About Stapler MCP
Stapler MCP is an MCP server in the Communication category: rust reimplementation of several MCP servers as a thin-client + shared-daemon — one shared process machine-wide instead of a per-session npx/uvx spawn per subagent.
Install
From source
git clone https://github.com/tstapler/stapler-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (13)
brave_web_searchStateless HTTP wrapper over the Brave Search API. Reads `BRAVE_API_KEY` from the **daemon's** environment. Base URL overridable via `BRAVE_API_BASE_URL` (used by both adapters' test suites to point at a mock server).
Parameters not published.
download_websiteSame crawl/`robots.txt` mechanics as `read_website`, saves raw HTML per page under `saveDir` instead of extracting Markdown. Merges what were two separate third-party MCP servers this user ran before.
Parameters not published.
fetch_pageHeadless-render a URL, return title + extracted text, optionally save rendered HTML to a local path (`savePath`).
Parameters not published.
read_saved_pageSearch (`query`, with `contextLines` of surrounding context — like `grep -n -C`) or paginate (`offset`/`limit`, line-numbered — like `Read`) a page previously saved by `read_website`'s `savedPath`. Only ever reads a path matching that mechanism's own naming scheme, never an arbitrary file. Works even when the caller isn't on the same machine as the daemon.
Parameters not published.
read_websiteFetch a URL (optionally BFS-crawling same-host links up to `maxDepth`/`maxPages`), extract main content via Readability-style extraction, return it as Markdown. Cached by URL hash on the daemon — a cache hit skips the network fetch entirely (at the cost of not expanding that page's links further). Respects `robots.txt`. Once the combined Markdown across every page returned passes ~60,000 characters (tunable via `maxInlineChars`, or force it for every page with `alwaysSaveToFile`), further pages come back as a short preview plus `savedPath` instead of the full text, so a long crawl can't crowd out the rest of the caller's context.
Parameters not published.
stapler_browser_close_all_sessionsClose every open session daemon-wide and report which succeeded/failed. Closes are attempted concurrently so one wedged session doesn't block the rest. **No per-caller scoping**: this closes sessions daemon-wide regardless of which caller opened them — safe for a single-agent daemon, but a multi-tenant daemon would need real authorization before exposing it.
Parameters not published.
stapler_browser_close_sessionClose a browser session and release its resources ahead of the idle-timeout reaper.
Parameters not published.
stapler_browser_hoverHover the pointer over an element identified by a snapshot `ref`, for triggering hover-revealed UI.
Parameters not published.
stapler_browser_list_sessionsList all open sessions daemon-wide (session id, tab count, idle time in milliseconds, and `blocked`/`crashed` diagnostic flags) — useful for finding sessions leaked by a crashed subagent.
Parameters not published.
stapler_browser_press_keyPress a single keyboard key, optionally focusing an element by `ref` first.
Parameters not published.
Show all 13 tools
stapler_browser_select_optionSelect one or more options in a `<select>` element identified by a snapshot `ref`.
Parameters not published.
stapler_browser_tabsList/open/switch/close tabs within a session via an `action` field (`list`/`new`/`select`/`close`), mirroring `@playwright/mcp`'s `browser_tabs`.
Parameters not published.
stapler_browser_wait_forWait until given text appears/disappears and/or a minimum time elapses before returning the next snapshot.
Parameters not published.
Ask AI
✦
Ask AI about Stapler MCP
Powered by Claude · Grounded in docs
I know everything about Stapler MCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.