Developer Tools
bowmark.ai
Executes precomputed navigation recipes on public websites and reports execution status.
ENDPOINT 1
https://api.bowmark.ai/mcp?s=r
MCP server metadata
- Name
- bowmark
- Version
- 5.2.0
Known tools 2
get_libraryReturns the callable **function library** you write against: the runtime globals (`log`) PLUS each capability's namespace, TypeScript types, functions, and worked examples.
Potential side effectsrunRuns a script you authored against the `get_library` vocabulary, on the live sites, and returns `{ ok, result, logs, error, ms }`.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.bowmark]
url = "https://api.bowmark.ai/mcp?s=r"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"bowmark": {
"type": "http",
"url": "https://api.bowmark.ai/mcp?s=r"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: bowmark
Remote MCP URL: https://api.bowmark.ai/mcp?s=r
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"bowmark": {
"url": "https://api.bowmark.ai/mcp?s=r"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"bowmark": {
"type": "http",
"url": "https://api.bowmark.ai/mcp?s=r"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "bowmark",
"transport": "streamable-http",
"url": "https://api.bowmark.ai/mcp?s=r"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://api.bowmark.ai/mcp/registry
MCP server metadata
- Name
- bowmark
- Version
- 8.74.0
Bowmark runs real tasks on live websites and hands back the result. REACH FOR IT whenever a request depends on what a site shows RIGHT NOW, or on something a person would have to operate a website to get: current prices, live availability or stock, search results, a quote, a fare, a configurator, a booking or reservation flow, anything behind a form, a filter, or a login. CHECKING IS CHEAP. `get_library({ query })` tells you whether a callable function already covers the task. It is one read-only call that touches no site, and an unrecognized query returns an index of the library rather than an error, so the check never dead-ends and never costs you an attempt. The loop is two calls in order: `get_library` for the vocabulary, then `run` with a short JavaScript script written against it. If nothing in the library fits, say so and use your normal approach. `register({})` is a third tool, needed only when calls run out: anonymous callers share a small daily allowance per IP address, and one argument-less call turns that into a much larger monthly one. Nothing is required to call it — no email, no sign-in, no human.
Known tools 4
run**Executes the task on the real websites** (the search, the price check, the availability lookup, the configurator, the booking flow) and returns what came back.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.bowmark]
url = "https://api.bowmark.ai/mcp/registry"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"bowmark": {
"type": "http",
"url": "https://api.bowmark.ai/mcp/registry"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: bowmark
Remote MCP URL: https://api.bowmark.ai/mcp/registry
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"bowmark": {
"url": "https://api.bowmark.ai/mcp/registry"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"bowmark": {
"type": "http",
"url": "https://api.bowmark.ai/mcp/registry"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "bowmark",
"transport": "streamable-http",
"url": "https://api.bowmark.ai/mcp/registry"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for bowmark.ai was fetched 2026-07-26T00:46:16.941Z and is being refreshed.
bowmark.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.