Unreleased: not public yet. Maintainers have not reviewed this result.
Results / @cyanheads/filesystem-mcp-server
@cyanheads/filesystem-mcp-server
A
Protocol4/4 points
F
Files1.5/4 pointscritical: fs-link-escape
Coverage: covered (5 of 10 tools reached with a valid call).
Protocol checks
| Check | Verdict | What happened |
|---|---|---|
| protocol Valid MCP handshake and tool schemas | pass | handshake ok, 10 well-formed tool(s) |
| tool-poisoningcritical No tool-poisoning indicators in tool metadata | pass | scanned 10 tool definition(s), including parameter text: nothing suspicious (1 listing(s) failed and were not scanned) |
| robust-input Survives malformed tool input | pass | 40 invalid call(s) rejected cleanly |
| secret-echocritical No environment secret echoed in responses | pass | canary secrets absent from tools/list and 40 captured response(s) |
Files checks
| Check | Verdict | What happened |
|---|---|---|
| fs-read-escapecritical Reads stay inside the allowed root | partial | 15 path variants aimed outside the root were refused or returned nothing, on read_file, list_files, but set_filesystem_default (the control call on {sandbox}/ok.txt failed (Default path must be absolute.)) |
| fs-write-escapecritical Writes stay inside the allowed root | pass | 12 write attempts aimed outside the root left the canary directory and the sibling root unchanged |
| fs-link-escapecritical Links cannot lead out of the allowed root | fail | a link inside the root led to a file outside it: read_file via link-dir; read_file via link-file; list_files via link-dir; write_file write via link-dir-write |
| fs-size-cap Large file reads are capped | fail | read_file: the connection dropped or the call timed out (the response was too large for the transport) |
What was not covered
- Database: Not applicable. Server config has no {dsn}/{host}/... Placeholder, so the harness cannot start the server once per role
- HTTP: Not applicable. The server is started over stdio; the http pack needs server.url
- Git: Not applicable. No tool is classified as taking a git repository path with medium confidence or higher
- Network: Not applicable. No tool is classified as taking a URL with medium confidence or higher
- SQLite: Not applicable. No tool takes a SQL string
- Effects: Not applicable. No tool declares annotations, so there is nothing to compare with what the sandbox observed
- Tool "delete_file" was not covered by the fs pack: a delete tool is never called by the standard probes; add a custom probe to test it
- Tool "delete_directory" was not covered by the fs pack: a delete tool is never called by the standard probes; add a custom probe to test it
- Tool "set_filesystem_default" was not covered by the fs pack: the control call on {sandbox}/ok.txt failed (Default path must be absolute.)
- Tools that a server lists only for clients that declare roots, sampling or elicitation capabilities are not seen: the harness declares none
- Tool "update_file" is covered by the core checks only: would be path (param "path", name matches /file/), but required parameter "blocks" cannot be filled by the harness; write a probes: entry to call it
- Tool "move_path" is covered by the core checks only: string parameters only, and none names a path, URL, command, SQL or repository; add it under tools: to include it
- Tool "copy_path" is covered by the core checks only: string parameters only, and none names a path, URL, command, SQL or repository; add it under tools: to include it
- 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.
Run it yourself
Started with the standard settings like this; put it in sealmark.yaml as the server:
npx -y @cyanheads/filesystem-mcp-server@1.0.4
Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.
Think a verdict is wrong, or want a server removed? Email disclosure@sealmark.dev with the server version. We recheck, correct the page if we were wrong, and add your reply. See the disclosure policy.