Severalnines CCX MCP Server (severalnines/ccx-mcp) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 30 tools. No publisher has claimed this listing.

Caution

54/100

Severalnines CCX MCP Server

Item: Severalnines CCX MCP Server
Rating: 54
Author: M8ven

Enables management of CCX database clusters through AI assistants, supporting operations such as datastore creation, scaling, and performance monitoring. It provides a comprehensive toolset for handling backups, database users, and firewall rules across various database engines including PostgreSQL, MySQL, and Redis.

→ severalnines/ccx-mcp · listed on glama

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 push why connect →

Who stands behind it

severalnines

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

🚨

Known vulnerabilities in dependencies: 1 critical, 3 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 2 credentials: CCX_CLIENT_SECRET, CCX_PASSWORD

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes30 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.

ccx_add_node

Add a new node to a CCX datastore (horizontal scale-out). The new node will be provisioned with the same or specified instance size and join the cluster as a replica.

ccx_apply_parameter_group

Apply a parameter group to a datastore. This creates a job on the cluster to update its database configuration. Blocked by protection mode (CCX_PROTECT) by default.

ccx_create_database

Create a new database on a CCX datastore

ccx_create_datastore

Create a new CCX database cluster. Requires db_vendor, cloud_provider, and cloud_region. All other options have smart defaults from the deployment wizard.

ccx_create_db_user

Create a new database user on a CCX datastore

ccx_create_firewall_rule

Add a trusted source (firewall rule) to a CCX datastore. Allows the specified CIDR to connect to the database.

ccx_create_parameter_group

Create a new parameter group (database configuration template). Use ccx_list_default_parameters first to see available parameters and their valid values.

ccx_delete_database

Delete a database from a CCX datastore. This is DESTRUCTIVE and cannot be undone. Blocked by protection mode (CCX_PROTECT) by default.

ccx_delete_datastore

Delete a CCX datastore. This is DESTRUCTIVE and cannot be undone. You must set confirm to true. Blocked by protection mode (CCX_PROTECT) by default.

ccx_delete_db_user

Delete a database user from a CCX datastore. This is DESTRUCTIVE and may break applications using this user. You must set confirm to true. Use ccx_list_db_users first to see existing users and their host restrictions. Blocked by protection mode (CCX_PROTECT) by default.

ccx_delete_firewall_rule

Remove a trusted source (firewall rule) from a CCX datastore. This is DESTRUCTIVE and may lock out applications or users. You must set confirm to true. Revokes the specified CIDR's access to the database. Blocked by protection mode (CCX_PROTECT) by default.

ccx_delete_parameter_group

Delete a parameter group. This is DESTRUCTIVE and cannot be undone. You must set confirm to true. Blocked by protection mode (CCX_PROTECT) by default.

ccx_get_connection_string

Get connection strings for a CCX datastore. Returns URI, CLI command, JDBC, and environment variable formats. Useful for configuring applications to connect to the database.

ccx_get_datastore

Get detailed information about a specific CCX datastore including credentials, status, and current job progress

ccx_get_nodes

Get the list of nodes for a specific CCX datastore, including their roles, status, and IP addresses

ccx_get_parameter_group

Get a single parameter group with its full list of parameters. Use this to inspect the current configuration values for a parameter group.

ccx_get_stats

ccx_get_top_queries

Get the slowest queries running on a CCX datastore, ranked by total execution time. Use this to diagnose performance problems, identify queries that need optimization, or find missing indexes.

ccx_list_backups

List available backups for a CCX datastore. Use this to check backup history, find a backup to restore, or verify that backups are running successfully.

ccx_list_clouds

List available cloud providers and their regions for deploying CCX database clusters

ccx_list_databases

List databases on a specific CCX datastore

ccx_list_datastores

List all CCX database clusters (datastores) with their status, vendor, and cloud provider

ccx_list_db_users

List database users for a specific CCX datastore

ccx_list_default_parameters

Get the default database parameters for a specific vendor and version. Useful before creating a parameter group to see available parameters, their default values, types, and validation options.

ccx_list_firewall_rules

List trusted sources (firewall rules) for a CCX datastore. Shows which CIDRs are allowed to connect.

ccx_list_parameter_groups

List all parameter groups (database configuration templates). Optionally filter by database vendor, version, or name. Returns a paginated list with name, vendor, version, description, and associated datastores.

ccx_list_plans

List available instance sizes, volume types, and volume sizes for a specific cloud provider

ccx_restore_backup

Restore a CCX datastore from a backup. This is a DESTRUCTIVE operation that replaces current data with the backup contents. Use ccx_list_backups first to find available backup IDs. Blocked by protection mode (CCX_PROTECT) by default.

ccx_scale_datastore

Scale a CCX datastore by resizing the instance (CPU/RAM) or expanding storage. Use this when a database needs more resources to handle increased load.

ccx_update_parameter_group

Update a parameter group's name, description, and/or parameters. Optionally sync changes to all associated datastores.

// known CVEs in dependencies1 critical3 high

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

criticalvitest@3.1.1GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

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.

configCCX_BASE_URLendpoint <url>

configCCX_CLIENT_IDclient-id <id>

🔐 secretCCX_CLIENT_SECRETclient-secret <secret>

🔐 secretCCX_PASSWORDpassword <password>

configCCX_PROTECTprotect <true\false>

configCCX_USERNAMEusername <email>

// 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

30/30 tools missing one or more hints — ccx_add_node (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ccx_apply_parameter_group (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ccx_create_database (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +27 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

Only 2/30 tool handlers declare input schemas (7%)

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 0/30 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.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

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 7 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/severalnines/ccx-mcp?variant=verified)](https://m8ven.ai/mcp/severalnines/ccx-mcp)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: beb15bd4a166989b31c5799e0335c2b4ef43b9c6

code hash: c82dfbf53946fba7cbaf95a74365aa80dc7aa502e29ec201ec926c884f1bbdd9

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