SkillTotal

Is @modelcontextprotocol/core safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Delegated authentication (OAuth 2.0 / OIDC)

@modelcontextprotocol/core is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct are reported for review. It can: delegated authentication — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@modelcontextprotocol/core 2.2.0

npm_package · npm:@modelcontextprotocol/core
LOW
0
/ 100 risk score
Snapshot · scanned Sep 28, 2026 · @modelcontextprotocol/core@2.2.0 · engine 0.53.0 / ruleset 60

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of @modelcontextprotocol/core's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
delegated authentication

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Delegated authentication
Tool Execution Context / User Delegated Credentials

Findings (1)

LOWDelegated authentication (OAuth 2.0 / OIDC)ST-AUTH-DELEGATED

An OAuth 2.0 / OpenID Connect delegated-authentication flow was detected (authorization-code / refresh-token / token-exchange grant, an OIDC authorize/discovery endpoint or id_token, or a delegation library). Tools authenticate with the end user's delegated, scoped credentials rather than a long-lived embedded service credential. (6 occurrence(s) shown as evidence).

authorization_endpoint: SafeUrlSchema,
authorization_endpoint: SafeUrlSchema,
id_token: z.string().optional(),
authorization_endpoint: SafeUrlSchema,
authorization_endpoint: SafeUrlSchema,
id_token: zod_v4.string().optional(),

Fix: Delegated auth is a lower-blast-radius execution context than an embedded static credential. Confirm the requested scopes are minimal and that tokens are never logged or forwarded off-host.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →