agent-sandbox (HatriGt/agent-sandbox) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 9 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

agent-sandbox

A cloud sandbox for coding agents, on your own server. Start a run from the dashboard, from any agentic IDE (Cursor, Claude Code, Codex, VS Code), or from a script — it runs in an isolated KVM microVM and streams back live.

→ HatriGt/agent-sandbox· listed on github_repo_search

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

HatriGt

Source: github_repo_search

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

GitHub

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
✅
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.
🔐
You'll be asked for 5 credentials: DASHBOARD_TOKEN, GITHUB_OAUTH_CLIENT_SECRET, MCP_HTTP_TOKEN, NPM_TOKEN, SECRETS_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes11 tools · 2 behind config

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.

delegate
status
resume
teardown

Stop and remove the box for a delegated session.

pool_status

Show the warm pool status: how many pre-booted boxes are available vs the target.

monitor
watch
ask
gh_token_add
list_reposbehind config
attach_repobehind config
// 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.
configADMIN_GITHUB_LOGINS
configANDROID_CERT_SHA256
configANDROID_PACKAGE
configASB_DOMAINSelf-hosted, single operator: deploy (below), open https://<>/dashboard, paste your
configASK_MODELASK_TIMEOUT_MS (default 45s, under the client's request timeout); points the co-pilot at
configASK_TIMEOUT_MS(default 45s, under the client's request timeout); ASK_MODEL points the co-pilot at
configBETA
configBILLING_URLtrial). Unset for self-hosting: no clock. is where Upgrade points.
🔐 secretDASHBOARD_TOKEN
configDATA_DIR
configEGRESS_ALLOW_ALL
configEGRESS_DOMAINS
configGITHUB_OAUTH_CLIENT_ID
🔐 secretGITHUB_OAUTH_CLIENT_SECRET
configMCP_HTTP_HOST
configMCP_HTTP_PORT
🔐 secretMCP_HTTP_TOKENonce. To let several people in, see [Multi-user mode](#multi-user-mode).
configMSB_MAX_BOXES
configMSB_POOL_REFILL_MS
configMSB_POOL_SIZE
configMSB_SNAPSHOT
configNOTIFY_WEBHOOK_URL
🔐 secretNPM_TOKEN. No GH_TOKEN/GIT_AUTHOR_ — GitHub access is reactive and resolved per repo from
configPUBLIC_URL
configRATE_LIMIT_PER_MIN
🔐 secretSECRETS_KEY
configSSH_EXTRA_OPTS
configTRIAL_DAYSPlans — =7 starts every new account on a free trial; when it lapses the account keeps
configWAIT_INTERVAL_MS
configWAIT_TIMEOUT_MS(run:running — an explicit "reconnect via status"). The wait window is bounded (,
configWORKSPACE_DIRis what lets you say "delegate this" with no repo argument — it tells the server
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

11/11 tools missing one or more hints — delegate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); resume (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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.

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/hatrigt/agent-sandbox)](https://m8ven.ai/mcp/hatrigt/agent-sandbox)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 7f08c0371172da17b5f6b692e8e175496a311398
code hash: 418c4e2d456aabcb4d821eee4e354d7710f5472e614c9dd517f59af1cfa4b3eb
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