBAC mirror) + engine.py (PolicyEngine, fail-closed)
audit/ AuditLogger (JSONL + stdout)
adapters/ base.py (interface) / http.py (httpx2 + cookies) / mock.py
tools/ AuronTools (policy + rate-limit + audit around every read)
errors/ normalize_error (model-safe error boundary)
server.py MCPServer wiring (stdio / streamable-http / sse)
http_app.py Streamable HTTP deployment: 2026-07-28 header validation,
DNS-rebinding settings, optional bearer token
manage.py operator CLI: login / status / cleanSecurity principles
Never trust a tenant ID supplied by an LLM as an authorization boundary.
Resolve tenant/scope from authenticated identity and server-side policy.
Tools are read-only; side effects are intentionally out of scope for v1.
Every sensitive action is auditable — including denied attempts.
MCP calls stable AURON application APIs, never raw SQL.
Never expose secrets, JWTs, upstream response bodies, or stack traces to the model.
A tool call has a cost — rate-limit it.
See docs/mcp-integration-audit.md (audit of the real AURON backend),
docs/ARCHITECTURE.md, docs/CONNECTING.md, and docs/ROADMAP.md.
This server cannot be deployed
Maintenance
Related MCP Connectors
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
Read-only access to your VortexIQ store data: audits, KPIs, alerts, Brand DNA, reports, Ask VIQ.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
Let AI agents query data and act across all your business apps via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePublic read-only MCP server for FoxTrove Voice, enabling LLMs to query call logs, customer records, assistant stats, and analytics via secure OAuth.MIT
- FlicenseBqualityCmaintenanceA secure, read-only MCP server that enables AI assistants to inspect transactions, vendor performance, wallet balances, and analytics through validated REST API calls.19-
- AlicenseNot gradedqualityAmaintenanceRead-only MCP server for the Helcim payment API, letting AI agents safely query customers, invoices, card transactions, subscriptions, and more without risking financial mutations.MIT
- AlicenseNot gradedqualityAmaintenanceProvides a secure, policy-driven read-only gateway that exposes multiple databases to AI tools via MCP, with governed select, search, and aggregate operations and no free-form SQL.Apache 2.0