Results / @autonomad1/computeback-mcp
@autonomad1/computeback-mcp
Sealmark's automated test of @autonomad1/computeback-mcp 1.1.4 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). None of the 32 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 8 checks, 3 passed, 1 partial, 2 inconclusive and 2 not applicable. 2 more checks are advisory, and advisory checks never change a grade: 2 not applicable. The run used Sealmark 1.0.1 with the standard settings.
Grade B
The server's grade is its lowest test-area grade. How grading works
None of the 32 tools could be called with default settings, so this grade covers the handshake and tool metadata only.
Grade by test area
Protocol checks
| Check | Verdict | What happened |
|---|---|---|
| protocol Valid MCP handshake and tool schemas | pass | handshake ok, 32 well-formed tool(s) Evidence for protocol: 1 line
|
| 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 | pass | 110 invalid call(s) rejected cleanly Evidence for robust-input: 1 line
|
| secret-echocritical No environment secret echoed in responses | pass | canary secrets absent from tools/list and 110 captured response(s), 0 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 |
Network checks
| Check | Verdict | What 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) |
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.
| Tool | Called by | Not exercised by |
|---|---|---|
| search_products | No check listed here called it with a valid call. | None |
| get_product | No check listed here called it with a valid call. | None |
| get_categories | No check listed here called it with a valid call. | |
| check_balance | No check listed here called it with a valid call. | None |
| create_order | No check listed here called it with a valid call. | None |
| get_orders | No check listed here called it with a valid call. | None |
| get_recommendations | No check listed here called it with a valid call. | None |
| buy_nomd | No check listed here called it with a valid call. | |
| get_audience_data | No check listed here called it with a valid call. | None |
| list_audiences | No check listed here called it with a valid call. | None |
| get_business_profile | No check listed here called it with a valid call. | None |
| get_product_info | No check listed here called it with a valid call. | None |
| fetch_url | No check listed here called it with a valid call. | None |
| dispatch_email_campaign | No check listed here called it with a valid call. | None |
| dispatch_voice_campaign | No check listed here called it with a valid call. | None |
| dispatch_sms_campaign | No check listed here called it with a valid call. | None |
| configure_landing_page | No check listed here called it with a valid call. | None |
| dispatch_landing_pages | No check listed here called it with a valid call. | None |
| send_landing_chat | No check listed here called it with a valid call. | None |
| list_workflow_templates | No check listed here called it with a valid call. | |
| start_workflow | No check listed here called it with a valid call. | None |
| accept_offer | No check listed here called it with a valid call. | None |
| decline_offer | No check listed here called it with a valid call. | None |
| start_offer | No check listed here called it with a valid call. | None |
| complete_offer | No check listed here called it with a valid call. | None |
| place_bid | No check listed here called it with a valid call. | |
| withdraw_bid | No check listed here called it with a valid call. | |
| list_my_inbox | No check listed here called it with a valid call. | |
| get_agent_profile | No check listed here called it with a valid call. | |
| edit_agent_profile | No check listed here called it with a valid call. | |
| get_settlement_status | No check listed here called it with a valid call. | |
| list_my_settlements | No check listed here called it with a valid call. |
What was not covered
- Database: Not applicable. The start command takes no database connection, so the database tests did not run. ({dsn}, {host} and the like are placeholders that Sealmark fills in with its own test database.)
- HTTP: Not applicable. The server is started over stdio; the http test area needs server.url
- Files: Not applicable. No tool is classified as taking a file path with medium confidence or higher
- Git: Not applicable. No tool is classified as taking a git repository path with medium confidence or higher
- Network: 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)
- SQLite: Not applicable. No tool takes a SQL string
- Effects: Not applicable. No tool declares annotations and none is an unannotated path or repository tool, so there is nothing to compare with what the sandbox observed
- Malformed-input probes cover the first 25 of 32 tools
- Tool "fetch_url" (url) was not probed by the net test area: 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)
- Tools that a server lists only for clients that declare roots, sampling or elicitation capabilities are not seen: the harness declares none
- Tool "search_products" is covered by the protocol checks only: argument "query" is not clearly SQL (nothing in the tool name, its description or the argument's description mentions sql, a database or a table); add it under tools: to include it
- Tool "get_product" is covered by the protocol checks only: free-text parameter "product_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_categories" is covered by the protocol checks only: the tool takes no parameters
- Tool "check_balance" is covered by the protocol checks only: free-text parameter "wallet_address": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "create_order" is covered by the protocol checks only: free-text parameter "product_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_orders" is covered by the protocol checks only: free-text parameter "wallet_address": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_recommendations" is covered by the protocol checks only: free-text parameter "wallet_address": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "buy_nomd" is covered by the protocol checks only: the tool takes no parameters
- Tool "get_audience_data" is covered by the protocol checks only: free-text parameter "business_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "list_audiences" is covered by the protocol checks only: free-text parameter "business_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_business_profile" is covered by the protocol checks only: free-text parameter "business_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_product_info" is covered by the protocol checks only: argument "query" is not clearly SQL (nothing in the tool name, its description or the argument's description mentions sql, a database or a table); add it under tools: to include it
- 19 more tool(s) are covered by the protocol checks only (see the classification)
- Tool "place_bid" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "withdraw_bid" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_my_inbox" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_agent_profile" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "edit_agent_profile" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_settlement_status" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_my_settlements" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_categories" was not covered by the core test area: needs probes: to be called (no arguments, and not declared read-only)
- Tool "buy_nomd" was not covered by the core test area: needs probes: to be called (no arguments, and not declared read-only)
- Tool "list_workflow_templates" was not covered by the core test area: needs probes: to be called (no arguments, and not declared read-only)
- SSRF: link-local and private-range addresses are never contacted; redirects from a public host to loopback and DNS rebinding are not tested (the harness contacts only its own loopback listener)
- The sandbox is a convention the harness follows, not a security boundary. A malicious server runs with your user's privileges, sees the real file system and network, and can ignore cwd, HOME and PATH. Run untrusted servers in a throwaway VM or container.
- Prompt injection carried in tool output (only tool metadata is scanned)
- Authentication and transport security
- Audit logging (not measured by these test areas; only the db test area has an advisory audit check)
Grade over time
Since the run on
Same as that run: the same grade in every test area, the same server version (1.1.4), the same Sealmark version (1.0.1).
- Bv1.1.4Sealmark 1.0.0
- Bv1.1.4Sealmark 1.0.1
- Bv1.1.4Sealmark 1.0.1
Package facts
- License
- MIT
- Latest release
- 1.1.4, published 2 Sep 2026 (the version graded on this page)
- Repository
- computeback/computeback-mcp
- Last push
- 12 May 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 1.1.4, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:
{
"mcpServers": {
"autonomad1-computeback-mcp": {
"command": "npx",
"args": [
"-y",
"@autonomad1/computeback-mcp@1.1.4"
]
}
}
}Or add it to Claude Code:
claude mcp add autonomad1-computeback-mcp -- npx -y "@autonomad1/computeback-mcp@1.1.4"
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 @autonomad1/computeback-mcp@1.1.4"
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 @autonomad1/computeback-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.