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

Results / firecrawl/firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

version tested 3.36.1GitHubtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run28 tools

Sealmark's automated test of firecrawl/firecrawl-mcp-server 3.36.1 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 28 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 4 passed, 4 inconclusive and 2 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 1 passed, 1 failed and 1 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

None of the 28 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

A
Protocol4/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 28 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server firecrawl-fastmcp 3.41.0 answered; 28 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 28 tool definition(s), the server instructions and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
123 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 123 invalid call(s) across 25 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 123 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
fail
0 of 9 refusal(s) say what to do instead or why retrying will not help (0 %)

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 27 of 36 probes were not explicitly refused (27 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 24 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
firecrawl_scrapeNo check listed here called it with a valid call.None
firecrawl_mapNo check listed here called it with a valid call.None
firecrawl_searchNo check listed here called it with a valid call.None
alexandria_library_searchNo check listed here called it with a valid call.None
alexandria_library_readNo check listed here called it with a valid call.None
firecrawl_crawlNo check listed here called it with a valid call.None
firecrawl_check_crawl_statusNo check listed here called it with a valid call.None
firecrawl_agentNo check listed here called it with a valid call.None
firecrawl_agent_statusNo check listed here called it with a valid call.None
firecrawl_interactNo check listed here called it with a valid call.None
firecrawl_interact_stopNo check listed here called it with a valid call.None
firecrawl_parseNo check listed here called it with a valid call.None
firecrawl_monitor_createNo check listed here called it with a valid call.None
firecrawl_monitor_listNo check listed here called it with a valid call.None
firecrawl_monitor_getNo check listed here called it with a valid call.None
firecrawl_monitor_updateNo check listed here called it with a valid call.None
firecrawl_monitor_deleteNo check listed here called it with a valid call.None
firecrawl_monitor_runNo check listed here called it with a valid call.None
firecrawl_monitor_checksNo check listed here called it with a valid call.None
firecrawl_monitor_checkNo check listed here called it with a valid call.None
firecrawl_research_search_papersNo check listed here called it with a valid call.None
firecrawl_research_inspect_paperNo check listed here called it with a valid call.None
firecrawl_research_related_papersNo check listed here called it with a valid call.None
firecrawl_research_read_paperNo check listed here called it with a valid call.None
firecrawl_research_lookup_proteinNo check listed here called it with a valid call.None
firecrawl_developer_searchNo check listed here called it with a valid call.
firecrawl_gov_searchNo check listed here called it with a valid call.
firecrawl_credit_usageNo 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 (3.36.1), the same Sealmark version (1.0.1).

  1. Av3.36.1Sealmark 1.0.0
  2. Av3.36.1Sealmark 1.0.1
  3. Av3.36.1Sealmark 1.0.1

Project facts

License
MIT
Latest release
3.36.1, published 3 Nov 2026
Repository
firecrawl/firecrawl-mcp-server
Last push
21 Nov 2026
Open issues and pull requests
199

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:firecrawl/firecrawl-mcp-server"

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 firecrawl/firecrawl-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.