build-mcp-server
What this skill does
Build an MCP server for integration with Claude
github/anthropics - Obfuscation - 33.4k stars
Threat analysis
Skill info
pkg:github/anthropics/claude-plugins-official@920824c?skill=build-mcp-serverAssessments (3)
Obfuscation
Obfuscation via local-llm-review
references/auth.md
Full reference: https://claude.com/docs/connectors/building/authenticationObfuscation via local-llm-review
references/remote-http-scaffold.md
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";Obfuscation via local-llm-review
references/versions.md
gh api repos/cloudflare/ai/contents/demos/remote-mcp-authless/src/index.ts --jq '.sha'Badge
Add the Anomity scan badge for build-mcp-server to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of build-mcp-server? Report an issue or request a rescan.
