- Home
- MCP servers
- sqlew
sqlew
- typescript
2
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"sin5ddd-mcp-sqlew": {
"command": "npx",
"args": [
"sqlew"
]
}
}
}sqlew is an MCP server that provides AI agents with a shared SQL-backed context repository across sessions. It centralizes decisions, constraints, tasks, and related context so your agents can recall why changes were made and how to proceed, reducing context rot and boosting consistency across multi-agent work.
How to use
Use sqlew to give your AI agents a persistent, queryable history of decisions and constraints. Interact with sqlew through an MCP client interface that detects your intent and routes actions to the appropriate tools. You can record decisions, define constraints, manage tasks, and query past work to guide current and future AI behavior. All access runs locally for security, and you benefit from reduced token usage through structured data instead of dumping full context into prompts.
Key workflows include recording a decision with the rationale behind it, listing existing constraints to ensure consistency, planning and tracking tasks, and searching past decisions to reuse patterns. Tasks can be linked to decisions and files, enabling end-to-end traceability from plan to implementation.
How to install
Prerequisites you need before installing sqlew:
-
Node.js 20.0.0 or higher
-
npm
-
npx
Step-by-step setup and run flow:
-
Ensure you have Node.js and npm/npx installed.
-
In your project root, create a file named .mcp.json with the following content to configure sqlew as an MCP server.
{
"mcpServers": {
"sqlew": {
"command": "npx",
"args": ["sqlew"]
}
}
}
- Restart Claude after you initialize the server to ensure the new context is loaded for your sessions.
Available tools
decision
Record choices and reasons for design or implementation decisions, including rationale and alternatives considered.
constraint
Define rules and boundaries that guide how tasks are implemented and how code should be written.
task
Track work items, assign dependencies, and monitor progress across the feature development lifecycle.
file
Track changes to files and surface what was modified, when, and why.
stats
Provide metrics related to database usage, task progress, and decision history.
suggest
Find similar decisions to promote reuse and consistency across projects.