Secure Host MCP (Razewang/secure-host-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 29 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

Secure Host MCP

Exposes a Windows or Linux host terminal to remote MCP clients via Streamable HTTP, enabling command execution, tunnel management, and privileged operations with security features like OAuth and audit logging.

→ Razewang/secure-host-mcp· listed on glama

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

Razewang

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
✅
29 tools verified — handlers match their declared behaviour
15 read-only tools verified — handlers contain no write/delete/exec
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes29 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

system_info

Read host system and privilege information

execute_command

Execute one command as the MCP service account

start_job

Start a tracked background command

job_status

Read tracked background job status

read_job_output

Read background job output from an offset

write_job_input

Write UTF-8 input to a running background job and optionally close stdin

cancel_job

Cancel a tracked background job

execute_elevated

Execute a command through administrator mode or the privileged helper

set_admin_mode

Restart the whole MCP as root/SYSTEM through the privileged helper, or request local service-account restoration.

tunnel_inspect

Inspect cloudflared and frpc installation/configuration with secrets redacted

tunnel_start

Start a configured tunnel client

tunnel_stop

Stop a tunnel client started by this service

create_terminal

Create a persistent interactive PTY terminal session

read_terminal

Read bounded PTY output from a monotonic byte offset

write_terminal

Write UTF-8 input to a running PTY terminal

resize_terminal

Resize a running PTY terminal

interrupt_terminal

Send Ctrl+C to a running PTY terminal

close_terminal

Close a PTY terminal session

workspace_info

Show the configured coding workspace and its limits

read_file

Read a bounded UTF-8 file range inside the coding workspace

list_directory

List entries inside the coding workspace without following symbolic links

list_files

Recursively list coding-workspace files with an optional glob

search_text

Search UTF-8 files in the coding workspace using literal text or a regular expression

apply_patch

Atomically create, uniquely replace, or delete files inside the coding workspace

git_status

Read Git working-tree status for the coding workspace

git_diff

Read a bounded staged or unstaged Git diff

git_log

Read bounded Git commit history for the coding workspace

git_show

Show a bounded Git revision and patch

git_blame

Read bounded Git line attribution for one workspace file

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configSECURE_HOST_MCP_HOME(by default ~/.secure-host-mcp). The status command
// quality suggestions

All four hints declared on every tool

28/29 tools missing one or more hints — system_info (missing: destructiveHint, idempotentHint); execute_command (missing: idempotentHint); start_job (missing: idempotentHint), +25 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 6/29 tools referenced in tests (21%)

Write tests that reference each tool by name so every tool has at least one test.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/razewang/secure-host-mcp)](https://m8ven.ai/mcp/razewang/secure-host-mcp)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 200cb9474aa81b48ae79319dac63f689e6b351ee
code hash: c5025d4eeae18bf9e58464efe8d4db65f53fadcf6019eee62bf2bb676d539e2d
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client