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

Results / gage-mcp

gage-mcp

version tested 0.9.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run59 tools

Sealmark's automated test of gage-mcp 0.9.0 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A and effects A). Only 5 of 59 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 6 checks, 5 passed and 1 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.

A

Grade A

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

Only 5 of 59 tools could be called with default settings, so the deeper test areas cover only those tools.

Grade by test area

A
Protocol4/4 points
A
Effects1/1 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 59 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server gage 0.9.0 answered; 59 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 59 tool definition(s), the server instructions and serverInfo, 1 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
105 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 105 invalid call(s) across 21 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 109 captured response(s), 4 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 8 tool(s) the server does not offer (lp_borrow, lp_roll, lp_unwrap, lp_vault_add_pool, lp_vault_remove_pool)
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
pass
gage_capabilities, gage_assets, gage_earn_vaults, gage_lp_vaults, gage_pool_vaults 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
gage_capabilitiesNone
gage_assetsNone
gage_borrow_quoteNo check listed here called it with a valid call.None
gage_leverage_quoteNo check listed here called it with a valid call.None
gage_loanNo check listed here called it with a valid call.None
gage_portfolioNo check listed here called it with a valid call.None
gage_earn_vaultsNone
gage_vault_free_cashNo check listed here called it with a valid call.None
gage_put_quoteNo check listed here called it with a valid call.None
gage_lp_positionsNo check listed here called it with a valid call.None
gage_lp_quoteNo check listed here called it with a valid call.None
gage_lp_loansNo check listed here called it with a valid call.None
gage_lp_vaultsNone
gage_park_positionsNo check listed here called it with a valid call.None
gage_prepare_borrowNo check listed here called it with a valid call.None
gage_prepare_leverageNo check listed here called it with a valid call.None
gage_prepare_cancelNo check listed here called it with a valid call.None
gage_prepare_reclaimNo check listed here called it with a valid call.None
gage_prepare_cash_outNo check listed here called it with a valid call.None
gage_prepare_rollNo check listed here called it with a valid call.None
gage_prepare_auto_rollNo check listed here called it with a valid call.None
gage_prepare_cancel_auto_rollNo check listed here called it with a valid call.None
gage_prepare_earn_depositNo check listed here called it with a valid call.None
gage_prepare_earn_redeemNo check listed here called it with a valid call.None
gage_prepare_collectNo check listed here called it with a valid call.None
gage_prepare_feedbackNo check listed here called it with a valid call.
gage_prepare_put_openNo check listed here called it with a valid call.
gage_prepare_put_closeNo check listed here called it with a valid call.
gage_prepare_put_rollNo check listed here called it with a valid call.
gage_prepare_put_auto_rollNo check listed here called it with a valid call.
gage_prepare_put_cancel_auto_rollNo check listed here called it with a valid call.
gage_prepare_lp_borrowNo check listed here called it with a valid call.
gage_prepare_lp_repayNo check listed here called it with a valid call.
gage_prepare_lp_return_positionNo check listed here called it with a valid call.
gage_prepare_lp_collectNo check listed here called it with a valid call.
gage_prepare_lp_withdrawNo check listed here called it with a valid call.
gage_prepare_lp_depositNo check listed here called it with a valid call.
gage_prepare_lp_redeemNo check listed here called it with a valid call.
gage_prepare_lp_claim_bonusNo check listed here called it with a valid call.
gage_prepare_lp_claim_rewardsNo check listed here called it with a valid call.
gage_prepare_lp_rollNo check listed here called it with a valid call.
gage_prepare_lp_wrapNo check listed here called it with a valid call.
gage_prepare_lp_unwrapNo check listed here called it with a valid call.
gage_prepare_lp_create_vaultNo check listed here called it with a valid call.
gage_prepare_lp_vault_add_poolNo check listed here called it with a valid call.
gage_prepare_lp_vault_remove_poolNo check listed here called it with a valid call.
gage_prepare_parkNo check listed here called it with a valid call.
gage_prepare_unparkNo check listed here called it with a valid call.
gage_prepare_rehypo_exit_nowNo check listed here called it with a valid call.
gage_prepare_earn_exit_nowNo check listed here called it with a valid call.
gage_prepare_earn_exit_listNo check listed here called it with a valid call.
gage_prepare_earn_exit_cancelNo check listed here called it with a valid call.
gage_prepare_earn_exit_collectNo check listed here called it with a valid call.
gage_prepare_create_vaultNo check listed here called it with a valid call.
gage_prepare_vault_manageNo check listed here called it with a valid call.
gage_pool_vaultsNo check listed here called it with a valid call.
gage_create_pool_vaultsNo check listed here called it with a valid call.
gage_create_partner_vaultNo check listed here called it with a valid call.
gage_vault_on_chainNo 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 (0.9.0), the same Sealmark version (1.0.1).

  1. Av0.9.0Sealmark 1.0.0
  2. Av0.9.0Sealmark 1.0.1
  3. Av0.9.0Sealmark 1.0.1

Badge for the README

The badge shows this automated result for version 0.9.0. It is a link to this page, not a certificate, and it changes when the next re-test does.

Sealmark badge for gage-mcp
The flat badge, one letter per graded test area.
[![Sealmark](https://sealmark.dev/badge/gage-mcp.svg)](https://sealmark.dev/results/gage-mcp/)

Files: badge SVG, card SVG, shields endpoint JSON.

Package facts

License
MIT
Latest release
0.9.0, published 7 Nov 2026 (the version graded on this page)
Repository
DebenLabs/gage-sdk
Last push
7 Nov 2026
Open issues and pull requests
0

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

{
  "mcpServers": {
    "gage-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "gage-mcp@0.9.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add gage-mcp -- npx -y "gage-mcp@0.9.0"

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 gage-mcp@0.9.0"

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 gage-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.