SQAI — deterministic, read-only structured data

io.github.thyn-aiPublished by GitHub account thyn-aiv0.1.20Updated Oct 27, 2026

SQAI MCP server — four governed, deterministic, read-only data tools. Free login to execute.

The publisher's own server: Deterministic

VerifiedSTDIODesktop onlyDatabasesData & Analytics

Overview

AI-generated overview

A local stdio MCP server that gives an assistant governed, deterministic, read-only query and computation tools over structured data sources such as CSV files.

What you can do
  • Discover sources, field names, types, allowed operations and computation signatures
  • Run one deterministic, read-only query or computation, with truncated results retrievable by result_id
  • Dry-run a query to see the resolved plan, plan hash and validation, or check a computation signature with a preview hash
When to use it
Useful when an assistant should answer questions over structured data such as CSV files without writing raw SQL or having any write path, and when you want policy-checked, replayable results with provenance.
Requirements
Runs locally via npx as a stdio server (Node.js). Sources are supplied through the SQAI_SOURCES environment variable as a JSON array of paths, URLs or inline row data. Executing tools requires a free community login (sqai login device registration) or the SQAI_API_KEY environment variable; introspection works without credentials. An optional SQAI_DEPLOYMENT_URL selects a private deployment.
Before you install
Every tool call, including local CSV reads, is gated by a license check and returns a login_required error without a login or SQAI_API_KEY. Licensing moves a signed token, and the computation plane provisions a signed managed runtime on first use. Sources may be given as URLs, which sends requests to those endpoints. Tools are declared read-only and non-destructive.

Installation

In SourceWeft

  1. Open SQAI — deterministic, read-only structured data in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

LayerPackageWhat it is
AI SDK tools@thyn-ai/sqai-ai-sdk (npm)Three Vercel AI SDK 7 tools — listSources, queryData, explainQuery
Product SDK@thyn-ai/sqai (npm)SQAI query plane + full computation plane
Product SDKsqai (PyPI)Same SQAI surface, 1:1 vocabulary
CLI@thyn-ai/sqai-cli (npm, bin sqai)sqai doctor --parity, sqai runtime install/verify/status/stop
Capability contractEmbedded SQAI contractThe generated, hash-pinned inventory of every capability SQAI exposes
Execution substrateAlgenta (exact-pinned)Underlying deterministic execution substrate and managed signed runtime bundle

Quickstart (AI SDK)

ts
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 four 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:

bash
npx @thyn-ai/sqai-mcp
json
{  "mcpServers": {    "sqai": {      "command": "npx",      "args": ["-y", "@thyn-ai/sqai-mcp"],      "env": {        "SQAI_SOURCES": "[{\"data\": \"./data/sales.csv\", \"name\": \"sales\"}]"      }    }  }}

Introspection (initialize / tools/list) needs no credentials — zero environment is a valid configuration. Executing any of the four tools requires a free community login (sqai login once / device registration, or SQAI_API_KEY) — fully offline thereafter; without it every tools/call returns a structured login_required error. SQAI_DEPLOYMENT_URL keeps its usual semantics from @thyn-ai/sqai.

ToolWhat it does
listSourcesDiscovery: sources with exact field names, types, and allowed operations; computation-catalog search; per-module signatures.
queryDataOne deterministic, read-only query or computation; truncated results stay retrievable via result_id.
explainQueryDry-run: resolved plan, plan_hash, validation — or a computation-signature check with a preview invocation_hash.

All three are annotated readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: false. All three execute under the one uniform license gate: free on 1 machine with a one-time device registration (sqai login) — licensing moves a signed token, never your data; without it, every tool call — local CSV reads included — returns a structured login_required error by design.

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_signature
  • Model-context truncation with opaque result handles

Repository layout

contracts/        generated capability contract + tested version pairpackages/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 gatedocs/             GitBook (docs.sqai.com)

Key documents

DocPurpose
docs/quickstart-ts.mdTypeScript quickstart
docs/quickstart-python.mdPython quickstart
docs/ai-sdk-tools.mdTool schemas and truncation contract
docs/determinism.mdHashes, envelopes, "deterministic within the declared execution scope"
docs/licensing.mdFree developer tier, entitlements, runtime bundle trust
SECURITY.mdSecurity policy

Source: README.md at commit 3ba3811

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

3
  1. v0.1.20LatestSep 25, 2026
  2. v0.1.18Sep 23, 2026
  3. v0.1.16Sep 23, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Deterministic integrations