Nuncio is in active development — building in the open, not shipping vapor.
Planned: Model Context Protocol (MCP) Client

Sane & Controlled AI Agent Access

An MCP client is a planned, separate thin client over Nuncio's gRPC contract — the same one the CLI uses today. It does not exist yet. This page describes the design: aggregate your accounts, control exactly how agents touch them, and audit everything.

Nothing on this page is usable yet

Why a Gateway, Not Direct Access

The design principle: never grant an AI agent uncontrolled credentials to your real accounts.

1. One Local Vault, Not Scattered Credentials

The plan: aggregate every account you connect into one local SQLite vault an agent can query, instead of handing separate credentials to separate AI tools.

2. A Gateway, Not Direct Access

Local LLMs and AI agents are designed to never receive raw passwords or direct, uncontrolled access to your provider accounts. Every action would pass through Nuncio's security enclave under an RBAC policy.

3. Every Action, Audited

The goal is that every agent tool call, read, draft, and send lands in the same immutable, hash-chained WORM audit ledger that already exists for other engine actions today.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard from Anthropic that lets AI applications safely read data and invoke actions on local services over stdio JSON-RPC. Nuncio plans to expose a governed MCP surface once its client architecture is built — think of the examples below as the target experience, not something you can do today.

1. Natural Language Triage

Eventually: "Find urgent emails from today across all my accounts and summarize them."

2. Autonomous Scheduling

Eventually: "Schedule a sync tomorrow afternoon and create the event." Depends on CalDAV, which is also planned.

3. Automated NSQL Rules

Eventually: "Create a rule to auto-archive newsletters." Rule creation works today via the CLI; wiring it to an agent is future work.

Target Configuration Shape

This is what an MCP client config would look like once it exists — it will not connect to anything today.

Target Config Shape (`claude_desktop_config.json`)

No `nuncio-mcp` binary exists to run this yet
Preview — won't connect
{
  "mcpServers": {
    "nuncio": {
      "command": "nuncio-mcp",
      "args": ["--stdio"]
    }
  }
}

Planned Security Enclave

You would control exactly what data and permissions any connected AI agent gets. None of this is built yet.

Capability Flags & Permissions

Toggle fine-grained capabilities per agent: read_mail, send_mail, read_calendar, write_calendar, and manage_filters. Unauthorized operations would be rejected.

Sensitive Data Redaction

Before message text reaches an LLM context window, sensitive identifiers would be masked automatically. This redaction pipeline does not exist yet.

Planned MCP Tool Surface

The tool names an eventual MCP client would expose — none of these are callable by an AI agent today.

nuncio_mail_listEmail

List messages with folder, account, and unread filters.

nuncio_mail_sendEmail

Draft or send email with human-in-the-loop confirmation.

nuncio_mail_searchEmail

Full-text search across synced mail.

nuncio_export_dataData Export

Export MBOX, EML, or JSON data programmatically.

nuncio_audit_listWORM Audits

Query the immutable audit log.

nuncio_audit_verifyWORM Audits

Verify the HMAC-SHA256 hash-chain ledger.

nuncio_cal_list_eventsCalendar

Query calendar events, once calendar sync exists.

nuncio_cal_create_eventCalendar

Create calendar events with conflict detection.

nuncio_filter_listNSQL Filters

Inspect NSQL filter rules and execution logs.

nuncio_filter_createNSQL Filters

Compile, validate, and save a new NSQL rule.

nuncio_filter_testNSQL Filters

Dry-run test an NSQL rule against a sample message.

nuncio_account_listAccounts

Inspect connected accounts and protocol status.