Sealmark
Automated re-test on 2026-11-21: not checked by hand, and not yet reviewed by the maintainers.

Results / @vaaya/mcp

@vaaya/mcp

version tested 0.8.3npmtested 2026-11-21Sealmark 1.0.1methodology 0.3-draftSTANDARD run16 tools

Sealmark's automated test of @vaaya/mcp 0.8.3 on 2026-11-21 gave it grade C, its lowest test-area grade (protocol C). None of the 16 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 2 passed, 1 failed, 1 partial, 4 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.

C

Grade C

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

None of the 16 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

C
Protocol2.5/4 pointsincludes a weak signal, not a security finding

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 16 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server vaaya 1.0.0 answered; 16 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
2 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
fail
server hung on malformed input
Evidence for robust-input: 3 lines
  1. Probe stocks: required arguments missing
    Outcome no answer within 10s
    Decided from the MCP exchange (protocol) · tool stocks
  2. Probe jobs: required arguments missing
    Outcome no answer within 10s
    Decided from the MCP exchange (protocol) · tool jobs
  3. Probe vaaya_test_connection: no arguments (declared read-only)
    Outcome no answer within 10s
    Decided from the MCP exchange (protocol) · tool vaaya_test_connection
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 3 captured response(s), 0 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 9 of 9 probes were not explicitly refused (9 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 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
inconclusive
every control call failed, so the read-only annotation could not be checked
openworld-honesty
Closed-world tools stay on the machine
inconclusive
every control call failed, so the closed-world annotation could not be checked
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
stocksNo check listed here called it with a valid call.None
jobsNo check listed here called it with a valid call.None
vaaya_test_connectionNo check listed here called it with a valid call.None
vaaya_onboardNo check listed here called it with a valid call.None
vaaya_accountNo check listed here called it with a valid call.None
vaaya_logoutNo check listed here called it with a valid call.None
docsNo check listed here called it with a valid call.None
consultNo check listed here called it with a valid call.None
useNo check listed here called it with a valid call.None
resultNo check listed here called it with a valid call.None
buyNo check listed here called it with a valid call.None
sessionNo check listed here called it with a valid call.None
closeNo check listed here called it with a valid call.None
llmNo check listed here called it with a valid call.None
logoutNo check listed here called it with a valid call.None
reauthorizeNo check listed here called it with a valid call.None

What was not covered

Grade over time

Since the run on

  • Server version changed from 0.8.1 to 0.8.3.

Unchanged: the same grade in every test area, the same tools with the same input schemas, the same Sealmark version (1.0.1).

  1. Cv0.7.0Sealmark 1.0.0
  2. Cv0.7.0Sealmark 1.0.1
  3. Cv0.8.1Sealmark 1.0.1
  4. Cv0.8.1Sealmark 1.0.1
  5. Cv0.8.3Sealmark 1.0.1

Package facts

License
MIT
Latest release
0.8.3, published 21 Nov 2026 (the version graded on this page)
Repository
vaaya-ai/vaaya-mcp
Last push
17 Nov 2026
Open issues and pull requests
9

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

{
  "mcpServers": {
    "vaaya-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@vaaya/mcp@0.8.3"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add vaaya-mcp -- npx -y "@vaaya/mcp@0.8.3"

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 @vaaya/mcp@0.8.3"

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 @vaaya/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.

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.