mcp-browserdata
Related Servers
Alternatives to mcp-browserdata
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables access to browser data (tabs, history, bookmarks) from Chromium-based browsers including Chrome, Brave, and Chromium, directly from local profile files without authentication.22 PyPIApache 2.0
- AlicenseNot gradedqualityBmaintenanceExposes 26 browser_* MCP tools that let an agent drive a local Chrome instance—opening and focusing tabs, reading pages, clicking, typing, uploading files, taking screenshots, recording GIFs, and inspecting console and network activity—even when the client runs inside Docker. Control is scoped to a dedicated tab group and protected by token authentication.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables access to browser data from Brave, Chrome, and Chromium — open tabs across all synced devices, browsing history with search and date filters, and bookmarks — by reading local profile files directly without authentication or network requests.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceExposes browser-drive tools over a local MCP endpoint, letting agents control isolated Chromium or Firefox profiles with their own cookies, fingerprints, and proxies to complete authenticated workflows across sessions. Supports profile lifecycle, navigation, clicking, typing, extraction, screenshots, JS evaluation, tabs, cookies, waits, and raw CDP calls.MIT
- FlicenseNot gradedqualityDmaintenanceEnables browser automation with AI agent support and secure credential management through 20 MCP tools, accessible via stdio or HTTP bridge.-
- AlicenseBqualityBmaintenanceEnables MCP clients to drive the Chrome or Edge tabs you already have open and signed in, by pairing with a local browser extension instead of launching a remote debugging port or a separate automation browser. Exposes 20 tools for accessibility-tree snapshots, clicking and filling, navigation, uploads, screenshots, JavaScript evaluation, and console and network log reading.24210 npm4MIT
TDQS
Scored across 12 tools
Each tool targets a distinct resource and action: browsers, cookies, bookmarks, credentials, site storage, sync, and export/import are all separate nouns paired with clear verbs. The read/write pairs (get_cookies/set_cookies, get_site_storage/set_site_storage) are trivially distinguishable, and sync_data's counters-only contract further separates it from the explicit per-kind getters.
All names follow a consistent snake_case verb_noun pattern with a small, well-defined verb vocabulary (list/get/set/add/sync/export/import). Minor deviation: reads alternate between `list_` (list_browsers, list_bookmarks) and `get_` (get_cookies, get_credentials, get_site_storage), and writes alternate between `set_` and `add_`, though the distinctions are semantically defensible.
At 12 tools the surface is well within the ideal 3-15 range and every tool maps to a genuine capability of the browser-data domain. No redundant or filler operations are present.
The surface covers discovery, read, write, migration, and backup/restore, but deletion is entirely absent: no remove_bookmark, delete_cookie, delete_credential, or remove_site_storage, so agents cannot undo writes. History and download data are also unaddressed, leaving notable gaps in the browse-and-manage lifecycle.