RocketCyber
OCI · GHCR.IO/WYRE-AI/ROCKETCYBER-MCP:V1.5.7 · SCANNED SEP 20
MCP server for RocketCyber Managed SOC — incidents, alerts, agents, and customer telemetry.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 10 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability82
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1134 tokens (~87/item across 13 items; 10 tools + 3 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the RocketCyber MCP server?
RocketCyber runs locally as a container image, launched with docker run --rm -i ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7
claude mcp add wyre-ai-rocketcyber-mcp -- docker run --rm -i ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7
{
"mcpServers": {
"wyre-ai-rocketcyber-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"
]
}
}
} {
"servers": {
"wyre-ai-rocketcyber-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"
]
}
}
} codex mcp add wyre-ai-rocketcyber-mcp -- docker run --rm -i ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"wyre-ai-rocketcyber-mcp": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"
],
"enabled": true
}
}
} mcp_servers:
wyre-ai-rocketcyber-mcp:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"] {
"McpServers": {
"wyre-ai-rocketcyber-mcp": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"
]
}
}
} {
"mcpServers": {
"wyre-ai-rocketcyber-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +4
- Stability: unverified → 0.27 ▲ functional
- 9 Sept 26 42
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
rocketcyber_get_account ~34
Get RocketCyber account information
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Account ID (optional, defaults to current account) |
No output schema declared.
No examples provided.
rocketcyber_get_defender ~30
Get Windows Defender status from RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Account ID |
No output schema declared.
No examples provided.
rocketcyber_get_event_summary ~41
Get event summary/statistics from RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Account ID |
| dates | string | – | Date range filter |
No output schema declared.
No examples provided.
rocketcyber_get_office ~31
Get Office 365 status from RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Account ID |
No output schema declared.
No examples provided.
rocketcyber_list_agents ~106
List monitored agents/endpoints in RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Filter by account ID |
| connectivity | string | – | Filter by connectivity status (online/offline) |
| dates | string | – | Date range filter |
| hostname | string | – | Filter by hostname |
| page | number | – | Page number |
| pageSize | number | – | Results per page |
| platform | string | – | Filter by platform |
| sort | string | – | Sort field |
No output schema declared.
No examples provided.
rocketcyber_list_apps ~79
List managed apps in RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Filter by account ID |
| name | string | – | Filter by name |
| page | number | – | Page number |
| pageSize | number | – | Results per page |
| sort | string | – | Sort field |
| status | string | – | Filter by status |
No output schema declared.
No examples provided.
rocketcyber_list_events ~275
List security events in RocketCyber. Requires appId - unlike every other list_* tool here, the underlying RocketCyber API rejects this specific endpoint outright (400 "appId is required") if it's omitted, regardless of any other filter supplied. Each RocketCyber "app" is a distinct monitored integration/module (Defender Manager, Office 365 Risk Detection, Datto Ransomware Detection, etc.) - events are always scoped to exactly one. Call rocketcyber_list_apps to see every app this account has and its ID, or rocketcyber_get_event_summary first (no appId needed) to see actual per-app event counts for this account and pick the one with data rather than guessing.
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Filter by account ID |
| appId | number | yes | REQUIRED. The RocketCyber app/module ID to scope events to (e.g. 34 = Defender Manager). See the tool description for how to discover the right value. |
| dates | string | – | Date range filter |
| eventType | string | – | Filter by event type |
| hostname | string | – | Filter by hostname |
| page | number | – | Page number |
| pageSize | number | – | Results per page |
| severity | string | – | Filter by severity |
| sort | string | – | Sort field |
No output schema declared.
No examples provided.
rocketcyber_list_firewalls ~91
List firewall devices in RocketCyber
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Filter by account ID |
| connectivity | string | – | Filter by connectivity status |
| hostname | string | – | Filter by hostname |
| page | number | – | Page number |
| pageSize | number | – | Results per page |
| sort | string | – | Sort field |
| vendor | string | – | Filter by vendor |
No output schema declared.
No examples provided.
rocketcyber_list_incidents ~206
List security incidents in RocketCyber. By default, long free-text fields (description, remediation) are truncated to ~300 characters, and the total response is capped at ~40,000 characters (a size cap) — if a page does not fit, only the first incidents are returned and the message says how many; use a smaller pageSize with page to paginate through the rest. Pass verbose: true for full untruncated text.
| Name | Type | Req | Description |
|---|---|---|---|
| accountId | number | – | Filter by account ID |
| dates | string | – | Date range filter |
| page | number | – | Page number |
| pageSize | number | – | Results per page |
| severity | string | – | Filter by severity |
| sort | string | – | Sort field |
| status | string | – | Filter by status |
| title | string | – | Filter by title |
| verbose | boolean | – | Return full untruncated description/remediation text (default false: truncated to ~300 characters) |
No output schema declared.
No examples provided.
rocketcyber_test_connection ~19
Test the connection to RocketCyber API
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the RocketCyber MCP server?
RocketCyber is an MCP server listed in the public MCP registry as io.github.WYRE-AI/rocketcyber-mcp. MCP server for RocketCyber Managed SOC, incidents, alerts, agents, and customer telemetry. This page covers its container image (ghcr.io/wyre-ai/rocketcyber-mcp:v1.5.7).
Is the RocketCyber MCP server safe to use?
RocketCyber scores 47 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the RocketCyber MCP server expose?
RocketCyber exposes 10 tools: rocketcyber_test_connection, rocketcyber_get_account, rocketcyber_list_agents, rocketcyber_list_incidents, rocketcyber_list_events, and 5 more. Their descriptions and schemas cost roughly 912 tokens of context every time the server is loaded.
Is the RocketCyber MCP server still maintained?
RocketCyber is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the RocketCyber MCP server under?
RocketCyber declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.