Summary
Pre-computed navigation paths for public websites, built to cut token usage when agents interact with browser automation. Instead of exploring a site's UI from scratch each time, your agent gets direct shortcuts (like jumping straight to YouTube search results) and step-by-step cheatsheets for common tasks (sharing a Notion doc, triaging Linear bugs). The system learns from actual agent runs and drops paths that stop working. During beta it's free with no auth required. Connect via the streamable HTTP transport and skip the expensive exploration phase when automating repetitive web workflows. Best for agents that hit the same public sites repeatedly where you're paying for redundant navigation tokens.
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Tools
Public tool metadata for what this MCP can expose to an agent.
2 tools
askPre-computed navigation recipes for public websites. CALL BEFORE any browser action on the open web (navigate, click, fetch, fill, URL guess) — replaces explore-and-discover. Returns `{ status, id?, shortcut?, ui_procedure?, verify_more?, error? }`. status=ok: execute exactly....4 params
Pre-computed navigation recipes for public websites. CALL BEFORE any browser action on the open web (navigate, click, fetch, fill, URL guess) — replaces explore-and-discover. Returns `{ status, id?, shortcut?, ui_procedure?, verify_more?, error? }`. status=ok: execute exactly....
Parameters* required
sitestringRegistrable domain, optionally followed by a product-surface path — 'google.com', 'docs.stripe.com', 'google.com/maps'. No scheme/port. A path is treated as an implicit scopeHint when it matches a known surface, so you can skip the ambiguous_scope round-trip for sites with multiple surfaces.
taskstringPlain-English intent, e.g. 'find Apple's latest 10-K'. No URLs — intent, not destination.
variantsobjectOptional. Behavior facets when one matters: `{ auth_state: 'logged_in'|'logged_out', locale: 'en-US', region: 'EU', currency: 'USD' }`. Affects cache key — omit when uncertain.
scopeHintstringOptional. Only after a prior `ambiguous_scope` — pass one of `error.scope_options[].pattern` verbatim (leading slash, no trailing).
report_outcomeReport whether the RECIPE ran cleanly — not whether you got the user a good answer. Call ONCE per envelope after you finished walking the recipe OR abandoned it. `success: true` = every step executed AS WRITTEN. Each locator resolved on the first try, no extra clicks/scrolls/w...3 params
Report whether the RECIPE ran cleanly — not whether you got the user a good answer. Call ONCE per envelope after you finished walking the recipe OR abandoned it. `success: true` = every step executed AS WRITTEN. Each locator resolved on the first try, no extra clicks/scrolls/w...
Parameters* required
successbooleanTrue ONLY if the recipe ran clean — every step as written, no retries, no JS-eval fallbacks, no extra clicks. False on ANY deviation, even if the user got the right answer another way.
evidenceobjectREQUIRED on every call. Describe how the RECIPE behaved — NOT what you found for the user. `{ what_happened: string, error?: string, screenshot_id? }`. `what_happened` should name which steps ran clean and which needed retries/substitutions/JS-eval/extra clicks. ❌ 'Found restaurant X with 4.9 stars' (task outcome). ✅ 'All 6 steps ran as written' (clean). ✅ 'Steps 1-4 clean. Step 5 `All filters` locator missed; tried 3 selectors then used raw JS click. Step 6 never reached.' (hiccup). Re-crawl reads this to decide what to fix.
envelope_idstring`id` from a `status: ok` envelope. Miss envelopes have no `id`.
bowmark skill
The skill for Bowmark — pre-computed navigation recipes for known websites, so the agent doesn't have to discover the page structure from scratch.
npx skills add bowmark-ai/skill
Works on any host that supports the SKILL.md standard — Claude Code, Codex (which adopted the standard natively), Cursor, GitHub Copilot, OpenCode, and others.
The skill calls Bowmark's MCP server — wire that up at bowmark.ai/#install or via Smithery.
Want both in one step? On Claude Code and Codex, install the plugin instead — it bundles this skill and auto-wires the MCP:
# Claude Code
claude plugin marketplace add bowmark-ai/plugin && claude plugin install bowmark@bowmark-ai
# Codex
codex plugin marketplace add bowmark-ai/plugin # then `codex /plugins` to install
OpenAI Apps (ChatGPT plugin) variant
The ChatGPT Apps submission takes a skill as a ZIP or folder, and its needs differ slightly from the general skill: the plugin always ships the MCP alongside the skill, and ChatGPT exposes the tools under bare names. So there's a tailored variant, generated from this same canonical skill — never hand-maintained:
- Folder:
openai/bowmark/— a content mirror ofbowmark/SKILL.mdwith the no-MCP HTTP-fallback + "Higher limits" sections dropped (the MCP is always present here), tool names rewritten to bareask/execute/report_outcome, and Claude-only frontmatter/tool-name references trimmed. - ZIP:
openai/bowmark-openai-skill.zip— the same folder zipped, ready to drop straight into the ChatGPT "Skills" uploader. A committed artifact (not built in CI: the release runner has nozipbinary), so it rides the mirror tobowmark-ai/skillat a stable raw URL like any other file.
Both are generated by build-openai.mjs. Edit bowmark/SKILL.md, then regenerate and commit — never edit the openai/ copies directly (CI's check:openai fails a PR whose text mirror is stale):
pnpm -F @bowmark/skill sync:openai # regenerate openai/bowmark/SKILL.md
pnpm -F @bowmark/skill build:openai-zip # rebuild openai/bowmark-openai-skill.zip (commit it)
License
MIT © Bowmark AI
Featured
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →