MCP/Risk

Scan report

ai.signal8/mcp

npm, scanned 2026-11-07, tool surface via remote-tools-list

This page reports an automated security scan of ai.signal8/mcp (npm), scanned 2026-11-07. It rates trust (provenance, transport, known vulnerabilities, instruction integrity) as grade C and capability risk (what the tools can do) separately at low. It does not certify the server is safe to connect; it reports what could be checked from outside.

Tool surface changed. This server’s tool schema differs from its previous scan (2026-10-30). Re-review §2 and §5 before continuing to trust it - silent schema changes are the "rug pull" pattern.

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.signal8/mcp. 1 finding
  • Registry entry: ai.signal8/mcp ↗
PASS Source repository is public and maintained §1.2
Active repository with a license. 5 findings
  • Repository ↗
  • Last push: 4 days ago
  • Stars: 1
  • License: MIT
  • Security policy (SECURITY.md): absent
WARN Published package is consistent and attested §1.3
Minor integrity gaps: no npm provenance attestation. 6 findings
  • Package: @signal8ai/mcp@0.19.0 ↗
  • Ecosystem: npm
  • Age: 233 days
  • Weekly downloads: 118
  • Repo field matches source repo: true
  • Build-provenance attestation: absent
PASS Tool surface is inspectable and proportionate §2.1–§2.4
113 tool(s) enumerated; no high-risk capability signals. 2 findings
  • Tools exposed: 113
  • Detected capabilities: none
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://mcp.signal8.ai/mcp
WARN Authentication required §3.2

Server answers anonymous requests (HTTP 200). Acceptable only for deliberately public, read-only (Low) servers.
PASS OAuth protected-resource metadata published §3.3
Publishes /.well-known/oauth-protected-resource per the June 2025 authorization spec. 1 finding
  • Authorization server: https://api.signal8.ai/
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for @signal8ai/mcp @0.19.0 (npm).
WARN Server-supplied instructions free of poisoning indicators §5.1–§5.4
15 suspicious indicator(s) found in server-supplied instructions, tool descriptions, or schemas. 15 findings
  • server instructions: oversized: 5262 chars (limit 4096)
  • get_float description: oversized: 4986 chars (limit 2048)
  • search_sec_filings description: oversized: 3413 chars (limit 2048)
  • get_filing_structured description: oversized: 2127 chars (limit 2048)
  • screen_companies description: oversized: 2184 chars (limit 2048)
  • get_split_performance description: oversized: 2083 chars (limit 2048)
  • get_dilution_risk description: oversized: 4056 chars (limit 2048)
  • get_dilution_snapshot description: oversized: 4009 chars (limit 2048)
  • get_dilution_instruments description: oversized: 3430 chars (limit 2048)
  • get_baby_shelf_capacity description: oversized: 2954 chars (limit 2048)
  • get_upcoming_reverse_splits description: oversized: 3315 chars (limit 2048)
  • get_reverse_split_lifecycle description: oversized: 3161 chars (limit 2048)
  • get_ended_reverse_splits description: oversized: 2579 chars (limit 2048)
  • get_reverse_split_authority description: oversized: 3023 chars (limit 2048)
  • get_reverse_splits_list description: oversized: 5782 chars (limit 2048)

Verify manually - the scoring model can’t judge these for you

  • §2.3 - Is the tool surface no broader than the server’s stated purpose requires?
  • §3.4 - For stdio servers: which environment credentials does it read, and are they scoped rather than org-wide tokens?
  • §6.1 - Cross this server’s capabilities with your already-connected servers: any read-capability × send-capability pairs need explicit sign-off.
  • §6.2 - Run the connecting agent with sandboxing and egress controls sized to the combined tool surface, not just this server’s.

Methodology: MCP Server Security Policy. Checks and scoring weights are open source. Unfamiliar term? See the glossary.