PageVault MCP Server
Adds a GitLab adapter that enriches captured page snapshots with project metadata, so archived GitLab pages retain repository/project context alongside the extracted content.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
PageVault saves web page content in a local SQLite archive. Enable recording for a site to collect structured snapshots as you browse. Search saved pages, view earlier snapshots, export JSON or read the archive through an MCP client.
The Chromium and Firefox extensions share one implementation and capture loaded text, headings, lists, tables, code, links and media references. A GitLab adapter adds project metadata. The extension and Go helper run locally, without telemetry or a remote service.
Installation
Download PageVault-1.5.0.zip and its SHA-256 file from GitHub Releases. Extract the bundle to a permanent directory and verify the checksum.
Install the helper: run
./install.sh chromeon macOS or Linux, orinstall-windows.cmdon Windows. Selectchromium,edge,braveorfirefoxas needed; for example,./install.sh firefoxorinstall-windows.cmd firefox.For Chromium, open the browser's extensions page, enable developer mode and load the bundle's
extensionfolder. For Firefox 140+, use the Firefox package or the bundle'sextension-firefoxfolder as described in installation.Check the helper connection in PageVault settings. Open an HTTP(S) page, enable recording for its site and grant access. Use Capture now for a manual snapshot.
macOS 13 and later also support an unsigned installer for Intel and Apple Silicon. See installation for downloads, checksums and troubleshooting, and upgrading before replacing an existing installation.
Related MCP server: shop-sql-mcp
Capture and storage
Only loaded content is captured. Scroll or expand a page first. Media files are not downloaded, and the archive does not recreate an interactive site. An accumulated page contains unique blocks collected over time; select a snapshot to view one recorded state.
Saved pages may contain private data. Read the privacy policy and capture limits and queue recovery. Drain the queue before removing the extension.
Development
See contributing for setup, verification for checks and distribution for release builds.
Technical reference: architecture, data format, Native Messaging, MCP, site adapters.
PageVault is MIT licensed. See LICENSE, dependency notices and the security policy.
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Shared copies of public web pages for AI agents. Search stored pages or fetch a URL.
Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Related MCP Servers
- AlicenseAqualityDmaintenanceExposes SQLite database query tools and markdown document resources over JSON-RPC 2.0 stdio transport, enabling AI assistants to read and search documents and execute read-only SQL queries.81MIT
- FlicenseNot gradedqualityCmaintenanceProvides AI agents read-only analytical access to a SQLite database over stdio, with tools for listing tables, describing schemas, and running paginated SQL queries.-
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to read-only analyze a SQLite e-commerce database, exploring schema and running analytical SQL queries over stdio.-
- AlicenseNot gradedqualityCmaintenanceEnables AI models to securely analyze SQLite datasets and read local text documents through a local stdio interface. It provides read-only querying, schema discovery, pagination, and timeout protections to prevent data leaks or destructive changes.MIT