Skip to content
SPECIFICTION
Get listed

Tablix

tablix.ai

WebAPISelf-hosted
Visit tablix.ai
Spec score 6.9 #19 of 21 in AI Database Assistants

What it is

Tablix is an open-source, self-hosted.NET server and React dashboard for asking natural-language questions of databases. It connects to SQLite, PostgreSQL, MySQL, and SQL Server and returns answers with executed SQL, rows, row counts, and evidence. It scans tables, keys, indexes, and relationships, then creates editable database and table context. Workflows are available in the dashboard, through MCP for agents, and through REST for applications and automation. The dashboard includes setup, schema browsing, context editing, query execution, chat, and CSV or JSON exports. Tablix can use Ollama, OpenAI, OpenAI-compatible endpoints, or Gemini; database chat and MCP require tool-calling support. Statement types can be allowed per database, calls are scoped to the selected connection, and multi-statement SQL is rejected. The project states there is no cloud dependency or telemetry, with outbound calls limited to the configured model provider. Docker Compose starts the server, dashboard, MCP endpoint, state, and sample SQLite database.

Spec sheet

What it does
Tablix connects databases to people and AI agents so they can ask natural-language questions and get answers backed by executed queries.Read 7 Oct 2026 · tablix.ai
Product
Tablix is a self-hosted .NET server and React dashboard for asking natural-language questions of databases.Read 7 Oct 2026 · tablix.ai
Intended users
The site identifies coding agents, data and platform teams, AI engineers, DevOps and SRE teams, and teams onboarding legacy schemas as use cases.Read 7 Oct 2026 · tablix.ai
Deployment
Docker Compose starts the server, dashboard, MCP endpoint, product state, and a sample SQLite database.Read 7 Oct 2026 · tablix.ai
Privacy
Tablix is self-hosted and states that it has no cloud dependency or telemetry; outbound calls go to the configured model provider, or none when using local Ollama.Read 7 Oct 2026 · tablix.ai
License
The site describes Tablix as MIT licensed.Read 7 Oct 2026 · tablix.ai
Access methods
Tablix provides a dashboard, an MCP endpoint for agents, and a REST API for applications and automation.Read 7 Oct 2026 · tablix.ai
Agent clients
The site names Claude, Codex, Cursor, and Gemini as MCP clients that can connect to Tablix.Read 7 Oct 2026 · tablix.ai
Dashboard
The built-in dashboard includes setup, schema browsing, context editing, query running, chat, and CSV/JSON exports.Read 7 Oct 2026 · tablix.ai
Data handling
Tablix says it is self-hosted and has no cloud dependency or telemetry; outbound calls go only to the configured model provider, and local Ollama requires none.Read 7 Oct 2026 · tablix.ai
Database support
The same server and dashboard can connect to SQLite, PostgreSQL, MySQL, and SQL Server.Read 7 Oct 2026 · tablix.ai
Interfaces
Tablix exposes workflows through its dashboard, MCP for agents, and REST for applications and automation.Read 7 Oct 2026 · tablix.ai
Maturity
The site describes Tablix as early software and says it fits internal tools, development environments, and read-only production access with proper database permissions.Read 7 Oct 2026 · tablix.ai
Model integrations
It can be configured to use Ollama, OpenAI, OpenAI-compatible endpoints, or Gemini; database chat and MCP workflows require tool-calling support.Read 7 Oct 2026 · tablix.ai
Model providers
It can configure Ollama, OpenAI, OpenAI-compatible endpoints, and Gemini; database chat and MCP require tool-calling support.Read 7 Oct 2026 · tablix.ai
Query controls
Statement types can be allowed per database, calls are scoped to the selected connection, and multi-statement SQL is rejected.Read 7 Oct 2026 · tablix.ai
Schema context
It crawls database tables, keys, indexes, and relationships, then generates editable database and table context.Read 7 Oct 2026 · tablix.ai
Security limitation
The project README says database passwords and provider API keys are stored in cleartext in tablix.db for v0.3.0 and recommends protecting that file with OS-level permissions.Read 7 Oct 2026 · github.com
Verified answers
Database chat returns answers backed by executed queries, with SQL, returned rows, row counts, and evidence.Read 7 Oct 2026 · tablix.ai

Strong points and limits

Strong points

  • Answers include executed SQL and evidence
  • Supports four database systems
  • Provides dashboard, MCP, and REST access
  • No cloud dependency or telemetry
  • Supports local Ollama deployment

Limits

  • Described as early software
  • Database chat requires tool-calling support
  • Secrets are stored cleartext in tablix.db for v0.3.0
  • Proper database permissions remain necessary

Who it suits

It suits coding agents, data and platform teams, AI engineers, DevOps and SRE teams, and teams onboarding legacy schemas. The project describes internal tools, development environments, and read-only production access as use cases.

Verdict

Tablix links databases with people and agents while exposing the query evidence behind answers. Its self-hosted design and connection controls are useful, but the early status and cleartext secret storage require attention.

Where Specifiction places it

Alternatives to TablixAll alternatives →