Sealmark
Automated re-test on 2026-11-22: not checked by hand, and not yet reviewed by the maintainers.

Results / dchub-mcp-server

dchub-mcp-server

version tested 2.12.61npmtested 2026-11-22Sealmark 1.0.1methodology 0.3-draftSTANDARD run98 tools

Sealmark's automated test of dchub-mcp-server 2.12.61 on 2026-11-22 gave it grade A, its lowest test-area grade (protocol A and effects A). Tools reached with a valid call: 64 of 98. 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 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

Tools reached with a valid call: 64 of 98.

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, 98 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server DC Hub 2.12.61 answered; 98 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 98 tool definition(s), the server instructions and serverInfo, 15 prompt(s) and 81 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
102 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 102 invalid call(s) across 23 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 104 captured response(s), 2 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 6 tool(s) the server does not offer (cite_as, next_ask, last_session, human_url, human_message)
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 18 of 18 probes were not explicitly refused (4 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 12 of 12 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
search_facilities, get_market_intel, get_gas_index, get_grid_scoreboard, get_intelligence_index, list_transactions, get_news, semantic_search, search_intelligence, get_pipeline, get_power_pipeline, get_infra_projects, get_global_power, get_interconnection_queue, get_refined_queue, get_hosting_capacity, discover_tools, get_grid_data, get_changes, compare_sites, get_fiber_intel, get_subsea_cables, get_peering_intel, get_metro_fiber, get_energy_prices, get_renewable_energy, get_tax_incentives, get_grid_intelligence, get_gas_intelligence declared read-only and changed nothing in the observed directories during a benign call (get_facility, analyze_parcel, rank_sites, get_facility_risk_delta, list_saved_sites, export_dataset, find_sites, analyze_site, get_composite_site_score, get_disaster_risk, get_climate_intel, generate_site_analysis, get_infrastructure, get_fiber_readiness, get_water_risk, get_agent_registry, get_backup_status, summarize_for_citation, why_dchub, dchub_services, get_dchub_recommendation, rank_markets, ai_capacity_index, hyperscaler_deals, site_selection_canvas, grid_transition_radar, deal_autopsy, get_permitting_intel, get_air_permit_context, simulate_scenario, list_standing_intents, cluster_sites_by_latency, source_capacity, read_inbox not judged: the control call failed)
openworld-honesty
Closed-world tools stay on the machine
pass
52 closed-world tool(s) called; none reached out beyond what was asked
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
execute_planNo check listed here called it with a valid call.None
get_api_keyNo 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
search_facilitiesNo check listed here called it with a valid call.None
get_facilityNo check listed here called it with a valid call.None
get_market_intelNo check listed here called it with a valid call.None
get_market_dcpi_rankNo check listed here called it with a valid call.None
predict_market_trajectoryNo check listed here called it with a valid call.None
get_gas_indexNo check listed here called it with a valid call.None
get_gas_economicsNo check listed here called it with a valid call.None
get_grid_scoreboardNone
compare_isosNo check listed here called it with a valid call.None
get_intelligence_indexNone
list_transactionsNo check listed here called it with a valid call.None
get_newsNo check listed here called it with a valid call.None
semantic_searchNo check listed here called it with a valid call.None
search_intelligenceNo check listed here called it with a valid call.None
get_market_contextNo check listed here called it with a valid call.None
get_iso_contextNo check listed here called it with a valid call.None
get_pipelineNo check listed here called it with a valid call.None
get_power_pipelineNo check listed here called it with a valid call.None
get_infra_projectsNo check listed here called it with a valid call.None
get_power_availability_timelineNo check listed here called it with a valid call.None
get_global_powerNo check listed here called it with a valid call.None
get_interconnection_queueNo check listed here called it with a valid call.
get_refined_queueNo check listed here called it with a valid call.
get_retirement_headroomNo check listed here called it with a valid call.
get_hosting_capacityNo check listed here called it with a valid call.
analyze_parcelNo check listed here called it with a valid call.
rank_sitesNo check listed here called it with a valid call.
discover_toolsNo check listed here called it with a valid call.
plan_queryNo check listed here called it with a valid call.
save_to_shortlistNo check listed here called it with a valid call.
get_shortlistNo check listed here called it with a valid call.
set_shortlist_alertNo check listed here called it with a valid call.
suggest_reallocationNo check listed here called it with a valid call.
get_grid_dataNo check listed here called it with a valid call.
get_changesNo check listed here called it with a valid call.
get_facility_risk_deltaNo check listed here called it with a valid call.
save_siteNo check listed here called it with a valid call.
list_saved_sitesNo check listed here called it with a valid call.
set_market_alertNo check listed here called it with a valid call.
subscribe_digestNo check listed here called it with a valid call.
set_site_alertNo check listed here called it with a valid call.
export_datasetNo check listed here called it with a valid call.
find_sitesNo check listed here called it with a valid call.
analyze_siteNo check listed here called it with a valid call.
get_composite_site_scoreNo check listed here called it with a valid call.
get_disaster_riskNo check listed here called it with a valid call.
get_climate_intelNo check listed here called it with a valid call.
generate_site_analysisNo check listed here called it with a valid call.
compare_sitesNo check listed here called it with a valid call.
get_infrastructureNo check listed here called it with a valid call.
get_fiber_intelNo check listed here called it with a valid call.
get_fiber_readinessNo check listed here called it with a valid call.
get_subsea_cablesNo check listed here called it with a valid call.
get_peering_intelNo check listed here called it with a valid call.
get_metro_fiberNo check listed here called it with a valid call.
get_energy_pricesNo check listed here called it with a valid call.
get_renewable_energyNo check listed here called it with a valid call.
get_tax_incentivesNo check listed here called it with a valid call.
get_water_riskNo check listed here called it with a valid call.
get_grid_intelligenceNo check listed here called it with a valid call.
get_gas_intelligenceNo check listed here called it with a valid call.
get_agent_registryNo check listed here called it with a valid call.
get_backup_statusNo check listed here called it with a valid call.
summarize_for_citationNo check listed here called it with a valid call.
why_dchubNo check listed here called it with a valid call.
dchub_servicesNo check listed here called it with a valid call.
get_dchub_recommendationNo check listed here called it with a valid call.
rank_marketsNo check listed here called it with a valid call.
find_alternativesNo check listed here called it with a valid call.
score_facilityNo check listed here called it with a valid call.
ai_capacity_indexNo check listed here called it with a valid call.
hyperscaler_dealsNo check listed here called it with a valid call.
site_selection_canvasNo check listed here called it with a valid call.
grid_transition_radarNo check listed here called it with a valid call.
deal_autopsyNo check listed here called it with a valid call.
get_permitting_intelNo check listed here called it with a valid call.
get_air_permit_contextNo check listed here called it with a valid call.
simulate_scenarioNo check listed here called it with a valid call.
research_taskNo check listed here called it with a valid call.
list_standing_intentsNo check listed here called it with a valid call.
register_standing_intentNo check listed here called it with a valid call.
delete_standing_intentNo check listed here called it with a valid call.
plan_fiber_leadinNo check listed here called it with a valid call.
cluster_sites_by_latencyNo check listed here called it with a valid call.
bind_emailNo check listed here called it with a valid call.
recover_my_keyNo check listed here called it with a valid call.
source_capacityNo check listed here called it with a valid call.
request_capacity_introNo check listed here called it with a valid call.
accept_capacity_termsNo check listed here called it with a valid call.
accept_capacity_introNo check listed here called it with a valid call.
unlock_more_dataNo check listed here called it with a valid call.
read_inboxNo check listed here called it with a valid call.
report_findingNo check listed here called it with a valid call.
request_enhancementNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

  • Server version changed from 2.12.60 to 2.12.61.
  • Input schema changed (any part of it, parameter wording included): get_facility, get_grid_intelligence.

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

  1. Av2.12.46Sealmark 1.0.0
  2. Av2.12.47Sealmark 1.0.0
  3. Av2.12.48Sealmark 1.0.0
  4. Av2.12.54Sealmark 1.0.1
  5. Av2.12.58Sealmark 1.0.1
  6. Av2.12.59Sealmark 1.0.1
  7. Av2.12.59Sealmark 1.0.1
  8. Av2.12.60Sealmark 1.0.1
  9. Av2.12.61Sealmark 1.0.1

Package facts

License
MIT
Latest release
2.12.60, published 21 Nov 2026. This page graded 2.12.61.
Repository
azmartone67/dchub-mcp-server
Last push
22 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 2.12.61, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "dchub-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "dchub-mcp-server@2.12.61"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add dchub-mcp-server -- npx -y "dchub-mcp-server@2.12.61"

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 dchub-mcp-server@2.12.61"

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 dchub-mcp-server 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.