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.inSideos-designs/cowork-qa

NPM · COWORK-QA-MCP · SCANNED SEP 20

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

Available components

0 this week 80 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 Security92
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • 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. View diagnostics → Partial
  • 31 of 98 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability75
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 239 tokens (~47/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage81
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 44% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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.inSideos-designs/cowork-qa MCP server?

io.github.inSideos-designs/cowork-qa runs locally as an npm package, launched with npx -y cowork-qa-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 · cowork-qa-mcp

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

  • 20 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.

  • 18 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.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 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 0
    • Security disclosure: unverified → fail functional
  • 11 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 0
    • Security disclosure: fail → unverified functional
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/cowork-qa-mcp@0.1.1

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 →

Install scripts 1 script
Hook Tier Command
postinstall unreviewed playwright install chromium

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

Dependencies 98 packages
Packages resolved 98
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~239 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
qa_get_trace ~54

Return the full recorded trace (goal, every step, final URL, final aria-snapshot) so the calling LLM can judge whether the goal was achieved. Call session_end first.

NameTypeReqDescription
session_idstringyes

No output schema declared.

No examples provided.

session_act ~76

Perform a browser action in a session: goto | click | fill | press | eval.

NameTypeReqDescription
actionstringyes
session_idstringyes
targetstringSelector for click/fill, URL for goto, key for press, JS expression for eval.
valuestringValue for fill.

No output schema declared.

No examples provided.

session_end ~31

Close the session, persist the trace to disk, and return the path.

NameTypeReqDescription
session_idstringyes

No output schema declared.

No examples provided.

session_observe ~31

Return the current URL and aria-snapshot of the session's page.

NameTypeReqDescription
session_idstringyes

No output schema declared.

No examples provided.

session_start ~47

Open a fresh browser tab and start recording a goal-driven session.

NameTypeReqDescription
goalstringyesPlain-English goal the agent will try to accomplish.
urlstringOptional starting URL.

No output schema declared.

No examples provided.

Common questions

What is the io.github.inSideos-designs/cowork-qa MCP server?

io.github.inSideos-designs/cowork-qa is an MCP server listed in the public MCP registry as io.github.inSideos-designs/cowork-qa. Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots. This page covers its npm package (cowork-qa-mcp).

Is the io.github.inSideos-designs/cowork-qa MCP server safe to use?

io.github.inSideos-designs/cowork-qa scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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.inSideos-designs/cowork-qa MCP server expose?

io.github.inSideos-designs/cowork-qa exposes 5 tools: session_start, session_act, session_observe, session_end, qa_get_trace. Their descriptions and schemas cost roughly 239 tokens of context every time the server is loaded.

Is the io.github.inSideos-designs/cowork-qa MCP server still maintained?

io.github.inSideos-designs/cowork-qa 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.inSideos-designs/cowork-qa MCP server under?

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