
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
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.
Installation
In SourceWeft
- Open SQAI — deterministic, read-only structured data in the dashboard and add it to a workspace.
- 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
Quickstart (AI SDK)
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:
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.
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
Key documents
Source: README.md at commit 3ba3811
Tools
0Version history
3- v0.1.20LatestSep 25, 2026
- v0.1.18Sep 23, 2026
- 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
Deterministic
sh.deterministicOfficial publisher
A remote MCP server that gives an assistant physics-based validation of simulation results, returning receipts with per-check verdicts.
EU EN-16931 & XRechnung Deterministic Validator
eu.iotpay
Remote MCP endpoint that validates EN 16931 and XRechnung e-invoice XML and issues signed Ed25519 verifiable credentials.

Website Change Monitor & Deterministic Diff
Published by GitHub account industrial-platform-ai
Paid remote MCP service that detects deterministic changes in public web pages, returning hashes and text diffs for recurring monitoring.

Deterministic
Published by GitHub account archradhq
ArchRAD Deterministic validates architecture graphs (IR) against deterministic lint rules, drafts IR from repos, and checks design-versus-code drift.
Quesen Deterministic Agent Decision Layer
Published by GitHub account Shxnque
Remote MCP endpoint that gives an agent deterministic PROCEED/REVIEW/SKIP risk verdicts, with reason codes and replayable receipts, before it acts.