word-mcp-live@1.6.22
CAUTION· not startedPublisher claims: "MCP server for Microsoft Word — live editing on Windows (COM) and macOS (JXA), plus cross-platform python-docx tools" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
MCP_AUTHORMCP_AUTHOR_INITIALSConfiguration, not credentials: MCP_HOST, MCP_PATH, MCP_PORT, MCP_SSE_PATH, MCP_TRANSPORT- Where it talks to
- no vendor host named in the codeAlso openxmlformats.org, microsoft.com, live.net — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names openxmlformats.org, microsoft.com, live.net as well as its own vendor. The guard injects MCP_AUTHOR, MCP_AUTHOR_INITIALS only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
subprocess.run([pip_path, 'install', '-r', requirements_path], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print("Loading configuration from .env file...", file=sys.stderr)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, "-m", "pip", "install", "word-mcp-live"], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print(f"Created .env.example at: {env_example_path}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Docker</b></summary> ```json { "mcpServers": { "word": { "command": "docker", "args": ["run", "-i", "--rm", "ghcr.io/ykarapazar/word-mcp-live"], "enFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.run([pip_path, 'install', 'fastmcp'], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([pip_path, 'install', 'python-docx'], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.<summary><b>OpenAI Codex (CLI, desktop app, IDE)</b></summary> ```bash codex mcp add word --env MCP_AUTHOR="Your Name" -- uvx word-mcp-live ``` Or add to `~/.coFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Create .env.example fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_example_path = os.path.join(base_path, '.env.example')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load environment variables from .env file. This must run before anythingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run([sys.executable, '-m', 'venv', venv_path], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, capture_output=True, text=True, timeout=60, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.'Open "/tmp/_word_hf_cleared.txt" For Output As #fileNum',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for word-mcp-live@1.6.22 as of 33 min ago. This is the package itself, not its dependencies.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim ykarapazar: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.