# Bowmark (remote · api.bowmark.ai)

Do things on live websites: prices, availability, quotes, bookings, anything behind a form or login.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.bowmark.ai`: 62/100 (this document), [markdown](https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry.md), [page](https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry)
- npm · `bowmark-mcp`: 44/100, [markdown](https://verifymcp.io/servers/ai-bowmark-bowmark/bowmark-mcp.md), [page](https://verifymcp.io/servers/ai-bowmark-bowmark/bowmark-mcp)
- pypi · `bowmark-mcp`: 39/100, [markdown](https://verifymcp.io/servers/ai-bowmark-bowmark/bowmark-mcp-2.md), [page](https://verifymcp.io/servers/ai-bowmark-bowmark/bowmark-mcp-2)

## Channel facts

- Endpoint: `https://api.bowmark.ai/mcp/registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `8.7.5`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 47/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2031 tokens (~1015/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (50% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-bowmark-bowmark https://api.bowmark.ai/mcp/registry
```

### Codex

```toml
[mcp_servers.ai-bowmark-bowmark]
url = "https://api.bowmark.ai/mcp/registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-bowmark-bowmark": {
      "type": "remote",
      "url": "https://api.bowmark.ai/mcp/registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-bowmark-bowmark --url https://api.bowmark.ai/mcp/registry --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-bowmark-bowmark:
    url: "https://api.bowmark.ai/mcp/registry"
```

### Other

```json
{
  "mcpServers": {
    "ai-bowmark-bowmark": {
      "type": "http",
      "url": "https://api.bowmark.ai/mcp/registry"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “run” rewrote its description, which is the text the model reads
- [security] Tool “get_library” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 876 → 1015
- [functional] Schema quality: excellent → good
- [functional] Server version: 8.4.0 → 8.6.4
- [functional] Server version: 8.3.31 → 8.4.0
- [functional] Server version: 8.3.28 → 8.3.31
- [functional] Server version: 8.3.25 → 8.3.28
- [functional] Server version: 8.3.22 → 8.3.25
- [functional] Server version: 8.3.20 → 8.3.22
- [functional] Server version: 8.3.18 → 8.3.20
- [functional] Server version: 8.3.15 → 8.3.18
- [functional] Server version: 8.3.12 → 8.3.15
- [functional] Server version: 8.3.10 → 8.3.12
- [functional] Server version: 8.3.7 → 8.3.10
- [functional] Server version: 8.3.5 → 8.3.7
- [functional] Server version: 8.3.3 → 8.3.5
- [functional] Server version: 8.3.2 → 8.3.3
- [functional] Server version: 8.3.1 → 8.3.2
- [functional] Server version: 8.3.0 → 8.3.1
- [functional] Server version: 8.2.22 → 8.3.0
- [cosmetic] “get_library” reworded the description of “query”

### 2026-08-02 (score 62, 0)

- [functional] Server version: 8.2.21 → 8.2.22
- [functional] Server version: 8.2.20 → 8.2.21
- [functional] Server version: 8.2.19 → 8.2.20

### 2026-08-01 (score 62, +1)

- [functional] Server version: 8.2.18 → 8.2.19
- [functional] Server version: 8.2.17 → 8.2.18
- [functional] Server version: 8.2.15 → 8.2.17
- [functional] Server version: 8.2.13 → 8.2.15
- [functional] Server version: 8.2.12 → 8.2.13
- [functional] Server version: 8.2.11 → 8.2.12
- [functional] Server version: 8.2.10 → 8.2.11
- [functional] Server version: 8.2.9 → 8.2.10
- [functional] Server version: 8.2.7 → 8.2.9
- [functional] Server version: 8.2.5 → 8.2.7
- [functional] Server version: 8.2.3 → 8.2.5
- [functional] Server version: 8.2.1 → 8.2.3
- [functional] Server version: 8.1.7 → 8.2.1
- [functional] Server version: 8.1.5 → 8.1.7
- [functional] Server version: 8.1.4 → 8.1.5
- [functional] Server version: 8.1.2 → 8.1.4
- [functional] Server version: 8.1.1 → 8.1.2
- [functional] Server version: 8.0.4 → 8.1.1
- [functional] Server version: 8.0.2 → 8.0.4

### 2026-07-31 (score 61, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “run” rewrote its description, which is the text the model reads
- [security] Tool “get_library” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 767 → 876
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: excellent → good
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
- [functional] Server version: 8.0.0 → 8.0.2
- [functional] Server version: 7.0.2 → 8.0.0
- [functional] Server version: 7.0.0 → 7.0.2
- [functional] Server version: 6.5.4 → 7.0.0
- [functional] Server version: 6.5.2 → 6.5.4
- [functional] Server version: 6.5.0 → 6.5.2
- [functional] Server version: 6.4.9 → 6.5.0
- [functional] Server version: 6.4.8 → 6.4.9
- [functional] Server version: 6.4.5 → 6.4.8
- [functional] Server version: 6.4.4 → 6.4.5
- [functional] Server version: 6.4.2 → 6.4.4
- [functional] Server version: 6.4.1 → 6.4.2
- [functional] Server version: 6.3.7 → 6.4.1
- [functional] Server version: 6.3.4 → 6.3.6
- [functional] Server version: 6.3.1 → 6.3.4
- [functional] Server version: 6.2.24 → 6.3.1
- [functional] Server version: 6.2.22 → 6.2.24
- [functional] Server version: 6.2.19 → 6.2.22
- [functional] Server version: 6.2.16 → 6.2.19
- [functional] Server version: 6.2.12 → 6.2.16
- [functional] Server version: 6.2.11 → 6.2.12
- [functional] Server version: 6.2.9 → 6.2.11
- [cosmetic] “run” reworded the description of “script”
- [cosmetic] “get_library” reworded the description of “query”

### 2026-07-30 (score 59)

First indexed and scored.

## MCP tools (2)

### `get_library` (~682 tokens)

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

\**Use this whenever a task touches a live website.** It answers, definitively and cheaply, 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.

\**Checking is cheap, so check.** One read-only call, no site is touched, and an unrecognized query returns a one-line index instead of an error, so the check never dead-ends and never costs you an attempt. If nothing fits, you have lost one cheap call and can use your normal approach.

What comes back is the callable **function library** you write against: the runtime globals (`log`) PLUS, for each capability your query named, its namespace, TypeScript types, functions, and worked examples. Everything listed is real and callable. The language rules and how to run a script are on the `run` tool description.

Pass `query` — what you want to DO (`"flights"`, `"price a GPU"`) or, if you have one in mind, the COMPANY or site (`"Kayak"`, `"newegg.com"`). A phrase in the user's own words is fine; it is matched against the whole library. **You get what you asked about and nothing else.** If nothing matches — or you send no query — you get instead a one-line index: pick whichever entry fits and CALL AGAIN with its name to get the types and examples you need to write a script.

\**Every response is bounded, and it says so when it is a slice.** A broad query can match more than one response carries; when that happens the answer opens with a partial-answer line naming what it left out. **Read it before concluding anything** — absence from a sliced list means nothing, and the fix is one narrower query (a single task, or a single company by name), which always returns that entry in full. Only an answer that does NOT say it is a slice supports the conclusion that a task is uncovered.

\**Two tiers come back.** CAPABILITIES (`bowmark.flights.search(…

Input parameters:

- `query` (string): Optional, but pass one — it decides how much detail comes back. What the user wants to do, in their words ("flights", "price a GPU", "book a table", "check stock"), or a company/site if they named on…

### `run` (~1153 tokens)

Do the task on the live websites and return the result

\**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. 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 — it gives the exact function names, argument shapes, and return types; this description is the LANGUAGE + how-to (get_library is just the vocabulary).

THE LANGUAGE — plain async JavaScript:
• `bowmark` is a ready global (no import). Call capabilities off it — `await bowmark.<capability>.<method>(...)` — always `await`, they're async.
• Individual sites are callable too, at `await bowmark.providers.<provider>.<fn>(...)`. Use one when you specifically want THAT site; otherwise prefer the capability, which fans out across sites and routes around failures.
• Real control flow: `await`, `if`, loops, array methods (`map`/`filter`/`sort`/`slice`), and `Promise.all` for fan-out.
• `return` a value to get it back (JSON-serialized). `log(...)` for progress lines.
• `bowmark` is the ONLY I/O — no `fetch`, `process`, filesystem, or `import`/`require`. Write a plain async body, not a wrapping function.
• Keep scripts small and deterministic — no infinite loops. Runs in a hard sandbox with CPU + memory + wall-clock limits.

SENDING IT: pass the script text as `run({ script })` — `script` is the only argument (there is no `site` argument; the library exposes every capability under `bowmark`). `result` is whatever you returned; `logs` are your `log()` lines in order; on a throw/timeout `ok:false` and `error` is set.

CHECK `status` BEFORE `ok`. It is `ok` | `error` | `partial` | `needs_user`.
• `partial` means the script RAN and `result` is real and usable, but some of what it called never answered — so the result is narrower than what you asked for. `ok` is still `true`; this is not a failure and re-running usually returns the same thing. `incomplete.summary` says w…

Input parameters:

- `script` (string, required): The JavaScript script body to execute (async, against the `bowmark` global). e.g. `const { flights, warnings } = await bowmark.flights.search({from:'SFO',to:'JFK',depart:'2026-09-01'}); return { best…

Output parameters:

- `error` (string|null)
- `incomplete`
- `logs` (array)
- `meta`
- `ms` (number)
- `needs` (array)
- `ok` (boolean)
- `result`
- `status` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 62
- 2026-07-31: 61
- 2026-07-30: 59

## Links

- Remote endpoint: https://api.bowmark.ai/mcp/registry
- Repository: https://github.com/bowmark-ai/skill
- Website: https://bowmark.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-bowmark-bowmark/mcp-registry