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

Results / @satohub/mcp

@satohub/mcp

version tested 1.0.3npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run48 tools

Sealmark's automated test of @satohub/mcp 1.0.3 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B and effects A). Only 21 of 48 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 10 checks, 3 passed, 2 partial, 2 inconclusive and 3 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 1 failed and 2 not applicable. The run used Sealmark 1.0.1 with the standard settings.

B

Grade B

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

Only 21 of 48 tools could be called with default settings, so the deeper test areas cover only those tools.

Grade by test area

B
Protocol3/4 pointsincludes a weak signal, not a security finding
A
Effects1/1 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 48 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server onchain-agent-mcp-server 0.1.0 answered; 48 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
1 weak indicator(s) worth reading, none conclusive
Weak signal, not a security finding. Some wording in the tool text is worth a read, but none of it is conclusive. A partial counts as half a point.
robust-input
Survives malformed tool input
partial
0 internals leak(s), 60 invalid call(s) accepted
Evidence for robust-input: first 6 of 60 lines
  1. Probe onchain_agent_search_resources: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_search_resources
  2. Probe onchain_agent_get_resource: required arguments missing
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_get_resource
  3. Probe onchain_agent_get_resource: every typed argument has the wrong type
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_get_resource
  4. Probe onchain_agent_get_resource: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_get_resource
  5. Probe onchain_agent_get_resource: wrong types plus an unexpected extra argument
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_get_resource
  6. Probe onchain_agent_get_resource: every string argument is an object
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool onchain_agent_get_resource
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 110 captured response(s), 60 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 7 tool(s) the server does not offer (preflight_summary, save_stack_url, trust_spec, next_since, verification_status)
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 9 of 9 probes were not explicitly refused (0 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; the tool may be a lookup rather than a fetcher, settle it with tools.overrides)
net-scheme-allowlistcritical
Only http(s) schemes accepted
inconclusive
no scheme had an observable effect, but 6 of 6 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
onchain_agent_search_resources, onchain_agent_recent_changes, onchain_agent_list_categories, onchain_agent_list_chains, onchain_agent_get_news, onchain_agent_get_metrics, onchain_agent_search_agents, onchain_agent_list_wiki_pages, onchain_agent_get_changes, onchain_agent_get_agent_economy, onchain_agent_search_skills, onchain_agent_get_trend, onchain_agent_get_score_methodology, onchain_agent_get_data_freshness, onchain_agent_search_listings, onchain_agent_preflight, onchain_agent_check_install, onchain_agent_route_agent, onchain_agent_resolve_token, onchain_agent_get_contract_facts, onchain_agent_get_x402_facilitators declared read-only and changed nothing in the observed directories during a benign call
openworld-honesty
Closed-world tools stay on the machine
n/a
no tool declares openWorldHint: false that could be given a harness-owned control argument
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
onchain_agent_search_resourcesNo check listed here called it with a valid call.None
onchain_agent_get_resourceNo check listed here called it with a valid call.None
searchNo check listed here called it with a valid call.None
fetchNo check listed here called it with a valid call.None
onchain_agent_get_deploy_specNo check listed here called it with a valid call.None
onchain_agent_recent_changesNo check listed here called it with a valid call.None
onchain_agent_list_categoriesNo check listed here called it with a valid call.None
onchain_agent_list_chainsNo check listed here called it with a valid call.None
onchain_agent_get_newsNo check listed here called it with a valid call.None
onchain_agent_get_metricsNo check listed here called it with a valid call.None
onchain_agent_get_wiki_pageNo check listed here called it with a valid call.None
onchain_agent_search_agentsNo check listed here called it with a valid call.None
onchain_agent_get_agent_passportNo check listed here called it with a valid call.None
onchain_agent_recommend_stackNo check listed here called it with a valid call.None
onchain_agent_list_wiki_pagesNo check listed here called it with a valid call.None
onchain_agent_get_changesNo check listed here called it with a valid call.None
onchain_agent_get_agent_economyNo check listed here called it with a valid call.None
onchain_agent_search_skillsNo check listed here called it with a valid call.None
onchain_agent_get_trendNo check listed here called it with a valid call.None
onchain_agent_compare_listingsNo check listed here called it with a valid call.None
onchain_agent_explain_numberNo check listed here called it with a valid call.None
onchain_agent_get_score_methodologyNo check listed here called it with a valid call.None
onchain_agent_get_data_freshnessNo check listed here called it with a valid call.None
onchain_agent_search_listingsNo check listed here called it with a valid call.None
onchain_agent_inspect_listingNo check listed here called it with a valid call.None
onchain_agent_get_listing_historyNo check listed here called it with a valid call.
onchain_agent_preflightNo check listed here called it with a valid call.
onchain_agent_check_installNo check listed here called it with a valid call.
onchain_agent_scan_recipientNo check listed here called it with a valid call.
onchain_agent_route_swapNo check listed here called it with a valid call.
onchain_agent_route_agentNo check listed here called it with a valid call.
onchain_agent_route_launchNo check listed here called it with a valid call.
onchain_agent_build_planNo check listed here called it with a valid call.
onchain_agent_route_lpNo check listed here called it with a valid call.
onchain_agent_create_agentNo check listed here called it with a valid call.
onchain_agent_scaffold_planNo check listed here called it with a valid call.
onchain_agent_watchNo check listed here called it with a valid call.
onchain_agent_submit_projectNo check listed here called it with a valid call.
onchain_agent_register_agentNo check listed here called it with a valid call.
onchain_agent_join_passportNo check listed here called it with a valid call.
onchain_agent_passport_actionNo check listed here called it with a valid call.
onchain_agent_swapNo check listed here called it with a valid call.
onchain_agent_resolve_tokenNo check listed here called it with a valid call.
onchain_agent_find_x402_serviceNo check listed here called it with a valid call.
onchain_agent_get_sdk_lineageNo check listed here called it with a valid call.
onchain_agent_get_contract_factsNo check listed here called it with a valid call.
onchain_agent_get_chain_cardNo check listed here called it with a valid call.
onchain_agent_get_x402_facilitatorsNo check listed here called it with a valid call.

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 (1.0.3), the same Sealmark version (1.0.1).

  1. Bv1.0.3Sealmark 1.0.0
  2. Bv1.0.3Sealmark 1.0.1
  3. Bv1.0.3Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.0.3, published 19 Oct 2026 (the version graded on this page)
Repository
satohubai/mcp
Last push
7 Oct 2026
Open issues and pull requests
1

From npm 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 1.0.3, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "satohub-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@satohub/mcp@1.0.3"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add satohub-mcp -- npx -y "@satohub/mcp@1.0.3"

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 "npx -y @satohub/mcp@1.0.3"

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 @satohub/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 20 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.