Directory / server
@modelcontextprotocol/server-filesystem
This directory entry reports an automated security scan of @modelcontextprotocol/server-filesystem, scanned 2026-07-26. Trust grade B rates provenance, transport, known vulnerabilities and instruction integrity; capability risk is reported separately, not folded into the grade.
Automated checks
| Status | Check | Policy | Result |
|---|---|---|---|
| WARN | Listed on the official MCP registry | §1.1 | Not found on the official MCP registry. Not disqualifying, but listed servers carry namespace-verified provenance. |
| PASS | Source repository is public and maintained | §1.2 | Active repository with a license. 5 findings
|
| PASS | Published package is consistent and attested | §1.3 | Package is consistent with its source and carries provenance attestation. 6 findings
|
| PASS | Tool surface is inspectable and proportionate | §2.1–§2.4 | Package source scanned. Capabilities detected: filesystem. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 5 findings
|
| INFO | Transport & authentication | §3 | Local (stdio) server: runs with host-process privileges by design. Transport checks apply to remote servers; scrutiny shifts to §1/§2. |
| FAIL | No known vulnerabilities (OSV.dev) | §4.1 | 2 advisory(ies) on record for @modelcontextprotocol/server-filesystem @2026.7.10 (npm) - review whether the evaluated version is affected. 2 findings |
| PASS | Server-supplied instructions free of poisoning indicators | §5.1–§5.4 | No poisoning indicators found across 14 server-supplied text item(s). |
Score history
| Date | Grade | Score |
|---|---|---|
| 2026-07-26 | B | 81/100 |
| 2026-07-25 | D | 59/100 |
| 2026-07-12 | D | 59/100 |
What this grade covers
- Provenance & supply-chain integrity (§1)
- Tool surface & capability risk (§2)
- Transport & authentication (§3)
- Known CVEs via OSV.dev (§4)
- Instruction/tool poisoning patterns (§5)
Limitations: pattern-based only (no semantic injection detection), static npm analysis (live server instructions not retrieved for package-only scans), single-server scope (no cross-server toxic flow analysis). See the full policy.
Methodology: MCP Server Security Policy. Unfamiliar term? See the glossary.