Back to resources

MCP SERVER

Bowmark

Primary machine endpointhttps://api.bowmark.ai/mcp/registry
Use with an agent

SUMMARY

What it does

Bowmark is an MCP server that enables agents to perform actions on live websites, such as checking prices, availability, getting quotes, and making bookings. It provides a function library to discover capabilities and a script execution environment to run tasks against real sites. The server exposes four tools: get_library (discover capabilities), run (execute scripts on live websites), register (create a free account for higher usage limits), and report (provide feedback on missing capabilities).

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

web.actionweight 100 · confidence 80web.discoverweight 80 · confidence 90account.createweight 40 · confidence 90feedback.reportweight 20 · confidence 90

TOOLS IN THIS MCP SERVER

Tools exposed by this MCP server

get_libraryCheck what can be done on a live website for this task

Use this whenever a task touches a live website. It answers whether Bowmark can already do the thing: look up current prices, check real availability or stock, search a site, get a quote or a fare, drive a configurator, start a booking, or pull anything that only exists behind a form, a filter, or a login. Pass a query describing what you want to do or a company/site name. Returns a function library with namespaces, types, functions, and examples.

Effect: readConfirm: explicit policy
registerCreate a free Bowmark account for more calls

Creates a free Bowmark account and returns an API key. Call it when a run is refused for hitting the anonymous limit, when you expect to make more than a handful of calls, or any time the user says they want an account. All arguments are optional; register({}) is a complete, valid call. Passing an email creates a Bowmark sign-in for that address; only pass it if the user supplied one.

Effect: account creationConfirm: explicit policy
reportReport what Bowmark could not do for this task

Record what was missing, wrong, or incomplete so Bowmark can build it. Pass the runId returned by run when this report is about a run; omit it when get_library did not cover the task. This records feedback only and does not retry a run.

Effect: writeConfirm: explicit policy
runDo the task on the live websites and return the result

Executes the task on the real websites (search, price check, availability lookup, configurator, booking flow) and returns what came back. Runs a script you authored against the get_library vocabulary, on the live sites, and returns { ok, result, logs, error, ms }. Call get_library first to get the exact function names and argument shapes.

Effect: irreversibleConfirm: explicit policy

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
mcp
Authentication
type: unknown
Pricing
model: unknown
Version
8.89.3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.