# io.github.restspace/sitelooper (npm · sitelooper)

Record a browser flow once with a model, then compile it to a Playwright spec that needs no model.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `sitelooper`: 75/100 (this document), [markdown](https://verifymcp.io/servers/restspace-sitelooper/sitelooper.md), [page](https://verifymcp.io/servers/restspace-sitelooper/sitelooper)

## Channel facts

- Registry: `npm`
- Package: `sitelooper`
- Version: `0.7.0`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 93 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 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2681 tokens (~157/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 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 io.github.restspace/sitelooper MCP server?

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

### Claude

```bash
claude mcp add restspace-sitelooper -- npx -y sitelooper
```

### Cursor

```json
{
  "mcpServers": {
    "restspace-sitelooper": {
      "command": "npx",
      "args": [
        "-y",
        "sitelooper"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "restspace-sitelooper": {
      "command": "npx",
      "args": [
        "-y",
        "sitelooper"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add restspace-sitelooper -- npx -y sitelooper
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add restspace-sitelooper --command npx --arg -y --arg sitelooper
```

### Hermes

```yaml
mcp_servers:
  restspace-sitelooper:
    command: "npx"
    args: ["-y", "sitelooper"]
```

### Netclaw

```json
{
  "McpServers": {
    "restspace-sitelooper": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "sitelooper"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add restspace-sitelooper -t stdio -c npx -a -y sitelooper
```

### Other

```json
{
  "mcpServers": {
    "restspace-sitelooper": {
      "command": "npx",
      "args": [
        "-y",
        "sitelooper"
      ]
    }
  }
}
```

## 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 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 73, +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.

### 2026-10-29 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 68)

First indexed and scored.

## MCP tools (17)

### `open` (~193 tokens)

Navigate a browser session to a URL (no model involved); starts the session if it is not running. learn and headed apply only when this call starts the session: learn=true records every later do/assert as a reusable flow step (needed before save_flow). Typical authoring: open (learn) → set_var → do/assert per outcome → save_flow → build_start.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `headed` (boolean): Show the browser window (--headed). Only takes effect when the session starts.
- `learn` (boolean): Record a flow in this session (--learn). Only takes effect when the session starts.
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.
- `url` (string, required): The URL to open.

### `do` (~276 tokens)

Have the agent perform ONE verifiable outcome in the session's browser and verify it, e.g. "create a customer named {{runid}} and confirm it appears in the list". One verifiable outcome per do: split multi-part tasks into several calls. State expected values in the sentence. Credentials: write each secret as one {{env:NAME}} marker ({{totp:NAME}} for a one-time code), exactly as written: the marker alone, never the value and never $NAME. NAME must be set in the environment the MCP server was started with. Never ask the user for a secret value. Needs a model API key in the server environment. Returns the report (status, summary, evidence values). Exit 1 = the agent could not complete it.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `instruction` (string, required): The outcome to achieve and how to verify it (sent on stdin, so any text is safe).
- `max_turns` (integer): Agent turn budget (--max-turns).
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.
- `timeout_s` (integer): Overall deadline in seconds (--timeout).

### `assert` (~237 tokens)

Check a condition on the current page now; never acts. State the expected text in the sentence, e.g. "the order list shows a row with total 42.00". In a learn session a passing assert becomes a flow step that fails the run when it does not hold. Credentials: write each secret as one {{env:NAME}} marker ({{totp:NAME}} for a one-time code), exactly as written: the marker alone, never the value and never $NAME. NAME must be set in the environment the MCP server was started with. Never ask the user for a secret value. isError with exit 1 = the condition did not hold; exit 2 = could not be checked.

Input parameters:

- `condition` (string, required): The condition to check (sent on stdin).
- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.
- `timeout_s` (integer): Deadline in seconds (--timeout).

### `set_var` (~124 tokens)

Set a session variable that later instructions reference as {{name}}; in a learn session it becomes a flow variable that build/check bind with vars. Not for secrets (use {{env:NAME}} markers).

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `name` (string, required): Variable name.
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.
- `value` (string, required): Variable value.

### `peek` (~111 tokens)

Return the session page's URL, title and an accessibility snapshot (no model, no actions).

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `interactive` (boolean): Only interactive elements (--interactive).
- `selector` (string): Limit the snapshot to this CSS selector (--selector).
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.

### `screenshot` (~101 tokens)

Capture the session page as a PNG; returns the image and the file path it was saved to.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `full_page` (boolean): Capture the full scrollable page (--full-page).
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.

### `save_flow` (~154 tokens)

Stop a learn session, save what it recorded as a named flow, then export the flow with its pinned procedures to a bundle file (default .sitelooper/procedures.json in cwd). Closes the session's browser. Then call build_start with the flow name.

Input parameters:

- `bundle` (string): Bundle path, relative to cwd or absolute (default .sitelooper/procedures.json).
- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `name` (string, required): Flow name.
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.

### `list_flows` (~55 tokens)

List saved flows with their step counts, variables and origin.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.

### `build_start` (~246 tokens)

Start a background job that compiles a saved flow (or bundle) into a Playwright .flow.ts/.spec.ts and verifies it (readiness: clean runs). With a reset command (sitelooper.config.json resetCommand) it first converges, re-recording failing steps with the model. Readiness needs a reset command or fixture_isolation. Returns a job_id at once: poll job_status until done/failed (minutes).

Input parameters:

- `converge`: true = --converge (default rounds), N = --converge N rounds, false = --no-converge (compile and readiness only).
- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `fixture_isolation` (boolean): Declare that project fixtures prepare fresh data (--fixture-isolation).
- `flow` (string, required): Flow name or bundle path.
- `vars` (object): Flow variables, passed as repeated --var k=v. "{n}" in a value is replaced per run with a fresh value. Never a secret: use {{env:NAME}} markers in instructions instead.

### `check` (~230 tokens)

Run a compiled <name>.flow.ts once under plain Playwright (no model) and report pass/fail (exit 4 = failed, 2 = could not run). With ready=true it runs the readiness gate (several clean runs) as a background job: the call returns a job_id; poll job_status.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `fixture_isolation` (boolean): Declare that project fixtures prepare fresh data (--fixture-isolation), with ready.
- `flow_file` (string, required): Path to the .flow.ts file, relative to cwd or absolute.
- `ready` (boolean): Readiness check (--ready), run as a job.
- `runs` (integer): Readiness executions (--runs), with ready.
- `vars` (object): Flow variables, passed as repeated --var k=v. "{n}" in a value is replaced per run with a fresh value. Never a secret: use {{env:NAME}} markers in instructions instead.

### `repair_propose` (~184 tokens)

Start a background job that replays a compiled .flow.ts against the app, repairs drifted steps and stages a checked candidate as a proposal file for review (repair --propose); never rewrites the spec. Returns a job_id: poll job_status. Apply a good proposal with repair_apply.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `flow_file` (string, required): Path to the .flow.ts file.
- `proposal_file` (string, required): Where to write the proposal JSON (must not exist yet).
- `vars` (object): Flow variables, passed as repeated --var k=v. "{n}" in a value is replaced per run with a fresh value. Never a secret: use {{env:NAME}} markers in instructions instead.

### `repair_apply` (~74 tokens)

Apply a proposal staged by repair_propose to its flow file exactly as checked (no browser run).

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `proposal_file` (string, required): The proposal JSON path.

### `rerecord` (~277 tokens)

Start a background job that re-records one step of a flow with the agent (optionally with a new instruction), then verifies it over several runs and re-pins it. Needs a model API key. Credentials: write each secret as one {{env:NAME}} marker ({{totp:NAME}} for a one-time code), exactly as written: the marker alone, never the value and never $NAME. NAME must be set in the environment the MCP server was started with. Never ask the user for a secret value. Returns a job_id: poll job_status.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `flow` (string, required): Flow name, bundle or .flow.ts path.
- `instruction` (string): Replacement instruction for the step (sent on stdin). Omit to keep the recorded one.
- `runs` (integer): Verification runs (--runs, default 2).
- `step_id` (string, required): Step id, e.g. "03-create".
- `vars` (object): Flow variables, passed as repeated --var k=v. "{n}" in a value is replaced per run with a fresh value. Never a secret: use {{env:NAME}} markers in instructions instead.

### `job_status` (~111 tokens)

Report a background job started by build_start, check (ready), repair_propose or rerecord: status running|done|failed, the last progress lines, and the final JSON result and exit code when finished. Waits up to wait_s seconds for the job to finish before answering.

Input parameters:

- `job_id` (string, required): The job_id a job-starting tool returned.
- `wait_s` (number): Long-poll: wait up to this many seconds for completion (default 25, max 50).

### `sessions` (~50 tokens)

List browser sessions and whether each is running.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.

### `stop` (~93 tokens)

Stop a browser session (closes its browser and daemon) without saving a flow. Use save_flow instead to keep a learn session's recording.

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.
- `session` (string): Browser session name (default "default"). Each session is its own browser and daemon.

### `doctor` (~66 tokens)

Inspect the setup: browser, Node, and which model provider/API key is in use and why (never shows the key).

Input parameters:

- `cwd` (string): Project directory (absolute) the command runs in; sitelooper.config.json is found from here. Default: the server's working directory.

## Diagnostics

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

## Score history

- 2026-11-05: 75
- 2026-11-04: 74
- 2026-11-03: 74
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 72
- 2026-10-30: 72
- 2026-10-29: 72
- 2026-10-28: 71
- 2026-10-27: 71
- 2026-10-26: 70
- 2026-10-25: 70
- 2026-10-24: 69
- 2026-10-23: 69
- 2026-10-22: 68

## Common questions

### What is the io.github.restspace/sitelooper MCP server?

io.github.restspace/sitelooper is an MCP server listed in the public MCP registry as io.github.restspace/sitelooper. Record a browser flow once with a model, then compile it to a Playwright spec that needs no model. This page covers its npm package (sitelooper).

### Is the io.github.restspace/sitelooper MCP server safe to use?

io.github.restspace/sitelooper scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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.restspace/sitelooper MCP server expose?

io.github.restspace/sitelooper exposes 17 tools: open, do, assert, set_var, peek, and 12 more. Their descriptions and schemas cost roughly 2,582 tokens of context every time the server is loaded.

### Is the io.github.restspace/sitelooper MCP server still maintained?

io.github.restspace/sitelooper is still listed as active in the MCP registry. We last reached this channel on 5 November 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.restspace/sitelooper MCP server under?

io.github.restspace/sitelooper 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

- npm package: https://www.npmjs.com/package/sitelooper
- Socket report: https://socket.dev/npm/package/sitelooper
- Repository: https://github.com/restspace/sitelooper
- Changelog RSS feed: https://verifymcp.io/servers/restspace-sitelooper/sitelooper.xml
- Changelog JSON feed: https://verifymcp.io/servers/restspace-sitelooper/sitelooper.json
- HTML version of this page: https://verifymcp.io/servers/restspace-sitelooper/sitelooper