io.github.charliemtnez/ghost-inspector-mcp

io.github.charliemtnez/ghost-inspector-mcpv0.2.0Browser Automation

Analyze, validate and safely update Ghost Inspector end-to-end browser tests

The current version, v0.2.0, was published to the official MCP registry on 2026-08-06. It is distributed as ghost-inspector-mcp on npm, filed under Browser Automation by this index, and declares 4 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using io.github.charliemtnez/ghost-inspector-mcp in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-09-27 00:10 UTC

screened 2026-08-06tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No malicious instructions found”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b
- Still current: the description we screened is unchanged, re-checked against the registry
- The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-09-20).

Contracts can change after screening, with no version bump. The gate pins io.github.charliemtnez/ghost-inspector-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Cite this record

People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.

Markdown

[Independent trust record for io.github.charliemtnez/ghost-inspector-mcp](https://mcpindex.ai/server/io-github-charliemtnez-ghost-inspector-mcp) - screening verdict, registry provenance, and contract drift monitoring.

HTML

<a href="https://mcpindex.ai/server/io-github-charliemtnez-ghost-inspector-mcp">Independent trust record for io.github.charliemtnez/ghost-inspector-mcp</a> - screening verdict, registry provenance, and contract drift monitoring.

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-charliemtnez-ghost-inspector-mcp)](https://mcpindex.ai/server/io-github-charliemtnez-ghost-inspector-mcp)

HTML

<a href="https://mcpindex.ai/server/io-github-charliemtnez-ghost-inspector-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-charliemtnez-ghost-inspector-mcp" alt="mcpindex verdict" height="20" /></a>

Environment variables

GHOST_INSPECTOR_API_KEY

requiredsecret

Your personal Ghost Inspector key, from Account Settings then API Access. Read fresh on every call, never written to disk, never echoed back.

GHOST_INSPECTOR_ORG_ID

Organization id. Needed only to execute a validation; read it from gi_whoami.

GHOST_INSPECTOR_ALLOW_WRITES

Set to exactly true to register the two mutating tools. Anything else keeps the server read-only.

GHOST_INSPECTOR_ALLOW_RUNS

Set to "true" to let gi_run_test execute a stored test against a real environment, which can submit a real form. Deliberately not implied by GHOST_INSPECTOR_ALLOW_WRITES: an edit can be rolled back from the backup this server returns, a submission cannot. Defaults to false.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Browser Automation

Qlane

ai.qlane/qlane

AI QA that runs your app in a browser on every pull request: projects, test targets, test cases.

FindMeTool

com.findmetool/lookup

Look up a FindMeTool page URL. Tool input stays in the browser.

io.github.cherchyk/browser

MCP server for loading authenticated web pages using Chrome DevTools Protocol

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "ghost-inspector-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "ghost-inspector-mcp"
      ],
      "env": {
        "GHOST_INSPECTOR_API_KEY": "<your-ghost_inspector_api_key>",
        "GHOST_INSPECTOR_ORG_ID": "<ghost_inspector_org_id>",
        "GHOST_INSPECTOR_ALLOW_WRITES": "<ghost_inspector_allow_writes>",
        "GHOST_INSPECTOR_ALLOW_RUNS": "<ghost_inspector_allow_runs>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "ghost-inspector-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "ghost-inspector-mcp"
      ],
      "env": {
        "GHOST_INSPECTOR_API_KEY": "<your-ghost_inspector_api_key>",
        "GHOST_INSPECTOR_ORG_ID": "<ghost_inspector_org_id>",
        "GHOST_INSPECTOR_ALLOW_WRITES": "<ghost_inspector_allow_writes>",
        "GHOST_INSPECTOR_ALLOW_RUNS": "<ghost_inspector_allow_runs>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- ghost-inspector-mcp

Claude Code (claude mcp add)

claude mcp add --scope user ghost-inspector-mcp -- npx -y -- ghost-inspector-mcp

Gemini CLI (gemini mcp add)

gemini mcp add -s user ghost-inspector-mcp npx -y -- ghost-inspector-mcp

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-charliemtnez-ghost-inspector-mcp

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.2.0
category: Browser Automation
verdict expires: 2026-09-27
quality: 79 / 100
operator: charliemtnez

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 967,663). Verify it yourself.

Links

Repository →