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

Results / antvis/mcp-server-chart

antvis/mcp-server-chart

version tested 0.9.10GitHubtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run27 tools

Sealmark's automated test of antvis/mcp-server-chart 0.9.10 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). None of the 27 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 3 passed, 1 partial and 2 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 3 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

None of the 27 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

B
Protocol3.5/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 27 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server mcp-server-chart 0.8.x answered; 27 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 27 tool definition(s) and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
121 internals leak(s), 17 invalid call(s) accepted, 1 reply(ies) show the invalid argument was used downstream, 136 unhandled runtime error(s)
Evidence for robust-input: first 6 of 275 lines
  1. Probe generate_area_chart: required arguments missing
    Outcome error response exposes a stack trace or internal file paths
    Decided from what the server returned (response) · tool generate_area_chart
  2. Probe generate_area_chart: required arguments missing
    Outcome an unhandled runtime error, not a validation decision: Failed to generate chart: Cannot read properties of null (reading 'map') TypeError: Cannot read properties of null (reading 'map') at <anonymous> (/var/task/cod
    Decided from what the server returned (response) · tool generate_area_chart
  3. Probe generate_area_chart: every typed argument has the wrong type
    Outcome error response exposes a stack trace or internal file paths
    Decided from what the server returned (response) · tool generate_area_chart
  4. Probe generate_area_chart: every typed argument has the wrong type
    Outcome an unhandled runtime error, not a validation decision: Failed to generate chart: Cannot read properties of null (reading '0') TypeError: Cannot read properties of null (reading '0') at R (/var/task/code/ApiControlle
    Decided from what the server returned (response) · tool generate_area_chart
  5. Probe generate_area_chart: every typed argument is null
    Outcome error response exposes a stack trace or internal file paths
    Decided from what the server returned (response) · tool generate_area_chart
  6. Probe generate_area_chart: every typed argument is null
    Outcome an unhandled runtime error, not a validation decision: Failed to generate chart: Cannot read properties of null (reading 'texture') evalmachine.<anonymous>:16 const _texture = texture || style.texture || 'default';
    Decided from what the server returned (response) · tool generate_area_chart
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 157 captured response(s), 17 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
n/a
the server sent no instructions
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
n/a
no tool declared readOnlyHint: true could be given a harness-owned control argument
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
generate_area_chartNo check listed here called it with a valid call.None
generate_bar_chartNo check listed here called it with a valid call.None
generate_boxplot_chartNo check listed here called it with a valid call.None
generate_column_chartNo check listed here called it with a valid call.None
generate_district_mapNo check listed here called it with a valid call.None
generate_dual_axes_chartNo check listed here called it with a valid call.None
generate_fishbone_diagramNo check listed here called it with a valid call.None
generate_flow_diagramNo check listed here called it with a valid call.None
generate_funnel_chartNo check listed here called it with a valid call.None
generate_histogram_chartNo check listed here called it with a valid call.None
generate_line_chartNo check listed here called it with a valid call.None
generate_liquid_chartNo check listed here called it with a valid call.None
generate_mind_mapNo check listed here called it with a valid call.None
generate_network_graphNo check listed here called it with a valid call.None
generate_organization_chartNo check listed here called it with a valid call.None
generate_path_mapNo check listed here called it with a valid call.None
generate_pie_chartNo check listed here called it with a valid call.None
generate_pin_mapNo check listed here called it with a valid call.None
generate_radar_chartNo check listed here called it with a valid call.None
generate_sankey_chartNo check listed here called it with a valid call.None
generate_scatter_chartNo check listed here called it with a valid call.None
generate_treemap_chartNo check listed here called it with a valid call.None
generate_venn_chartNo check listed here called it with a valid call.None
generate_violin_chartNo check listed here called it with a valid call.None
generate_waterfall_chartNo check listed here called it with a valid call.None
generate_word_cloud_chartNo check listed here called it with a valid call.
generate_spreadsheetNo 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 (0.9.10), the same Sealmark version (1.0.1).

  1. Bv0.9.10Sealmark 1.0.0
  2. Bv0.9.10Sealmark 1.0.1
  3. Bv0.9.10Sealmark 1.0.1

Project facts

License
MIT
Latest release
0.9.10, published 25 Feb 2026
Repository
antvis/mcp-server-chart
Last push
27 Aug 2026
Open issues and pull requests
7

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

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 github:antvis/mcp-server-chart"

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 antvis/mcp-server-chart 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.