Kasm MCP Server v2 (roguedev-ai/kasm-mcp-server-v2) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 27 tools. No publisher has claimed this listing.

D
Caution
54/100

Kasm MCP Server v2

Enables AI agents to manage and interact with Kasm Workspaces containerized desktop infrastructure, providing tools for session management, command execution, file operations, and user management via the Model Context Protocol.

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

⚡ 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

roguedev-ai

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
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — get_session_screenshot (line 487: with open(save_to_file, "wb") as f:)
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 2 credentials: KASM_API_KEY, KASM_API_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes26 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.

execute_kasm_command

Execute a command in a Kasm session. Args: kasm_id: ID of the Kasm session command: Command to execute working_dir: Working directory for command execution Returns: Command execution result

create_kasm_session

Create a new Kasm session with the specified workspace image. Args: image_name: Name or ID of the workspace image to launch - Can be a Docker image name like "kasmweb/chrome:1.8.0" - Can be an image ID (UUID) like "01366df3a03b4bccbb8c913846594826" group_id: Group ID for the session Returns: Session

destroy_kasm_session

Destroy an existing Kasm session. Args: kasm_id: ID of the Kasm session to destroy Returns: Destruction result

get_session_status

Get the status of a Kasm session. Args: kasm_id: ID of the Kasm session Returns: Session status information

list_user_sessions

List all active sessions for the current user. Returns: List of user's active sessions

list_all_sessions

List all active sessions in the system (admin). Returns: List of all active sessions

pause_kasm_session

Pause a running Kasm session to free up resources. Args: kasm_id: ID of the Kasm session to pause Returns: Pause operation result

resume_kasm_session

Resume a paused Kasm session. Args: kasm_id: ID of the Kasm session to resume Returns: Resume operation result

get_session_screenshot

Get a screenshot of a Kasm session. Args: kasm_id: ID of the Kasm session save_to_file: Optional path to save the screenshot Returns: Screenshot data or file path

read_kasm_file

Read a file from a Kasm session. Args: kasm_id: ID of the Kasm session file_path: Path to the file to read Returns: File content

write_kasm_file

Write content to a file in a Kasm session. Args: kasm_id: ID of the Kasm session file_path: Path where the file should be written content: Content to write to the file Returns: Write operation result

get_available_workspaces

Get list of available workspace images. Returns: List of available workspace configurations

get_kasm_users

Get list of Kasm users. Returns: List of users in the Kasm system

create_kasm_user

Create a new user account in the Kasm system. Args: username: Username for the new user password: Password for the new user first_name: User's first name (optional) last_name: User's last name (optional) organization: User's organization (optional) phone: User's phone number (optional) locked: Wheth

get_kasm_user

Get details for a specific user. Args: user_id: User ID to retrieve (optional if username provided) username: Username to retrieve (optional if user_id provided) Returns: User details

update_kasm_user

Update an existing user's details. Args: user_id: User ID to update username: New username (optional) password: New password (optional) first_name: New first name (optional) last_name: New last name (optional) organization: New organization (optional) phone: New phone number (optional) locked: New l

delete_kasm_user

Delete a user from the Kasm system. Args: user_id: User ID to delete force: Force deletion even if user has active sessions Returns: Deletion result

logout_kasm_user

Logout all sessions for a specific user. Args: user_id: User ID to logout Returns: Logout result

get_session_frame_stats

Get frame rendering statistics for a Kasm session. Args: kasm_id: ID of the Kasm session client: Which client to retrieve stats for ('none', 'auto', 'all', or websocket_id) Returns: Frame statistics including timing and performance metrics

get_session_bottleneck_stats

Get CPU and network bottleneck statistics for a Kasm session. Args: kasm_id: ID of the Kasm session Returns: Bottleneck statistics showing CPU and network constraints

get_session_recordings

Get session recordings for a specific Kasm session. Args: kasm_id: ID of the Kasm session download_links: Whether to include pre-authorized download links Returns: List of session recordings with metadata and optional download links

add_user_to_group

Add a user to an existing Kasm group

remove_user_from_group

Remove a user from an existing Kasm group

get_login_link

Generate a passwordless login link for a user

get_deployment_zones

Get list of Kasm deployment zones

get_sessions_recordings

Get recordings for multiple Kasm sessions

// 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.
configKASM_API_URL
🔐 secretKASM_API_KEYyour_api_key_here
🔐 secretKASM_API_SECRETyour_api_secret_here
configKASM_USER_ID
configKASM_GROUP_ID
configKASM_DEFAULT_GROUP_ID
configLOG_LEVEL
configKASM_ALLOWED_ROOTS/home/kasm-user
// 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

27/27 tools missing one or more hints — execute_kasm_command (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_kasm_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); destroy_kasm_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +24 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — get_session_screenshot (line 487: with open(save_to_file, "wb") as f:)

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

17/21 tool handlers declare input schemas (81%)

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

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

get_session_screenshot: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

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/roguedev-ai/kasm-mcp-server-v2?variant=verified)](https://m8ven.ai/mcp/roguedev-ai/kasm-mcp-server-v2)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 433c2825b4c3439193578b170907ec6c6f94ce48
code hash: 7e0b4fb4361b483bb6903928780d182af21bcbd61db76b1dc0b199d0dd3a5f28
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