Sealmark
Automated re-test on 2026-11-20: not checked by hand, and not yet reviewed by the maintainers.

Results / mirastack-redfish-mcp

mirastack-redfish-mcp

version tested 0.1.2PyPItested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run25 tools

Sealmark's automated test of mirastack-redfish-mcp 0.1.2 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A and effects A). Tools reached with a valid call: 24 of 25. Of its 10 checks, 6 passed, 2 inconclusive and 2 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 1 passed and 2 not applicable. The run used Sealmark 1.0.1 with the standard settings.

A

Grade A

The server's grade is its lowest test-area grade. How grading works

Tools reached with a valid call: 24 of 25.

Grade by test area

A
Protocol4/4 points
A
Effects2/2 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 25 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server MIRASTACK Redfish MCP Server 0.1.2 answered; 25 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 25 tool definition(s), the server instructions and serverInfo, 3 prompt(s) and 7 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
46 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 46 invalid call(s) across 13 tool(s)
    Outcome all rejected cleanly and the server stayed responsive
    Decided from the MCP exchange (protocol)
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 47 captured response(s), 1 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
pass
the instructions name no tool the server lacks
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 54 of 54 probes were not explicitly refused (54 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-scheme-allowlistcritical
Only http(s) schemes accepted
inconclusive
no scheme had an observable effect, but 36 of 36 scored probes were not explicitly refused, so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-caps
Response size and time are capped
n/a
net-loopback-ssrf was inconclusive: the server never reached the loopback listener, so no loopback URL is known to be fetchable; response size and time caps were not measured
net-redirect
Redirects are re-validated
n/a
the server refused or never reached the loopback listener, so redirect handling could not be observed (a server that blocks loopback cannot be sent a redirect it would follow)

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
pass
list_endpoints declared read-only and changed nothing in the observed directories during a benign call (service_info, list_systems, get_system, list_chassis, get_chassis, list_managers, get_manager, get_health_summary, get_thermal, get_power, get_sensors, get_component_inventory, get_log_entries, get_firmware_inventory, get_boot_config, get_bios_attributes, list_tasks, get_task, list_accounts, list_virtual_media, redfish_get, redfish_walk, redfish_list_available_actions not judged: the control call failed)
openworld-honesty
Closed-world tools stay on the machine
pass
1 closed-world tool(s) called; nothing connected to the loopback listener (path and git tools cannot be pointed at it, so this confirms only that nothing connected out during the call)
undeclared-writes (advisory)
Unannotated tools leave the sandbox unchanged
n/a
every tool carries annotations, nothing to check

Each check id links to what it tests and how to fix a failure. The same text is in sealmark explain <id>.

Under a check, Evidence shows what it probed (sent or inspected) and what it observed in this run: up to 6 lines per check, each cut at 240 characters, for checks that are not security checks. The text is shortened, and paths and anything that looks like a secret or token are replaced. Run sealmark run --format json yourself for every line in full.

By tool

Which checks called each tool with a valid call in this run, and which did not exercise it. A check can leave a tool out for several reasons: a limit Sealmark sets, a tool left out by design, input the run could not fill in, or a call that returned an error. The CLI report gives the reason. A verdict belongs to the whole check, not to one tool: a failed check that called three tools does not say which one failed. Security checks are left out of this table.

ToolCalled byNot exercised by
list_endpointsNone
service_infoNo check listed here called it with a valid call.
list_systemsNo check listed here called it with a valid call.None
get_systemNo check listed here called it with a valid call.
list_chassisNo check listed here called it with a valid call.None
get_chassisNo check listed here called it with a valid call.
list_managersNo check listed here called it with a valid call.None
get_managerNo check listed here called it with a valid call.
get_health_summaryNo check listed here called it with a valid call.
get_thermalNo check listed here called it with a valid call.
get_powerNo check listed here called it with a valid call.
get_sensorsNo check listed here called it with a valid call.None
get_component_inventoryNo check listed here called it with a valid call.None
get_log_entriesNo check listed here called it with a valid call.None
get_firmware_inventoryNo check listed here called it with a valid call.None
get_boot_configNo check listed here called it with a valid call.
get_bios_attributesNo check listed here called it with a valid call.
list_tasksNo check listed here called it with a valid call.None
get_taskNo check listed here called it with a valid call.
list_accountsNo check listed here called it with a valid call.None
list_virtual_mediaNo check listed here called it with a valid call.
redfish_getNo check listed here called it with a valid call.None
redfish_walkNo check listed here called it with a valid call.None
redfish_describe_schemaNo check listed here called it with a valid call.None
redfish_list_available_actionsNo check listed here called it with a valid call.None

What was not covered

Grade over time

Since the run on

Same as that run: the same grade in every test area, the same server version (0.1.2), the same Sealmark version (1.0.1).

  1. Av0.1.2Sealmark 1.0.0
  2. Av0.1.2Sealmark 1.0.1
  3. Av0.1.2Sealmark 1.0.1

Package facts

License
Apache-2.0
Latest release
0.1.2, published 12 Aug 2026 (the version graded on this page)
Repository
mirastacklabs-ai/mirastack-redfish-mcp
Last push
12 Aug 2026
Open issues and pull requests
3

From PyPI and GitHub, checked 22 Nov 2026. Plain facts about the package; they play no part in the grade.

Add it to an MCP client

This starts version 0.1.2, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "mirastack-redfish-mcp": {
      "command": "uvx",
      "args": [
        "mirastack-redfish-mcp==0.1.2"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add mirastack-redfish-mcp -- uvx mirastack-redfish-mcp==0.1.2

The test run started the server with no API keys or other secrets, and with a cleaned environment. If the server needs some, its own documentation says how to pass them.

Run it yourself

This repeats the run with the same Sealmark version and the standard settings, starting the server the same way:

npx -y sealmark@1.0.1 run --start "uvx mirastack-redfish-mcp==0.1.2"

To confirm your run used the standard settings, add --format json --out report.json to the command. In the report, config.standard should be true and config.hash should start with sha256:d13e7893a0ac, as they did in this run. If either differs, so did the settings, and the verdicts may too (STANDARD and CUSTOM runs).

To keep the setup, put the start command in sealmark.yaml as the server.

Grade alerts

One email when the grade of mirastack-redfish-mcp changes after a re-test. Nothing else, and every email has a link to stop them.

Or follow it in a feed reader: the Atom feed lists each move of the overall grade that came with a different version of this server, tested with the same Sealmark version as the graded run before.

Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.

The issue we opened No reply yet

Sealmark opened a public issue on this project's repository on 14 Nov 2026 to share this grade. No reply yet. A reply is optional.

Read the issue on GitHub. State as of the last re-test run.

Is this wrong?

Reply on the GitHub issue or email disclosure@sealmark.dev and we will recheck it. Maintainers can ask for their server to be removed.

If we were wrong, we correct the page and add your reply. Security findings go to the maintainer privately first; see the disclosure policy.