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.

Ghost Hands

PYPI · GHOST-HANDS

Governed browser hands for AI agents: classified actions, human approvals, replayable audit trails.

Available components

72 Trust /100

Last scanned (5 hours ago)

Scores higher than 67% of PyPI servers

Category Browser Automation

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to littlestjames82-sys/ghost-hands). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability53
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 223 tokens (~55/item across 4 items; 4 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
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.

  • 4 Nov 26 72

    First indexed and scored.

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 5 Nov 2026 · Analysed pypi/ghost-hands@0.9.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo littlestjames82-sys/ghost-hands
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/littlestjames82-sys/ghost-hands/.github/workflows/publish.yml@refs/tags/v0.9.3
Rekor log index 3687241883
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:5c27e4ac4cce1eb9dfe7608a2809063f8c9266408e72aec6d6531e047635be3f

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~223 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
hands_act ~69

Perform one governed action (e.g. {"kind":"click","target":3}) on the perceived page. Consequential actions are denied without an approver (or decided by the phone when GHOST_HANDS_APPROVER=phone); the response states which channel decided.

NameTypeReqDescription
actionobjectyes–

No output schema declared.

No examples provided.

hands_perceive ~44

Open a URL (or install a fake web via 'pages') and return the numbered element map.

NameTypeReqDescription
pagesobject––
urlstring––

No output schema declared.

No examples provided.

hands_run ~90

Run scripted steps through the governed Runner. driver: 'fake', 'chromium', 'simphone' or 'android' (default: the session body, GHOST_HANDS_DRIVER).

NameTypeReqDescription
approve_allboolean––
driverstring––
goalstring––
pagesobject––
start_urlstring––
stepsarrayyes–

No output schema declared.

No examples provided.

hands_trail ~20

Return this session's trail events and per-run accounting.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Ghost Hands MCP server?

Ghost Hands runs locally as a PyPI package, launched with uvx ghost-hands. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · ghost-hands

# add to Claude Code
claude mcp add littlestjames82-sys-ghost-hands -- uvx ghost-hands
Common questions

What is the Ghost Hands MCP server?

Ghost Hands is an MCP server listed in the public MCP registry as io.github.littlestjames82-sys/ghost-hands. Governed browser hands for AI agents: classified actions, human approvals, replayable audit trails. This page covers its PyPI package (ghost-hands).

Is the Ghost Hands MCP server safe to use?

Ghost Hands scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 Ghost Hands MCP server expose?

Ghost Hands exposes 4 tools: hands_perceive, hands_act, hands_run, hands_trail. Their descriptions and schemas cost roughly 223 tokens of context every time the server is loaded.

Is the Ghost Hands MCP server still maintained?

Ghost Hands 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 Ghost Hands MCP server under?

Ghost Hands declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.