# peek (npm · @peekdev/mcp)

Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local

- Trust score: 76/100 (medium)
- Change this week: +33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@peekdev/mcp`: 76/100 (this document), [markdown](https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp.md), [page](https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp)

## Channel facts

- Registry: `npm`
- Package: `@peekdev/mcp`
- Version: `0.1.0-alpha.24`
- Transport: `stdio`

## 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 2026-08-03.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (149 of 153), so this covers what we could see, not the whole tree.
  - Runs a script at install time (postinstall) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.
  - Only part of the dependency tree could be resolved (149 of 153), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Cubenest/rrweb-stack).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 24 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3862 tokens (~203/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add cubenest-peek-mcp -- npx -y @peekdev/mcp
```

### Codex

```bash
codex mcp add cubenest-peek-mcp -- npx -y @peekdev/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cubenest-peek-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@peekdev/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cubenest-peek-mcp --command npx --arg -y --arg @peekdev/mcp
```

### Hermes

```yaml
mcp_servers:
  cubenest-peek-mcp:
    command: "npx"
    args: ["-y", "@peekdev/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "cubenest-peek-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@peekdev/mcp"
      ]
    }
  }
}
```

## 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 76, +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.

### 2026-08-02 (score 75, +52)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Provenance: unverified → pass
- [security improvement] Install scripts: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] The scripts that run when this package is installed changed: postinstall
- [security] The attested source repository moved: Cubenest/rrweb-stack
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 23, +17)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −20)

- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 26, −17)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (19)

### `list_recent_sessions` (~172 tokens)

List recent browser sessions

List the user's recorded browser sessions, newest first — the entry point for debugging what already happened (the get_session_* and DOM tools). Returns compact JSON rows ({ sessionId, origin, url, title, startedAt, ... }); free-text fields are clipped (origin 100, url 300, title 200 chars). If the MCP client scoped roots to specific origins and no origin filter is given, results are restricted to the client's scoped origins. Start here to obtain a sessionId, then call get_session_summary.

Input parameters:

- `limit` (integer): Maximum sessions to return (1-50, newest first; default 10).
- `origin` (string): Filter to one origin, e.g. 'https://app.example.com'. Omit to list across all recorded origins (subject to client roots scoping).

### `search_sessions` (~318 tokens)

Search recorded sessions

Search your recorded browser sessions by metadata and facets — free text in title/URL/origin (q), exact origin, recorded date range (createdAfter/createdBefore, ISO-8601), status (active/finalized), and whether the session has console errors (hasConsoleErrors) or network errors (hasNetworkErrors). Returns the same compact rows as list_recent_sessions, newest first. Read-only and local. Use it to find a sessionId when you don't already have one, then call get_session_summary. Matches session metadata only — not page content or error-message text. Multiple facets combine with AND (e.g. hasConsoleErrors + hasNetworkErrors returns sessions that have BOTH); to find sessions with either kind of error, search for each separately.

Input parameters:

- `createdAfter` (string): Only sessions first recorded at or after this ISO-8601 time.
- `createdBefore` (string): Only sessions first recorded at or before this ISO-8601 time.
- `hasConsoleErrors` (boolean): Only sessions with at least one console error.
- `hasNetworkErrors` (boolean): Only sessions with a failed/4xx-5xx network request.
- `limit` (integer): Maximum sessions to return (1-50, newest first; default 10).
- `origin` (string): Exact origin filter, e.g. 'https://app.example.com'.
- `q` (string): Free text matched (case-insensitive) against session title, URL, and origin.
- `status` (string): Filter by session status.

### `get_session_summary` (~79 tokens)

Summarize a session

Get an LLM-readable narrative summary of one session — your orientation for debugging what already happened: pages visited, click/input/navigation counts, and error counts. Use this first for an overview before drilling into get_session_console_errors / get_session_network_errors. Returns a structured JSON summary.

Input parameters:

- `sessionId` (string, required): Session id from list_recent_sessions.

### `get_session_console_errors` (~145 tokens)

List console errors

List console error messages recorded in a session, oldest first. Each row has a numeric id to pass to get_user_action_before_error. Returns JSON rows ({ id, ts, level, message, stack }); message clipped to 500 and stack to 800 chars. For error counts at a glance, use get_session_summary first.

Input parameters:

- `limit` (integer): Maximum errors to return (1-200, oldest first; default 50).
- `sessionId` (string, required): Session id from list_recent_sessions.
- `since` (integer): Only return errors with ts >= this epoch-ms timestamp (to page forward through a long session). Omit to start from the beginning.

### `get_session_network_errors` (~150 tokens)

List failed network requests

List failed or notable network requests in a session (HTTP status >= statusGte, or a transport-level network error), oldest first. Returns JSON rows ({ id, ts, method, url, status, statusText, resourceType, durationMs, errorText }); url and errorText clipped to 300 chars.

Input parameters:

- `limit` (integer): Maximum requests to return (1-200, oldest first; default 50).
- `sessionId` (string, required): Session id from list_recent_sessions.
- `statusGte` (integer): Minimum HTTP status treated as notable (100-599; default 400, i.e. 4xx/5xx). Transport-level errors are always included regardless.

### `get_user_action_before_error` (~181 tokens)

Actions before an error

Pre-assembled causal chain for a console error: the user actions, DOM mutations, and network errors in the window before it, merged into one time-ordered timeline with a deterministic narrative — to explain how the error was triggered. Returns JSON { errorId, errorTs, error, windowMs, actions, domMutations, networkErrors, timeline, narrative, truncated }. Get errorId from get_session_console_errors first.

Input parameters:

- `errorId` (integer, required): Console error id from get_session_console_errors.
- `sessionId` (string, required): Session id from list_recent_sessions.
- `window` (integer): How many preceding user actions to return (1-50; default 10).
- `windowMs` (integer): Time window (ms) before the error for correlated DOM mutations + network errors (100-60000; default 5000).

### `generate_playwright_repro` (~215 tokens)

Generate Playwright repro

Generate a runnable Playwright test (TypeScript) reproducing the user actions in a session: clicks, typing, navigation, and <select> changes. Optionally limit to a [startTs, endTs] epoch-ms window. Pass errorId (from get_session_console_errors) to seed a console-error-absence regression assertion — the generated test will capture console errors and assert the given error is not reproduced. Returns the test source as text. Note: only single-value <select> is represented (rrweb captures one value per input).

Input parameters:

- `endTs` (integer): Only include actions at or before this epoch-ms timestamp. Omit to run through the session end.
- `errorId` (integer): Console error id (from get_session_console_errors) to seed a console-error-absence regression assertion.
- `sessionId` (string, required): Session id from list_recent_sessions.
- `startTs` (integer): Only include actions at or after this epoch-ms timestamp. Omit to start at the session beginning.

### `get_dom_snapshot` (~152 tokens)

Reconstruct DOM at a time

Reconstruct the page DOM as it existed at a timestamp (or a selector subtree within it) and return it as HTML. Applies structural/attribute/text mutations on top of the nearest full snapshot at or before ts. Returns JSON { baseSnapshotTs, mutationsApplied, html }; html clipped to 24000 chars. Fails if no full snapshot exists at or before ts.

Input parameters:

- `selector` (string): CSS selector to return only that subtree. Omit to return the full document.
- `sessionId` (string, required): Session id from list_recent_sessions.
- `ts` (integer, required): Epoch-ms timestamp to reconstruct the DOM at. Use timestamps from get_session_summary, error rows, or get_user_action_before_error.

### `query_dom_history` (~278 tokens)

DOM change timeline

Timeline of DOM changes in a session. Two modes: (1) selector mode — pass `selector` to track one node's attribute/text history (use `op` to restrict). (2) window mode — pass `ts` (and optional `windowMs`) instead, to get ALL DOM changes in [ts - windowMs, ts] with per-change `target` hints, no selector needed. Returns JSON { selector, changes } or { ts, windowMs, changes }.

Input parameters:

- `limit` (integer): Maximum changes to return (1-500; default 100). Selector mode keeps the earliest matches; window mode keeps the most recent (closest to `ts`).
- `op` (string): Selector mode only: restrict to 'attributeChanges' or 'innerText'. Omit for both.
- `selector` (string): Selector mode: CSS selector to track one node, e.g. '#status'. Omit and pass `ts` for window mode.
- `sessionId` (string, required): Session id from list_recent_sessions.
- `ts` (integer): Window mode: anchor (epoch-ms). Returns DOM changes in [ts - windowMs, ts]. Ignored if `selector` is given.
- `windowMs` (integer): Window mode size in ms (100-60000; default 5000).

### `request_authorization` (~137 tokens)

Request action authorization

Ask the user to authorize a browser action via the side-panel banner (Level-3 act-with-confirm). On Allow, returns a one-shot confirmToken to pass to execute_action; on Deny, returns the denial. Every call - allowed or denied - is recorded to ~/.peek/audit.log. Use before execute_action when the origin is at permission Level 3, or to pre-authorize.

Input parameters:

- `action` (required): The browser action to authorize (e.g. click/type/navigate; see the action schema).
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.

### `execute_action` (~314 tokens)

Execute a browser action

Execute an action (click/type/navigate/...) in the user's live browser. Requires per-origin permission Level 3+: Level 3 raises a confirm banner unless a valid confirmToken from request_authorization is passed; Level 4 auto-allows non-destructive actions; Level <3 denies. The destructive-action override (delete/remove/transfer/send/pay/purchase/buy/confirm/subscribe/logout/sign out/unsubscribe/cancel subscription/wire/withdraw) always prompts, even at Level 4. Every call is recorded to ~/.peek/audit.log. After a mutating action, re-read to confirm it took: get_element_detail on the target (its value should match what you intended) and get_page_view (no validation error should have appeared) before advancing; if it did not take, stop and report rather than blind-retrying. Password/email/PII values return masked — verify those by the absence of an error.

Input parameters:

- `action` (required): The browser action to execute (e.g. click/type/navigate; see the action schema).
- `confirmToken` (string): One-shot token from a prior request_authorization Allow, to skip the Level-3 banner. Omit to trigger the banner (Level 3) or rely on Level-4 auto-allow.
- `connectorSecret` (string): SP4: paired-connector secret; presented by connectors, ignored for direct clients.
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.

### `suggest_element` (~141 tokens)

Highlight an element in the live browser

Draw a non-destructive highlight overlay on a CSS selector in the user's live browser, with an optional label, to point something out. Available at per-origin permission Level 2 (Suggest) and above; it never clicks, types, or navigates. The overlay persists until clear_highlight is called. Every call is recorded to ~/.peek/audit.log.

Input parameters:

- `label` (string): Optional short text shown in a badge next to the highlight (<=120 chars).
- `selector` (string, required): CSS selector of the element to highlight.
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.

### `clear_highlight` (~75 tokens)

Clear the highlight overlay

Remove the highlight overlay previously drawn by suggest_element in the user's live browser. Available at per-origin permission Level 2 (Suggest) and above. Idempotent. Recorded to ~/.peek/audit.log.

Input parameters:

- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.

### `set_intent` (~256 tokens)

Set the control-shield banner text

Set the agent's status banner shown on the control shield (e.g. 'Applying to Senior Frontend · step 2/4'), so the user can follow what you're doing. Up to 80 chars, plain text. Requires the origin at Level 4 with the shield up; auto-allowed. Recorded to ~/.peek/audit.log. Advance the step only after the previous step verified (re-read it took); on a failure, set a 'stopped — <what> didn't take' status instead of advancing. End an assisted-apply loop by calling set_intent with a short summary text plus status:'done' (success) or status:'failed' (with a brief reason), so the user sees a clear outcome.

Input parameters:

- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.
- `status` (string): Set 'done' when the task is fully complete, or 'failed' when you stopped because a step didn't take, to show a terminal banner on the shield. Omit for an ongoing status update.
- `text` (string, required): Status text shown in the shield banner (<=80 chars). Pass an empty string to clear it.

### `request_user_input` (~309 tokens)

Pause and ask the user to fill something in on the page

Pause the agent and hand the keyboard back to the user for ONE editable, non-destructive field (or a free-text prompt), then resume. Requires the origin at Level 4 with the control shield up. Blocks until the user clicks Done, a timeout fires, or the run is stopped. Returns { resumed:true, value? } or { resumed:false, reason }. The returned value is only included when readBack:true and the field isn't a password/OTP/credit-card field. Recorded to ~/.peek/audit.log (prompt + selector only — never the value).

Input parameters:

- `prompt` (string, required): What to ask the user to do (shown in the card, below a peek-authored framing line).
- `readBack` (boolean): If true, return what the user typed to the agent (never for password/OTP/cc fields). Default false.
- `scope` (string): 'field' (default) unlocks one editable field; 'page' hands full page control back (CAPTCHAs, native widgets, final review) until Resume. Inherits the handoff recording-suspension.
- `selector` (string): CSS selector of the editable field to unlock for the user. Omit for a free-text prompt card.
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.
- `timeoutMs` (integer): How long to wait for the user (default 120000, max 600000).

### `get_page_view` (~226 tokens)

Get a live, ref-tagged view of the current page

Return a compact, masked snapshot of the user's LIVE page as a list of interactive/labeled elements, each with a stable `ref` (e.g. e5). Pass a `ref` to execute_action / request_authorization (click/type/scroll/enter/dblclick) instead of authoring a CSS selector — deterministic and far cheaper than reading get_dom_snapshot's HTML. Refs expire on navigation; re-call after navigating. Available at per-origin Level 1+; non-mutating; recorded to ~/.peek/audit.log. Password/email/tel and PII-autofill (card/address/etc.) input values, and fields marked private, are masked; structured PII is scrubbed, but free-text field values may be returned.

Input parameters:

- `maxElements` (integer): Cap on elements returned (1-500; default 200).
- `selector` (string): Scope the snapshot to a CSS subtree. Omit for the whole page.
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions; determines the per-origin permission level.

### `get_element_detail` (~196 tokens)

Get full masked detail for one element by ref

Given a `ref` from get_page_view, return the FULL masked detail of that single element (role, accessible name, accessible description, all aria-*, effective aria-hidden/disabled, a curated computed-style bag, state, value, href, position, nearby heading, and its interactive descendants with their refs, capped). The compact get_page_view stays cheap; call this only for the one element you need to disambiguate or act on. Refs expire on navigation. Level 1+; non-mutating; audited. Values for password/email/PII inputs are masked; free-text values may be returned (like the recorder). For live console/network state use get_session_console_errors / get_session_network_errors.

Input parameters:

- `ref` (string, required): An element ref (e.g. "e5") from a recent get_page_view.
- `sessionId` (string, required): Session id (origin context) from list_recent_sessions.

### `verify_audit_log` (~149 tokens)

Verify the action audit log

Verify the integrity of peek's local action audit log (~/.peek/audit.log) — the append-only, hash-chained record of every browser action peek authorized or attempted. Returns JSON { logPresent, status, entriesVerified, prelude, headPresent, brokenAtLine?, expected?, got?, gaps?, summary }. status is one of intact | broken | truncated | tail-tampered | prefix-tampered | incomplete-final | gaps | head-missing. Local and read-only. The log is tamper-EVIDENT, not tamper-proof: it has no cryptographic signature and no external timestamp anchor. Use it to confirm the action trail on this machine has not been altered.

### `request_pairing` (~88 tokens)

Request connector pairing

Initiate a connector-pairing handshake: present a pairing code and receive a one-shot secret on approval. The connecting client name is taken from the MCP connection identity. Returns JSON { approved, secret? }. Every attempt is recorded to ~/.peek/audit.log; the secret is never written to the log.

Input parameters:

- `code` (string, required): The pairing code generated by the connector for this handshake.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp#diagnostics

## Score history

- 2026-08-03: 76
- 2026-08-02: 75
- 2026-08-01: 23
- 2026-07-30: 6
- 2026-07-29: 26
- 2026-07-28: 43
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/@peekdev/mcp
- Socket report: https://socket.dev/npm/package/@peekdev/mcp
- Repository: https://github.com/Cubenest/rrweb-stack
- Website: https://peek.cubenest.in/
- Changelog RSS feed: https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/cubenest-peek-mcp/peekdev-mcp