# Flintrail (mcpb · flintrail.mcpb)

Drive a real Chrome live, record a flow once, replay it in milliseconds without an LLM.

- Trust score: 48/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `flintrail.mcpb`: 48/100 (this document), [markdown](https://verifymcp.io/servers/com-soflution-flintrail/flintrail.md), [page](https://verifymcp.io/servers/com-soflution-flintrail/flintrail)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/Soflutionltd/flintrail/releases/download/v1.3.0/flintrail.mcpb`
- Transport: `stdio`
- SHA-256: `fa576058086607914d32d55eabd80871f8f332968a34fcd67f5b3ae7e566b44d`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-11-05.

- **Supply Chain Security**: 23/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs were checked across the 94 of 94 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1262 tokens (~66/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 35% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Flintrail MCP server?

Flintrail ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, fa576058086607914d32d55eabd80871f8f332968a34fcd67f5b3ae7e566b44d; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/Soflutionltd/flintrail/releases/download/v1.3.0/flintrail.mcpb`
- SHA-256: `fa576058086607914d32d55eabd80871f8f332968a34fcd67f5b3ae7e566b44d`

### Verify on macOS / Linux

```bash
echo "fa576058086607914d32d55eabd80871f8f332968a34fcd67f5b3ae7e566b44d  flintrail.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\flintrail.mcpb).Hash -eq "fa576058086607914d32d55eabd80871f8f332968a34fcd67f5b3ae7e566b44d"
```

## 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.

### 2026-11-05 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 45, 0)

- [functional] Dependency health: partial → 0.86

### 2026-10-30 (score 45, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 44, 0)

- [functional regression] Schema quality: 57 → 66
- [functional improvement] Tool coverage: 29% → 35%
- [functional] Dependency health: 0.86 → partial

### 2026-10-28 (score 44, +2)

- [functional regression] Schema quality: 943 → 1040
- [functional improvement] Tool coverage: 23% → 29%
- [functional improvement] Stability: unverified → 0.07

### 2026-10-26 (score 42)

First indexed and scored.

## MCP tools (19)

### `fl_open` (~87 tokens)

Open a URL in a background tab of the dedicated browser (logged-in sessions kept). Returns a compact snapshot whose [eN] refs can be used directly in fl_act.

Input parameters:

- `max` (number): Max interactive elements listed (default 150).
- `text` (number): Characters of page text to include (default 600, 0 for none).
- `url` (string, required)

### `fl_adopt` (~97 tokens)

Take control of a tab the user already has open in the browser (first match on a URL substring), e.g. a site they just signed in to by hand. Returns its snapshot.

Input parameters:

- `max` (number): Max interactive elements listed (default 150).
- `text` (number): Characters of page text to include (default 600, 0 for none).
- `url` (string, required): Substring of the tab URL

### `fl_act` (~108 tokens)

Run SEVERAL actions in one call (fill a whole form, click, submit, wait, extract) and get one fresh snapshot back. Always batch as many actions as possible: one call beats ten.

Input parameters:

- `actions` (array, required)
- `max` (number): Max interactive elements listed (default 150).
- `snapshot` (boolean)
- `tab` (string, required)
- `text` (number): Characters of page text to include (default 600, 0 for none).

### `fl_login` (~222 tokens)

Sign in on the open sign-in form with the user's saved password: from the browser's own password manager, or from a password manager CLI the user configured (1Password, Bitwarden, custom command). Flintrail fills username, password and one-time code itself; the secrets never reach you. A CLI login is only filled when the page domain matches its website. On a multi-step sign-in (e-mail page, then password page), call it on each step. While recording, the flow stores the source and login ID, never a secret.

Input parameters:

- `item` (string): Login ID, title or username in a password manager CLI, when several match the site.
- `max` (number): Max interactive elements listed (default 150).
- `source` (string): Only this source: browser, 1password, bitwarden or command.
- `submit` (boolean): Press Enter after filling (default true).
- `tab` (string, required)
- `text` (number): Characters of page text to include (default 600, 0 for none).

### `fl_snapshot` (~70 tokens)

Re-read a tab: interactive elements with refs, headings and the start of the text.

Input parameters:

- `max` (number): Max interactive elements listed (default 150).
- `tab` (string, required)
- `text` (number): Characters of page text to include (default 600, 0 for none).

### `fl_extract` (~68 tokens)

Run JavaScript in the page and return the result. Fastest way to pull tables, lists or links.

Input parameters:

- `js` (string, required): Function body with return, e.g. return [...document.querySelectorAll("tr")].map(r => r.innerText)
- `tab` (string, required)

### `fl_network` (~75 tokens)

List the API calls (fetch/XHR) the site made, with method, status, timing, body and a JSON sample. Use it to replace UI clicks with a direct {do:"request"} step: the fastest possible replay.

Input parameters:

- `filter` (string): Substring the URL must contain.
- `limit` (number)

### `fl_console` (~60 tokens)

Console errors and uncaught exceptions of a tab (level "all" adds warnings and logs). fl_act and fl_snapshot already say when new errors appeared.

Input parameters:

- `clear` (boolean)
- `level` (string)
- `tab` (string, required)

### `fl_screenshot` (~80 tokens)

Screenshot of a tab, or of one element with ref / selector. Only when the visual layout matters: snapshots are much cheaper. Pixels are CSS pixels, usable as x / y for {do:"mouse"}.

Input parameters:

- `full` (boolean)
- `ref` (string)
- `selector` (string)
- `tab` (string, required)

### `fl_tabs` (~16 tokens)

List tabs opened by Flintrail.

### `fl_close` (~22 tokens)

Close a Flintrail tab.

Input parameters:

- `tab` (string, required)

### `fl_record_start` (~81 tokens)

Start recording a flow. Every fl_open / fl_act after this is captured with robust element fingerprints so fl_run can replay it without an LLM. repairFrom keeps steps before that index and replaces the rest.

Input parameters:

- `description` (string)
- `name` (string, required)
- `repairFrom` (number)
- `startUrl` (string)

### `fl_record_stop` (~28 tokens)

Stop recording and save the flow (save=false to discard).

Input parameters:

- `save` (boolean)

### `fl_run` (~64 tokens)

Replay a recorded flow at browser speed, no LLM. On failure (site changed) it stops at the failing step and returns the page so the flow can be repaired.

Input parameters:

- `name` (string, required)
- `tab` (string)
- `vars` (object)

### `fl_run_many` (~56 tokens)

Replay the same flow for many variable sets in parallel, each in its own background tab.

Input parameters:

- `concurrency` (number)
- `keepTabs` (boolean)
- `name` (string, required)
- `runs` (array, required)

### `fl_flows` (~19 tokens)

List recorded flows with their variables and last timing.

### `fl_flow` (~26 tokens)

Show a flow with all its steps and element fingerprints.

Input parameters:

- `name` (string, required)

### `fl_flow_set_var` (~63 tokens)

Turn the literal value of one step into a variable {{var}}, e.g. after recording by demonstration.

Input parameters:

- `name` (string, required)
- `step` (number, required): Step index, as shown by fl_flow (0-based).
- `var` (string, required)

### `fl_extension` (~20 tokens)

Status of the Flintrail browser extension (extension mode).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-soflution-flintrail/flintrail#diagnostics

## Score history

- 2026-11-05: 48
- 2026-11-04: 47
- 2026-11-03: 47
- 2026-11-02: 46
- 2026-11-01: 46
- 2026-10-31: 45
- 2026-10-30: 45
- 2026-10-29: 44
- 2026-10-28: 44
- 2026-10-27: 42
- 2026-10-26: 42

## Common questions

### What is the Flintrail MCP server?

Flintrail is an MCP server listed in the public MCP registry as com.soflution/flintrail. Drive a real Chrome live, record a flow once, replay it in milliseconds without an LLM. This page covers its MCPB bundle (https://github.com/Soflutionltd/flintrail/releases/download/v1.3.0/flintrail.mcpb).

### Is the Flintrail MCP server safe to use?

Flintrail scores 48 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Flintrail MCP server expose?

Flintrail exposes 19 tools: fl_open, fl_adopt, fl_act, fl_login, fl_snapshot, and 14 more. Their descriptions and schemas cost roughly 1,262 tokens of context every time the server is loaded.

### What licence is the Flintrail MCP server under?

Flintrail declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/Soflutionltd/flintrail
- Changelog RSS feed: https://verifymcp.io/servers/com-soflution-flintrail/flintrail.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-soflution-flintrail/flintrail.json
- HTML version of this page: https://verifymcp.io/servers/com-soflution-flintrail/flintrail