Sandbox Studio MCP Server (sandboxstudiosoftware/sandbox-studio-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 81 tools. No publisher has claimed this listing.

D
Caution
56/100

Sandbox Studio MCP Server

Connects AI assistants to the Sandbox Studio API to manage AWS sandbox accounts, leases, templates, events, and settings through natural language conversations.

Caution. Specific findings reduced this grade. They are listed on the page. 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

sandboxstudiosoftware

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 →

Install from

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
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// tools this server exposes81 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.

list_accounts

List all registered sandbox accounts with pagination. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

import_accounts

Import AWS accounts into the sandbox pool

eject_accounts

Eject AWS accounts from the sandbox pool

list_unregistered_accounts

List AWS accounts available in the organization but not yet registered in the sandbox pool. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

get_account

Get details of a specific sandbox account by AWS account ID

get_account_lease_history

Get lease history for a specific sandbox account. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

retry_account_cleanup

Retry cleanup for a sandbox account that failed its previous cleanup attempt

get_account_cleanup_logs

Get cleanup logs for a specific sandbox account

get_account_failed_resources

Get resources that failed cleanup for a specific sandbox account

list_approvals

List pending lease approval requests. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

list_events

List sandbox events with optional status filtering. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

create_event

Create a new sandbox event with provisioned accounts and team assignments

get_event

Get details of a specific event

update_event

Update an existing event's configuration

get_event_teams

Get teams for a specific event

add_event_teams

Add teams to an event

terminate_event

Terminate an event and all its associated leases

start_event

Start a provisioned event, granting access to teams

provision_event

Provision accounts for an event

assign_event_team_owner

Assign an owner to a team within an event

get_lease_costs

Get lease cost reporting data with optional grouping and filtering

trigger_drift_detection

Trigger an on-demand drift detection job across sandbox accounts

trigger_lease_monitoring

Trigger an on-demand lease monitoring job to check budgets and durations

list_leases

List leases with optional filtering by status, user, date, and pagination. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

get_lease

Get details of a specific lease by ID

request_lease

Request a new lease from a template. May require approval depending on template configuration.

update_lease

Update an existing lease's budget, duration, or expiration settings

suspend_lease

Suspend an active lease

resume_lease

Resume a suspended lease

review_lease

Approve or deny a pending lease request

terminate_lease

Terminate an active lease and begin cleanup. ⚠️ WARNING: When terminating multiple leases, ALWAYS confirm with the user: - Clearly list which leases will be terminated (showing owner name, template name, and lease ID) - Distinguish between the user's OWN leases and OTHER users' leases - If the requ

withdraw_lease

Withdraw a pending lease request before it is approved

get_lease_team_members

Get the team members who have access to a shared lease

share_lease

Share a lease with additional users

unshare_lease

Remove users from a shared lease

get_lease_logs

Get the setup/activity logs for a lease

get_lease_secrets

Get the build output secrets (credentials) for a lease

get_cleanup_settings

Get the account cleanup (nuke) configuration

update_cleanup_settings

Update the account cleanup (nuke) configuration

get_cleanup_hook

Get a cleanup hook script by type

update_cleanup_hook

Update a cleanup hook script

get_email_settings

Get email notification template settings

update_email_settings

Update email notification template settings

send_test_email

Send a test email to verify email/SMTP configuration

get_smtp_settings

Get SMTP configuration for outbound email

update_smtp_settings

Update SMTP configuration for outbound email

get_global_config

Get platform-wide global configuration

update_global_config

Update platform-wide global configuration. IMPORTANT: When updating lease settings: - If changing 'maxBudget', ask the user if they also want to enable 'requireMaxBudget' (which forces all templates to have a budget set). Otherwise the max budget only acts as an upper cap for templates that already

get_runtime_config

Get the runtime configuration for the current Sandbox Studio deployment

list_public_templates

List public account templates available for lease requests. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

get_template

Get full details of an account template by ID

get_template_info

Get basic details (name, description, icon, colour) of a template

list_managed_templates

List templates managed by the current user. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

create_template

Create a new account template. Before creating a template, ask the user if they would like to: - Add tags for categorisation (e.g., "ai", "development", "training", "data-science") - Set a custom icon and colour - Specify who should manage or approve leases When providing a launchSetupScript or la

delete_template

Delete an account template

update_template_info

Update basic details of a template (name, description, icon, colour)

get_template_leases

Get leases associated with a template. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

get_template_permissions

Get the IAM permission configuration for a template

update_template_permissions

Update the IAM permission configuration for a template

get_template_launch_settings

Get launch/setup settings for a template

update_template_launch_settings

Update launch/setup settings for a template. IMPORTANT: When writing launch setup scripts or run scripts, use 'set-sandbox-output' to expose variables to the lease owner instead of using 'echo'. This command registers outputs in the Sandbox Studio UI. Usage: set-sandbox-output --name <name> --va

update_template_budget

Update budget settings for a template

update_template_duration

Update duration settings for a template

update_template_managers

Update managers and approval settings for a template

update_template_sharing

Update sharing settings for a template

update_template_tags

Update tags for a template. Tags are key-value pairs with a name and value.

list_users

List users from the connected identity provider. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

list_groups

List groups from the connected identity provider. Results are paginated — if the response contains a nextPageIdentifier, inform the user that more results are available and offer to fetch the next page.

validate_users

Validate that user IDs exist in the identity provider

update_preferences

Update the current user's preferences

list_all_oauth_clients

List all OAuth API clients (admin endpoint)

list_my_oauth_clients

List OAuth API clients owned by the current user

create_oauth_client

Create a new OAuth API client for machine-to-machine integrations

delete_oauth_client

Delete an OAuth API client

update_oauth_client

Update an OAuth API client's description

get_terms_of_service

Get the latest published terms of service

list_terms_versions

List all published terms of service versions

get_terms_version

Get a specific terms of service version

publish_terms_of_service

Publish a new terms of service version

get_tags

Get all unique tags defined across account templates

validate_s3_path

Validate that an S3 path exists and is accessible

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// 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.
configSS_LOG_LEVEL
// 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

81/81 tools missing one or more hints — list_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); import_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); eject_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +78 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 inputs are validated

68/81 tool handlers declare input schemas (84%)

Declare an inputSchema with zod/joi/yup on every tool definition.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 0/81 tools referenced in tests (0%)

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

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

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 6 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 Verified](https://m8ven.ai/badge/mcp/sandboxstudiosoftware/sandbox-studio-mcp?variant=verified)](https://m8ven.ai/mcp/sandboxstudiosoftware/sandbox-studio-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 91080f2e9616bc47c98d8640696a08c10afaec93
code hash: af792ecd2163a7e8f5c1d89d36e76a6b47ad71c9e5bc8e8f175111c9f0756851
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