MCP Risk

Scan report

build.exascale/osint

This page reports an automated security scan of build.exascale/osint (remote), scanned 2026-07-28. 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.

remote, scanned 2026-07-28, tool surface via remote-tools-list

C 70/100 Capability risk: Low permalink

The grade rates trust: provenance, transport, known vulnerabilities and instruction integrity. Capability risk rates what the tools can do and is reported, not penalised – a server built to run shell commands is doing its job (Policy §2.4).

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as build.exascale/osint. 1 finding
  • Registry entry: build.exascale/osint ↗
WARN Source repository is public and maintained §1.2

No public source repository could be identified for this server.
INFO Published package is consistent and attested §1.3

No published package associated with this server (remote-only or non-npm/PyPI source).
PASS Tool surface is inspectable and proportionate §2.1–§2.4
50 tool(s) enumerated; no high-risk capability signals. 2 findings
  • Tools exposed: 50
  • Detected capabilities: none
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://api.exascale.build/mcp
UNVERIFIABLE Authentication required §3.2

Endpoint rejected the probe (HTTP 400); whether it requires authentication could not be determined.
WARN OAuth protected-resource metadata published §3.3
No protected-resource metadata found - clients cannot discover the authorization server per spec. 1 finding
  • Checked: https://api.exascale.build/.well-known/oauth-protected-resource
INFO No known vulnerabilities (OSV.dev) §4.1

No package to query (remote-only server).
WARN Server-supplied instructions free of poisoning indicators §5.1–§5.4
20 suspicious indicator(s) found in server-supplied instructions, tool descriptions, or schemas. 20 findings
  • query_power_demand_v1 description: oversized: 2256 chars (limit 2048)
  • query_power_demand_rollup_v1 description: oversized: 3144 chars (limit 2048)
  • query_power_retail_sales_v1 description: oversized: 2117 chars (limit 2048)
  • query_power_interconnection_queue_v1 description: oversized: 2678 chars (limit 2048)
  • query_power_interconnection_queue_pjm_v1 description: oversized: 3007 chars (limit 2048)
  • query_power_interconnection_queue_pjm_cycle_v1 description: oversized: 2595 chars (limit 2048)
  • query_power_interconnection_queue_caiso_v1 description: oversized: 3618 chars (limit 2048)
  • query_power_interconnection_queue_nyiso_v1 description: oversized: 4080 chars (limit 2048)
  • query_power_interconnection_queue_isone_v1 description: oversized: 3470 chars (limit 2048)
  • query_power_interconnection_queue_ercot_v1 description: oversized: 4230 chars (limit 2048)
  • query_power_interconnection_queue_spp_v1 description: oversized: 3834 chars (limit 2048)
  • query_power_price_ercot_v1 description: oversized: 3108 chars (limit 2048)
  • query_ai_infrastructure_construction_v1 description: oversized: 3090 chars (limit 2048)
  • query_ai_infrastructure_employment_v1 description: oversized: 6313 chars (limit 2048)
  • query_ai_infrastructure_trade_v1 description: oversized: 2357 chars (limit 2048)
  • query_ai_infrastructure_equipment_trade_v1 description: oversized: 2737 chars (limit 2048)
  • query_ai_infrastructure_production_v1 description: oversized: 2744 chars (limit 2048)
  • query_robotics_trade_v1 description: oversized: 2901 chars (limit 2048)
  • query_robotics_adoption_v1 description: oversized: 2836 chars (limit 2048)
  • query_space_satellite_filings_v1 description: oversized: 2940 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.