Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Samrj12/doppel

NPM · DOPPEL-MCP · SCANNED SEP 20

Drive your real, logged-in Chrome/Edge from AI agents over CDP. Faster. Sharper.

Available components

0 this week 78 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability81
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2398 tokens (~119/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.Samrj12/doppel MCP server?

io.github.Samrj12/doppel runs locally as an npm package, launched with npx -y doppel-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · doppel-mcp

# add to Claude Code
claude mcp add samrj12-doppel -- npx -y doppel-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "samrj12-doppel": {
      "command": "npx",
      "args": [
        "-y",
        "doppel-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "samrj12-doppel": {
      "command": "npx",
      "args": [
        "-y",
        "doppel-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add samrj12-doppel -- npx -y doppel-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "samrj12-doppel": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "doppel-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add samrj12-doppel --command npx --arg -y --arg doppel-mcp
# ~/.hermes/config.yaml
mcp_servers:
  samrj12-doppel:
    command: "npx"
    args: ["-y", "doppel-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "samrj12-doppel": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "doppel-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add samrj12-doppel -t stdio -c npx -a -y doppel-mcp
// mcp.json
{
  "mcpServers": {
    "samrj12-doppel": {
      "command": "npx",
      "args": [
        "-y",
        "doppel-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 +1
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 9 Sept 26 +1
    • Stability: 0.97 → pass security
  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/doppel-mcp@0.7.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 97 packages
Packages resolved 97
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 20 exposed · ~2,398 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
doppel_batch ~159

Apply a SEQUENCE of actions (click/type/press_key/hover) in ONE call, in order. PREFER THIS over separate click/type calls whenever you can already see the targets in the current snapshot - e.g. filling a form, ticking several checkboxes, or 'pick an option then click Continue'. Each separate tool call costs a full model round-trip; a batch is one. Refs come from the latest snapshot, so all targets must exist on the SAME page (a batch can't span a navigation). Stops at the first failed op and reports which one. Returns one snapshot at the end.

NameTypeReqDescription
includeSnapshotbooleanReturn a snapshot after the batch. Default true.
opsarrayyesOrdered list of actions.

No output schema declared.

No examples provided.

doppel_cleanup_tabs ~92

Close leftover Doppel automation tabs. By default only the generic 'Doppel' / 'Doppel Test' groups (debris from past sessions), leaving purpose-named task groups alone. Pass all:true to also close every purpose-named Doppel task group. Non-Doppel tabs and groups are never touched.

NameTypeReqDescription
allbooleanAlso close purpose-named Doppel task groups, not just the generic ones.

No output schema declared.

No examples provided.

doppel_click ~87

Click an element by its [ref] from the latest snapshot. Waits until it's actionable, then uses trusted native input. If you already know several actions from this snapshot, prefer doppel_batch to run them in one call.

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after clicking. Default true.
refintegeryesThe [ref] number from a snapshot

No output schema declared.

No examples provided.

doppel_close_tab ~36

Close a tab Doppel controls and drop its session.

NameTypeReqDescription
tabIdintegeryesThe tab id from doppel_list_tabs

No output schema declared.

No examples provided.

doppel_console ~221

See the page's console output + JS errors, captured read-only. By default shows browser-level problems (errors, warnings, failed network/CSP/deprecation), which is fully stealthy. Page console.log/info is NOT captured unless you set `pageConsole:true`, which enables the CDP Runtime domain (detectable by a hostile page while on, so off by default; captures from that point forward). Uncaught JS exceptions are merged in as errors; consecutive duplicates collapse with [xN].

NameTypeReqDescription
grepstringKeep messages whose text matches this substring or regex.
includeStackbooleanInclude stack traces (capped ~50 frames).
levelstringMinimum severity to show. Default 'warn' (warnings + errors + failures).
limitintegerMax messages. Default 50.
offsetintegerSkip the first N matching messages (paginate).
pageConsolebooleanCapture page console.log/info too (enables Runtime; detectable while on). Set false to turn it back off.

No output schema declared.

No examples provided.

doppel_hover ~64

Hover the mouse over an element by its [ref] (reveals menus/tooltips). Waits until it's actionable.

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after hovering. Default true.
refintegeryesThe [ref] from a snapshot

No output schema declared.

No examples provided.

doppel_list_tabs ~27

List the tabs Doppel controls (its tab group), with URLs and which is active.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

doppel_navigate ~92

Navigate the active tab: go to a URL, or go back/forward/reload. Waits for load. Returns the final URL plus a fresh page snapshot (by default).

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after navigating. Default true.
typestringNavigation type. Default 'url'.
urlstringAbsolute URL (required when type is 'url').

No output schema declared.

No examples provided.

doppel_network ~424

See the page's network activity, captured read-only from the moment the tab attaches. Without `reqid`, returns a compact one-line-per-request list; pass `reqid` for full detail plus the response body. Successful static assets (images/fonts/scripts/css) are hidden unless `includeStatic`. Filter with `grep` (URL), `status`, `method`, `resourceType`, `failedOnly`, `xhrOnly` (just API calls), or `sinceLastAction` (only what the last click/type/navigate triggered).

NameTypeReqDescription
bodystringWith reqid: which body to include. Default 'response'.
failedOnlybooleanOnly failed requests (transport error or status >= 400).
grepstringKeep requests whose URL matches this substring or regex (case-insensitive).
includeStaticbooleanInclude successful images/fonts/scripts/css (hidden by default).
limitintegerMax requests in the list. Default 50.
maxBytesintegerWith reqid: truncate inlined bodies to N bytes (default 10000).
methodstringHTTP method, e.g. GET, POST.
offsetintegerSkip the first N matching requests (paginate).
reqidintegerDrill into one request by its [id] from the list (full detail + body).
resourceTypestringdoc | css | img | script | font | xhr | fetch | ws | media | other.
saveToFilestringWith reqid: write the FULL response body to a file (filename only) in the Doppel captures dir (~/.doppel/captures or $DOPPEL_CAPTURE_DIR), instead of inlining it.
sinceLastActionbooleanOnly requests triggered since the last click/type/navigate.
statusstringStatus filter: "404", "5xx", ">=400".
xhrOnlybooleanOnly XHR/fetch requests (the API-call case).

No output schema declared.

No examples provided.

doppel_new_tab ~125

Open a new tab (background, no focus stealing) and make it active. Optionally load a URL. Pass `group` to name the tab group by the task's purpose (e.g. '27in Monitor'); tabs sharing a group cluster together.

NameTypeReqDescription
groupstringShort purpose label for the tab group, e.g. '27in Monitor', 'Job Apply'. Defaults to 'Doppel'.
includeSnapshotbooleanReturn a snapshot after opening. Default true.
urlstringURL to load. Default about:blank.

No output schema declared.

No examples provided.

doppel_press_key ~72

Press a special key (Enter, Tab, Backspace, Delete, Escape, Arrow keys) via trusted native input.

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after the keypress. Default true.
keystringyesKey name, e.g. Enter, Tab, ArrowDown

No output schema declared.

No examples provided.

doppel_screenshot ~91

Screenshot the current page (PNG by default). Returns the image. Prefer doppel_snapshot (text) when possible; use this only when you need to SEE pixels.

NameTypeReqDescription
formatstringImage format. Default png.
fullPagebooleanCapture the full scrollable page, not just the viewport.
qualityintegerQuality 0-100 (jpeg/webp only).

No output schema declared.

No examples provided.

doppel_scroll ~120

Scroll an element into view by its [ref] - e.g. to scroll to the last item of a list to trigger lazy-loading / infinite scroll, then re-snapshot. The snapshot already captures the whole page (all elements, on- or off-screen) and clicks auto-scroll into view, so use this only to trigger scroll-driven loading, not to 'see more'.

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after scrolling. Default true.
refintegeryesThe [ref] of the element to scroll into view.

No output schema declared.

No examples provided.

doppel_select_tab ~63

Switch the active tab to another tab Doppel controls (tabId from doppel_list_tabs).

NameTypeReqDescription
includeSnapshotbooleanReturn a snapshot of the newly active tab. Default true.
tabIdintegeryesThe tab id from doppel_list_tabs

No output schema declared.

No examples provided.

doppel_set_group ~79

Name the current tab's group by the task's PURPOSE (e.g. '27in Monitor', 'Job Apply'), not the site. Call this at the start of a task so the group chip reads as what you're doing instead of 'Doppel'.

NameTypeReqDescription
namestringyesShort purpose label, e.g. '27in Monitor'.

No output schema declared.

No examples provided.

doppel_snapshot ~244

Capture a structured accessibility snapshot of the current page. Elements are tagged with a [ref] for doppel_click/doppel_type; refs stay stable across grep/offset within a snapshot. Fast: no screenshot. On dense pages (search results, shopping) use interactive:true and/or grep to cut noise, and offset to page through results.

NameTypeReqDescription
grepstringKeep only elements whose printed line matches this text or regex (case-insensitive), e.g. 'Dell', 'button', or 'button "S"'.
interactivebooleanOnly actionable elements (links/buttons/inputs); skips headings/static text/lists. Best for dense pages.
limitintegerMax elements to return. Default 500; 300-1000 is a good range. Prefer interactive/grep over a huge limit.
offsetintegerSkip the first N matching elements (paginate a long page).
withinSerialize only part of the page: a [ref] to scope to that element's subtree, or a container role like "dialog", "form", or "navigation" to scope to that region. Ignores the rest.

No output schema declared.

No examples provided.

doppel_status ~27

Check whether the Doppel browser extension is connected. Call this first if other tools error out.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

doppel_type ~86

Type text into an element by its [ref]. Waits until actionable, focuses it, and inserts trusted text (works with React/controlled inputs).

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after typing. Default true.
refintegeryesThe [ref] of the input/textarea from a snapshot
textstringyesThe text to type

No output schema declared.

No examples provided.

doppel_upload ~184

Upload local file(s) to a file input WITHOUT opening the native OS file dialog. Point `ref` at the upload control from a snapshot - the file input itself, or the button/label that opens it (Doppel finds the underlying <input type=file>). `path` is an absolute path on this machine; pass an array for a multi-file input. Fires the real change event, so the page reacts exactly as if a human picked the file.

NameTypeReqDescription
includeSnapshotbooleanReturn a fresh snapshot after uploading. Default true.
pathyesAbsolute path to a local file (must be under Downloads/Documents/Desktop/Pictures/temp or $DOPPEL_UPLOAD_DIRS), or an array for a multi-file input.
refintegeryesThe [ref] of the upload control (the file input, or the button/label that opens it).

No output schema declared.

No examples provided.

doppel_wait_for ~105

Wait until specific text appears on the page, or for a fixed time. Use after an action that loads content.

NameTypeReqDescription
includeSnapshotbooleanReturn a snapshot after waiting. Default true.
textstringText to wait for (case-insensitive substring).
timeMsintegerOr wait a fixed number of milliseconds (max 60000).
timeoutMsintegerMax wait when using 'text' (default 10000).

No output schema declared.

No examples provided.

Common questions

What is the io.github.Samrj12/doppel MCP server?

io.github.Samrj12/doppel is an MCP server listed in the public MCP registry as io.github.Samrj12/doppel. Drive your real, logged-in Chrome/Edge from AI agents over CDP. Faster. Sharper. This page covers its npm package (doppel-mcp).

Is the io.github.Samrj12/doppel MCP server safe to use?

io.github.Samrj12/doppel scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 io.github.Samrj12/doppel MCP server expose?

io.github.Samrj12/doppel exposes 20 tools: doppel_status, doppel_navigate, doppel_snapshot, doppel_scroll, doppel_click, and 15 more. Their descriptions and schemas cost roughly 2,398 tokens of context every time the server is loaded.

Is the io.github.Samrj12/doppel MCP server still maintained?

io.github.Samrj12/doppel is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.Samrj12/doppel MCP server under?

io.github.Samrj12/doppel declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.