sqai-mcp
OfficialClick 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., "@sqai-mcpWhich region had the highest total revenue last quarter?"
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.
SQAI — Structured Query AI
SQAI is the deterministic, read-only structured-data tool for AI agents, with governed execution and replayable provenance.
Apache-2.0 · TypeScript + Python · built on Algenta as the underlying substrate · a Thyn product
The model proposes meaning. SQAI controls execution: typed intent in, policy-checked deterministic execution, replayable results with full provenance out. No raw SQL, no eval, no write path.
Architecture
Layer | Package | What it is |
AI SDK tools |
| Three Vercel AI SDK 7 tools — |
Product SDK |
| SQAI query plane + full computation plane |
Product SDK |
| Same SQAI surface, 1:1 vocabulary |
CLI |
|
|
Capability contract | Embedded SQAI contract | The generated, hash-pinned inventory of every capability SQAI exposes |
Execution substrate | Algenta (exact-pinned) | Underlying deterministic execution substrate and managed signed runtime bundle |
Related MCP server: governed-rag-mcp
Quickstart (AI SDK)
import { generateText } from "ai";
import { createSQAI } from "@thyn-ai/sqai-ai-sdk";
const sqai = createSQAI({ sources: [{ data: "./data/sales.csv", name: "sales" }] });
const { text } = await generateText({
model: "openai/gpt-5-mini",
tools: sqai.tools(),
prompt: "Which region had the highest total revenue?",
});No server. No daemon for the query plane. The computation plane provisions a signed managed runtime transparently on first use.
MCP server
The same three governed tools are available to any MCP host (Claude Desktop, Cursor, …) as a stdio server — descriptions, Zod schemas, and execute functions are read straight off the AI-SDK tool objects, never forked:
npx @thyn-ai/sqai-mcp{
"mcpServers": {
"sqai": {
"command": "npx",
"args": ["-y", "@thyn-ai/sqai-mcp"],
"env": {
"SQAI_SOURCES": "[{\"data\": \"./data/sales.csv\", \"name\": \"sales\"}]"
}
}
}
}Zero environment is a valid configuration: initialize and tools/list answer
with no credentials (sources connect lazily on the first tool call). SQAI_API_KEY
and SQAI_DEPLOYMENT_URL keep their usual semantics from @thyn-ai/sqai.
Tool | What it does |
| Discovery: sources with exact field names, types, and allowed operations; computation-catalog search; per-module signatures. |
| One deterministic, read-only query or computation; truncated results stay retrievable via |
| Dry-run: resolved plan, |
All three are annotated readOnlyHint: true, destructiveHint: false,
idempotentHint: true, openWorldHint: false. The computation plane is free on
1 machine with a one-time device registration (sqai login) — licensing moves a
signed token, never your data; without it, computation calls return a structured
licensing error by design and queries keep working.
What works today
Query plane (connect / resolve / query / verify / ask) — in-process, both languages
Full SQAI computation plane behind capability-contract validation
Policy allow-lists (sources, fields, functions) the model can never override
Cross-language conformance: identical values,
plan_hash,intent_signatureModel-context truncation with opaque result handles
Repository layout
contracts/ generated capability contract + tested version pair
packages/sdk/ @thyn-ai/sqai (TypeScript product SDK)
packages/ai-sdk/ @thyn-ai/sqai-ai-sdk (Vercel AI SDK tools)
packages/cli/ sqai CLI (doctor, runtime verbs)
packages/mcp/ @thyn-ai/sqai-mcp (MCP stdio server)
packages/python-sdk/ sqai (PyPI)
examples/ runnable examples (AI SDK registry example)
scripts/ contract sync + parity gate
docs/ GitBook (docs.sqai.com)Key documents
Doc | Purpose |
TypeScript quickstart | |
Python quickstart | |
Tool schemas and truncation contract | |
Hashes, envelopes, "deterministic within the declared execution scope" | |
Free developer tier, entitlements, runtime bundle trust | |
Security policy |
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
- BasedashOAuthcom.basedash
Governed BI MCP. Ask questions of live company data and list workspace sources via OAuth.
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA read-only MCP server for querying telemetry data from configurable backends. Provides tools to list sources, describe schemas, run bounded queries, and compute aggregates.MIT
- AlicenseAqualityBmaintenanceProvides governed retrieval over MCP with hybrid search, strict confidence gating, and access control, exposing three read-only tools.3Apache 2.0

MCP DB Gatewayofficial
AlicenseNot gradedqualityBmaintenanceProvides governed, read-only PostgreSQL access for AI agents via MCP. Enforces schema/table allowlists, query limits, and audit events.MIT- FlicenseNot gradedqualityAmaintenanceProvides a stdio MCP server for Codex to inspect and query configured datasources, with tools for health checks, read-only queries, metadata, and fixed physical sessions with audit trails.19 npm-