$ loading_
Provide agents a compact backend with SQLite, auth, realtime, and safe writes.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mekka" yet — see the docs or source repo.
Use mekka via MCP to inspect the current SQLite schema and main table contents in read-only mode. Do not modify anything, and summarize the fields available for further analysis.
Returns the schema, key table overview, and available field descriptions without performing any writes.
Based on the existing data, prepare a change plan to add new profile fields. First stage the read-write changes in an isolated preview branch and show the exact SQL to be executed, then wait for my approval before continuing.
Outputs a staged change plan and exact SQL in a preview branch for human review before any production promotion.
Summarize the backend capabilities available in mekka, including the SQLite data plane, embedded Studio, auth, storage, realtime features, and the default permission model for agents.
Provides a list of backend components and explains the default read-only access with optional controlled writes.
Developers can expose backend capabilities to agents through a scoped MCP server. Agents get read-only access by default, reducing the risk of accidental production writes.
When an agent needs to perform writes, teams can first review changes in an isolated preview branch. Changes are promoted to production only after the exact SQL is shown and approved.
It fits scenarios that need SQLite, auth, storage, realtime features, and an embedded Studio. It bundles these backend capabilities into one platform for agents.
It is a compact backend platform that exposes a scoped MCP server to AI agents. The description says it includes a SQLite data plane, embedded Studio, auth, storage, and realtime features.
Agents have read-only access by default. To enable read-write mutations, changes go through isolated preview branches and require approval of the exact SQL before promotion to production.
The provided information does not include installation steps, runtime requirements, or key configuration details. For prerequisites, see the source repository.
Helps LLM agents discover, register, and run local and remote MCP tools.
Secure, token-efficient MySQL access for AI agents with query safeguards.
Manage MySQL databases with natural language for queries, CRUD, and monitoring.
Create, manage, and compose AI agents for MCP-compatible clients and tools.
Securely query and analyze multiple databases with natural language across systems.
Safely let AI query PostgreSQL, MySQL, and SQLite in read-only mode.