# MCP · Tech watch

[Canonical source](<https://sebastien.rigaux.be/en/tech-watch/tags/mcp>)

An integration protocol connecting AI applications, tools and context sources.

## [OpnForm: open-source forms for cloud or self-hosted deployments](<https://sebastien.rigaux.be/en/tech-watch/links/opnform-open-source-forms-for-cloud-or-self-hosted-deployments>)

OpnForm is an open-source form builder available as both a managed cloud service and a self-hosted application. Its repository documents practical operational details: bundle-size limits, PostgreSQL index migrations that keep writes available, isolated Docker environments for worktrees, and dependency security checks. It also provides an MCP server that lets AI agents create and preview drafts, with versioned previews that support restoring earlier revisions.

2026-10-29 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/opnform-open-source-forms-for-cloud-or-self-hosted-deployments.md>) · [Original resource](<https://github.com/OpnForm/OpnForm>)

## [prompts.chat: AI prompts integrated with developer tools](<https://sebastien.rigaux.be/en/tech-watch/links/promptschat-ai-prompts-integrated-with-developer-tools>)

prompts.chat brings together community prompts for ChatGPT, Claude, Gemini, and other assistants, alongside an interactive book on prompt engineering. The repository also provides a CLI, a Claude Code plugin, and an MCP server for using prompts across different tools.

For a team, self-hosting provides a private prompt library with custom branding and authentication configured by the setup wizard. The integration examples range from `npx prompts.chat` to a remote MCP connection, without requiring a single access method.

2026-10-28 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/promptschat-ai-prompts-integrated-with-developer-tools.md>) · [Original resource](<https://github.com/f/prompts.chat>)

## [Data API builder: REST, GraphQL and MCP for your databases](<https://sebastien.rigaux.be/en/tech-watch/links/data-api-builder-rest-graphql-and-mcp-for-your-databases>)

Data API builder generates REST and GraphQL endpoints, as well as MCP tools, from Azure databases and on-premises stores. It supports several backends, including Azure SQL, SQL Server, PostgreSQL, MySQL and Cosmos DB, and runs in a container or locally during development.

Configuration defines entities and their permissions; DAB then translates requests into SQL. This layer reduces the API code teams need to maintain, while access remains shaped by the configuration and each database’s capabilities.

2026-10-22 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/data-api-builder-rest-graphql-and-mcp-for-your-databases.md>) · [Original resource](<https://github.com/Azure/data-api-builder>)

## [Engram: persistent memory for MCP-compatible AI agents](<https://sebastien.rigaux.be/en/tech-watch/links/engram-persistent-memory-for-mcp-compatible-ai-agents>)

Engram provides **persistent memory** for AI agents, compatible with any agent supporting the MCP protocol (Claude Code, Gemini CLI, Codex, VS Code, etc.). The tool runs as a single Go binary with no external dependencies, storing memories in a SQLite file with built-in FTS5 search. It features a TUI, Git sync, and a self-hostable cloud extension, while remaining local-first and open source under the MIT license.

2026-10-16 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/engram-persistent-memory-for-mcp-compatible-ai-agents.md>) · [Original resource](<https://engram.gentlemanprogramming.com/>)

## [An evidence-graded index of the Jev ecosystem](<https://sebastien.rigaux.be/en/tech-watch/links/an-evidence-graded-index-of-the-jev-ecosystem>)

Awesome Jev Live indexes SDKs, MCP tools, agents, apps, and open models related to TypeSafe System One. Entries are graded by evidence and organized by category and language; the catalog rebuilds every two hours to track changes across the ecosystem.

2026-10-05 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/an-evidence-graded-index-of-the-jev-ecosystem.md>) · [Original resource](<https://github.com/wh000wh000/awesome-jev-live>)

## [DBX: one cross-platform client for 100+ databases](<https://sebastien.rigaux.be/en/tech-watch/links/dbx-one-cross-platform-client-for-100-databases>)

DBX is a cross-platform database client advertised at 25 MB, with support for more than 100 systems including PostgreSQL, SQLite, Redis, MongoDB, and DuckDB. The repository combines a desktop app, CLI, MCP server, and AI features, bringing several database workflows together.

2026-10-04 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/dbx-one-cross-platform-client-for-100-databases.md>) · [Original resource](<https://github.com/t8y2/dbx>)

## [Map a repository to guide code reviews with Code Review Graph](<https://sebastien.rigaux.be/en/tech-watch/links/map-a-repository-to-guide-code-reviews-with-code-review-graph>)

Code Review Graph builds a local graph of a codebase and exposes it through MCP and CLI tools. It aims to give agents relevant context without loading the entire repository every time.

2026-03-23 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/map-a-repository-to-guide-code-reviews-with-code-review-graph.md>) · [Original resource](<https://github.com/tirth8205/code-review-graph>)

## [Bring current library docs into coding agents with Context7](<https://sebastien.rigaux.be/en/tech-watch/links/bring-current-library-docs-into-coding-agents-with-context7>)

Context7 gives coding agents documentation snippets for a specific library and version. It helps reduce answers based on outdated or guessed APIs.

2026-02-26 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/bring-current-library-docs-into-coding-agents-with-context7.md>) · [Original resource](<https://context7.com/>)

## [Expose Storybook to an agent through MCP](<https://sebastien.rigaux.be/en/tech-watch/links/expose-storybook-to-an-agent-through-mcp>)

This article shows how to expose a Storybook-documented React library through a local MCP server. Component manifests let an agent consult design-system rules before generating code.

2026-02-06 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/expose-storybook-to-an-agent-through-mcp.md>) · [Original resource](<https://alexocallaghan.com/react-design-system-library-mcp>)

## [Vibium: give agents browser verification tools](<https://sebastien.rigaux.be/en/tech-watch/links/vibium-give-agents-browser-verification-tools>)

Vibium exposes navigation, forms, clicks and screenshots through CLI, MCP or client libraries. It uses WebDriver BiDi so agents can verify changes in a real interface.

2025-12-28 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/vibium-give-agents-browser-verification-tools.md>) · [Original resource](<https://github.com/VibiumDev/vibium>)

## [Mastra 101: learn to build agents inside your editor](<https://sebastien.rigaux.be/en/tech-watch/links/mastra-101-learn-to-build-agents-inside-your-editor>)

This practical course guides the creation and deployment of Mastra agents. Tools, memory and MCP are introduced through a guided workflow inside the code editor.

2025-06-11 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/mastra-101-learn-to-build-agents-inside-your-editor.md>) · [Original resource](<https://mastra.ai/course>)

## [CentralMind Gateway: expose a database through MCP and OpenAPI](<https://sebastien.rigaux.be/en/tech-watch/links/centralmind-gateway-expose-a-database-through-mcp-and-openapi>)

Gateway generates an MCP or REST interface from a database connection. It provides a bridge for connecting agents to data without implementing every endpoint manually.

2025-04-22 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/centralmind-gateway-expose-a-database-through-mcp-and-openapi.md>) · [Original resource](<https://github.com/centralmind/gateway>)

## [Anyquery: query files and applications with SQL](<https://sebastien.rigaux.be/en/tech-watch/links/anyquery-query-files-and-applications-with-sql>)

Anyquery extends SQLite through plugins that query files and application services. It also offers an MCP connection for making those sources available to AI assistants.

2025-04-22 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/anyquery-query-files-and-applications-with-sql.md>) · [Original resource](<https://github.com/julien040/anyquery>)

## [An MCP server for debugging Node.js at runtime](<https://sebastien.rigaux.be/en/tech-watch/links/an-mcp-server-for-debugging-node-js-at-runtime>)

This server exposes the Node.js debugger to assistants such as Cursor and Claude Code. It adds runtime information to the context available for diagnosing problems.

2025-03-29 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/an-mcp-server-for-debugging-node-js-at-runtime.md>) · [Original resource](<https://github.com/workbackai/mcp-nodejs-debugger>)

## [Discover and manage MCP servers and skills in VS Code](<https://sebastien.rigaux.be/en/tech-watch/links/discover-and-manage-mcp-servers-and-skills-in-vs-code>)

This extension combines discovery, installation and management of MCP servers and skills. It makes those resources available to coding agents used alongside the editor.

2025-03-11 · [Markdown](<https://sebastien.rigaux.be/en/tech-watch/links/discover-and-manage-mcp-servers-and-skills-in-vs-code.md>) · [Original resource](<https://github.com/VikashLoomba/copilot-mcp>)
