Skip to main content
Glama

Why

Browser MCP servers today make the model do everything, every time: read the page, pick one element, click, read the page again. Each click is a tool call, and each tool call is a model turn that costs seconds. Do the same task tomorrow and the agent pays the full price again.

Flintrail treats the browser like a JIT compiler treats code:

  1. Live, the agent drives the page, but batches a whole sequence of actions into one call and gets back a compact snapshot with clickable refs.

  2. Record, the same calls are captured with multi-clue element fingerprints and {{variables}}.

  3. Replay, the flow runs at browser speed with no model between steps. When a site changes, the run stops at the exact failing step and hands the page back so the agent repairs only that part.

  4. API replay, Flintrail sees the site's own fetch/XHR calls and can replay them from inside the page, with the same cookies and session. No rendering, no clicking.

Related MCP server: byob

Benchmark

Same 5-step task (fill a field, tick a box, change page, click a client-rendered button that calls an API, wait for the result), median of 10 runs, headless Chromium. The numbers are tool-side wall time only. In a real agent every tool call also costs a model turn, so going from 7 calls to 2 saves several more seconds on top.

The hatched bar is the floor: the same clicks as a raw Playwright script, with no MCP and no agent. Any tool that clicks through the UI is bounded by it, which is why the per-call ratios stay modest. Flintrail adds about 50 ms per call on top of that floor, Playwright MCP about 260 ms. The only way under the floor is to stop clicking, which is what API replay does.

Reproduce it: npm run bench (installs nothing global; Playwright MCP is a dependency of bench/ only).

Architecture

Install

Claude Desktop: download flintrail.mcpb and double-click it.

Claude Desktop, Claude Code, Cursor (stdio)

{
  "mcpServers": {
    "flintrail": {
      "command": "npx",
      "args": ["-y", "flintrail@latest"]
    }
  }
}

Claude Code: claude mcp add flintrail -- npx -y flintrail@latest

From a local clone (git clone https://github.com/Soflutionltd/flintrail.git && cd flintrail && npm install && npm run build), start node /absolute/path/to/flintrail/bin/supervise.cjs.

Automatic updates

Every install below keeps itself up to date, without restarting Claude or Cursor. The MCP client talks to a small supervisor (bin/supervise.cjs) that stays connected while the server runs behind it. At start-up and every 6 hours it asks npm for the latest flintrail, installs it in the background in ~/.soflution/mcp/flintrail/, and switches over as soon as no request is in flight (the client is told the tool list may have changed). A version that fails to start is rolled back at once and never picked again on that machine. npm checks the integrity of every download, and releases are published from GitHub Actions with provenance.

The only network call is that version check to registry.npmjs.org; nothing about your machine or your use is sent. Turn it off with NO_UPDATE_NOTIFIER=1 (or SOFLUTION_AUTO_UPDATE=0). Started directly with node dist/..., flintrail does not update itself and only mentions a newer version in its first tool result.

Any agent, any machine (HTTP)

node dist/cli.js --http --host 127.0.0.1 --port 8931
# token is generated once in ~/.flintrail/token (or pass --token / FLINTRAIL_TOKEN)

Clients connect to http://host:8931/mcp with Authorization: Bearer <token>. Put it behind a tunnel or reverse proxy with TLS if it leaves the machine.

Browser modes

Mode

When

How

attach (default)

Your desktop. Keep your logged-in sessions.

Connects over CDP to a dedicated Chrome for Testing. On macOS Flintrail finds it, restarts it with a local debugging port if needed (tabs are restored) and opens its own tabs in the background.

launch

Servers, CI, Docker.

FLINTRAIL_MODE=launch starts Chromium with a persistent profile in ~/.flintrail/profile, headless by default.

extension

Anyone, any Chromium browser, no debugging port.

FLINTRAIL_MODE=extension and the Flintrail extension installed. See below.

Flintrail refuses to attach to a personal browser (Brave, Edge, Opera, or on macOS anything that is not Chrome for Testing) unless FLINTRAIL_ALLOW_ANY_BROWSER=1. Your everyday browser stays yours.

Browser extension

The extension is the easiest way in: no command-line flags, no debugging port, works in Chrome, Edge, Brave, Arc or any Chromium 125+.

  1. Install. Download flintrail-extension-<version>.zip from the latest release, unzip it, open chrome://extensions, enable Developer mode, click Load unpacked and pick the folder. (Chrome Web Store listing in progress.)

  2. Run Flintrail in extension mode, for example in Claude Desktop:

    { "mcpServers": { "flintrail": { "command": "npx", "args": ["-y", "flintrail@latest"], "env": { "FLINTRAIL_MODE": "extension" } } } }
  3. Connect. Click the Flintrail icon, paste the token from ~/.flintrail/token, click Connect. The extension reconnects by itself afterwards.

How it works: Flintrail starts a relay on 127.0.0.1:8932. The extension connects to it with the token and executes CDP commands with chrome.debugger, one tab at a time. Playwright sees an ordinary CDP browser, so every tool, recording and replay works unchanged. The agent only sees tabs it opened itself or tabs you share with Share with agent. Chrome shows its "started debugging this browser" bar while a tab is driven, by design.

Teach by demonstration

You do not have to explain a task to the agent. Type a flow name in the popup, click Start recording, do the task yourself in the tab, click Stop and save. The extension records clicks, typing, selects, checkboxes and Enter with the same element fingerprints the engine uses, and never records password fields. Then:

fl_flow_set_var("paybyphone-renew", 0, "plate")   # turn the typed plate into {{plate}}
fl_run("paybyphone-renew", { "plate": "AB-123-CD" })

The flow now runs without you, without the LLM, in milliseconds per step.

Limits in extension mode: browser-level CDP (download folder, permissions, window size) is not available to extensions, so download saves through the browser's normal download flow. Chrome dismisses dialogs of background tabs driven by chrome.debugger before anyone can answer, so in this mode {do:"dialog"} answers the next alert / confirm / prompt from inside the page instead.

Tools

Tool

What it does

fl_open

Open a URL in a background tab, return a compact snapshot with [eN] refs.

fl_act

Run many actions in one call: click, dblclick, hover, fill, type, select, check, press, upload, download, goto, back, wait, scroll, mouse, dialog, resize, eval, request.

fl_snapshot

Re-read a page: interactive elements, headings, text excerpt, same-origin frames.

fl_extract

Run JavaScript in the page and return the result.

fl_network

List the site's own API calls with timing, body and a JSON sample.

fl_screenshot

JPEG screenshot of the tab, or of one element (ref / selector), in CSS pixels usable by mouse.

fl_console

Console errors and uncaught exceptions of a tab (level: "all" adds warnings and logs). fl_act says when new ones appear.

fl_record_start / fl_record_stop

Record a flow; repairFrom keeps the good steps and re-records the rest.

fl_run

Replay a flow with variables, no LLM.

fl_run_many

Replay a flow for many variable sets in parallel tabs.

fl_flows / fl_flow

List flows, inspect one.

fl_flow_set_var

Turn a recorded value into a {{variable}}, for flows taught by demonstration.

fl_extension

Extension connection status.

fl_adopt

Take control of a tab you already opened yourself, for example right after signing in by hand.

fl_login

Sign in with your saved password (browser password manager, 1Password, Bitwarden or your own command). Flintrail fills it, the agent never sees it. See Sign in.

fl_tabs / fl_close

Manage tabs.

Example

// one call, five actions
{ "tool": "fl_act", "tab": "t1", "actions": [
  { "do": "fill",  "ref": "e1", "value": "AA-111-AA", "var": "plate" },
  { "do": "check", "ref": "e3" },
  { "do": "click", "role": "button", "name": "Continue" },
  { "do": "click", "selector": "[data-testid=confirm]" },
  { "do": "wait",  "text": "active" }
]}

Then fl_run("permit", { "plate": "ZZ-999-ZZ" }) repeats it in under a second.

// files, native dialogs, coordinates, mobile width
{ "tool": "fl_act", "tab": "t1", "actions": [
  { "do": "upload", "ref": "e4", "files": ["/Users/me/statement.csv"], "var": "statement" },
  { "do": "dialog", "accept": true },
  { "do": "click", "role": "button", "name": "Delete" },
  { "do": "mouse", "x": 640, "y": 380 },
  { "do": "resize", "width": 390, "height": 844 }
]}

upload works on a file input, even a hidden one, and on a button or drop zone that opens the file chooser. Dialogs are dismissed by default and every one is reported in the result, as are new console errors.

Sign in

fl_login signs the agent in with the passwords you already have, without ever showing them to the agent: it only learns which fields were filled. Passwords and one-time codes are masked in every tool result, including captured request bodies and page reads, and a recorded flow stores a reference to the login, never the secret. On a multi-step sign-in (e-mail page, then password page) the agent calls it on each step.

Sources are tried in the order of FLINTRAIL_PASSWORDS (default browser):

Source

Setup

Notes

browser

None. Save the password in Chrome, Edge or Brave as usual.

The browser fills the form itself; Flintrail confirms with a real click and submits. Works in extension mode and in attach mode, on the profile that holds your passwords. With several saved accounts for a site, the browser picks one: use a CLI source to choose.

1password[:path]

1Password CLI signed in, or OP_SERVICE_ACCOUNT_TOKEN in Flintrail's environment for unattended use.

One-time codes stored in 1Password are filled too. A service account never asks for Touch ID; scope it to a vault that holds only what the agent needs.

bitwarden[:path]

Bitwarden CLI unlocked, BW_SESSION in Flintrail's environment.

One-time codes through bw get totp.

command:path

Any program: Flintrail runs it with the page URL as only argument.

It prints [{ "url", "username", "password", "totp"?, "title"? }]. Use it for KeePassXC, Dashlane, pass or a company vault.

Logins from a CLI source are only filled in frames whose domain matches the login's website, so a look-alike page gets nothing. Several matches: the agent passes item (ID, title or username). Example for Claude Desktop:

"env": { "FLINTRAIL_PASSWORDS": "browser,1password" }

Not supported: Apple Passwords (iCloud Keychain) has no command-line access. One-time codes sent by SMS, e-mail or phone prompt: fl_login says so and the agent asks you.

How replay finds elements again

Each recorded step stores a fingerprint, not a fragile selector: test id, stable id, name attribute, ARIA role and accessible name, placeholder, link target, visible text and a short CSS path. At replay time Flintrail tries them from most to least stable and takes the first that matches exactly one element, waiting only for that element, never for the network to go idle.

Security

  • No password is ever written to a flow. Password fields are skipped during recording; keep the session logged in instead.

  • fl_login never returns a password or a one-time code to the agent and masks them in every tool result. CLI logins are only filled on their own website. Password manager programs are chosen in the configuration, never by the agent, and run without a shell.

  • Flows are plain JSON in ~/.flintrail/flows, easy to review and version.

  • The HTTP transport requires a bearer token (constant-time comparison) and binds to 127.0.0.1 by default.

  • eval and request run inside the page with the page's own privileges, nothing more.

Configuration

Variable

Default

FLINTRAIL_MODE

attach

attach, launch or extension

FLINTRAIL_RELAY_PORT

8932

Local port the extension connects to

FLINTRAIL_CDP_URL

http://127.0.0.1:9222

Browser to attach to

FLINTRAIL_PORT

9222

Debugging port used when Flintrail starts Chrome for Testing

FLINTRAIL_CHROME

auto

Browser executable

FLINTRAIL_HEADLESS

1

0 to see the window in launch mode

FLINTRAIL_HOME

~/.flintrail

Flows, profile, token

FLINTRAIL_DOWNLOADS

~/Downloads/Flintrail

Where downloads land

FLINTRAIL_TOKEN

generated

HTTP bearer token and extension token

FLINTRAIL_PASSWORDS

browser

Password sources for fl_login, in order: browser, 1password[:path], bitwarden[:path], command:path. off removes the tool.

Develop

npm install
npx playwright-core install chromium   # once, for tests
npm test                               # build + 26 end-to-end tests over real MCP, extension included
npm run pack:extension                 # flintrail-extension-<version>.zip
npm run bench                          # benchmark vs Playwright MCP

Roadmap

  • Chrome Web Store and Edge Add-ons listings for the extension.

  • Automatic promotion of recorded UI steps to API steps when the captured call is replay-safe.

  • Shared flow library for common sites.

  • Visual diff on replay failure.

En français

Flintrail est un serveur MCP de navigation pour agents IA. Il pilote un vrai Chrome dédié (jamais votre navigateur personnel), enchaîne plusieurs actions en un seul appel, enregistre une tâche la première fois puis la rejoue seul, sans IA, en quelques centaines de millisecondes, ou en rejouant directement les appels API du site avec votre session. Sur notre banc d'essai, la même tâche prend 2,4 s avec Playwright MCP et 0,11 s avec Flintrail en mode API.

L'extension Chrome rend tout cela accessible à tout le monde : on l'installe, on colle le jeton, et l'agent pilote le navigateur. Mieux, on peut lui apprendre une tâche en la faisant soi-même une fois (bouton Start recording), Flintrail la rejoue ensuite seul. Les mots de passe ne sont jamais enregistrés.

Pour se connecter, l'agent utilise fl_login avec vos mots de passe habituels : ceux enregistrés dans le navigateur (sans réglage), ou 1Password, Bitwarden ou tout autre gestionnaire par sa ligne de commande. Flintrail remplit le formulaire lui-même, l'agent ne voit jamais ni le mot de passe ni le code.

License

MIT © 2026 Soflution Ltd

Available Tools

19 tools
fl_actB

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.

Inputs: tab (required), actions (required), max, text, +1 more.

fl_adoptA

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.

Inputs: url (required), max, text.

fl_closeC

Close a Flintrail tab.

Inputs: tab (required).

fl_consoleC

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.

Inputs: tab (required), clear, level.

fl_extensionB

Status of the Flintrail browser extension (extension mode).

Inputs: no named parameters.

fl_extractB

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

Inputs: js (required), tab (required).

fl_flowB

Show a flow with all its steps and element fingerprints.

Inputs: name (required).

fl_flowsB

List recorded flows with their variables and last timing.

Inputs: no named parameters.

fl_flow_set_varC

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

Inputs: var (required), name (required), step (required).

fl_loginA

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.

Inputs: tab (required), max, item, text, +2 more.

fl_networkB

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.

Inputs: limit, filter.

fl_openA

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.

Inputs: url (required), max, text.

fl_record_startA

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.

Inputs: name (required), startUrl, repairFrom, description.

fl_record_stopA

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

Inputs: save.

fl_runB

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.

Inputs: name (required), tab, vars.

fl_run_manyB

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

Inputs: name (required), runs (required), keepTabs, concurrency.

fl_screenshotA

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"}.

Inputs: tab (required), ref, full, selector.

fl_snapshotC

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

Inputs: tab (required), max, text.

fl_tabsB

List tabs opened by Flintrail.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 19 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: recording (record_start/stop), replay (run/run_many), inspection (snapshot/network/console/screenshot), and action batching (act/extract). A few pairs are close—fl_run vs fl_run_many, fl_flows vs fl_flow, and fl_open vs fl_snapshot both returning snapshots—but the descriptions disambiguate them adequately.

    Naming Consistency4/5

    All names share a consistent fl_ prefix and snake_case formatting, which is highly predictable. There is mild inconsistency between verb-style (fl_open, fl_run, fl_extract) and noun-style (fl_tabs, fl_flows, fl_console) names, but this mirrors the common list-vs-action distinction and remains readable.

    Tool Count4/5

    19 tools is on the heavier side but justified by a genuinely multi-faceted domain: browser control, flow recording, replay, login, and debugging. Each tool maps to a concrete capability rather than redundant surface area.

    Completeness4/5

    The surface covers the full lifecycle of record→save→replay→repair, plus inspection, auth, and parallel execution. Minor gaps exist—no explicit flow delete/rename or dedicated tab-switch/navigation tool—but agents can work around these via fl_act or re-opening.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      A
      maintenance
      Enables AI agents to drive your real, logged-in Chrome browser with existing sessions and cookies, bypassing CAPTCHA and anti-bot measures, with support for multi-session and human-in-the-loop workflows.
      40
      64
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to drive the user's real, already-logged-in Chrome browser locally, so they can read and navigate pages, click, type, fill forms, take screenshots, and inspect cookies, tabs, console, and network traffic without headless browsers or remote-debugging ports.
      1 npm
      ISC
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive your real browser — your tabs, logins, and extensions — by opening and controlling pages with Playwright, taking screenshots, capturing network traffic and recordings, and handing tabs back to you for logins or payments. Works across Chrome, Edge, Brave, Arc, Helium, Vivaldi, Opera, and Chromium through a local relay and extension.
      16,934 npm
      4
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to capture real browser interactions over CDP, compile them into deterministic replay scripts with parameterized inputs and stored secrets, and execute those workflows with real input events — no page re-reading or LLM in the replay loop. Also emits portable Agent Skills from recorded workflows.
      38 npm
      1
      AGPL 3.0