MCP security report

scholar.0xpi.com

F31/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓8 tools scanned

https://scholar.0xpi.com/api/mcp

mediumask_ai_tutor
Referenced authentication token has no corresponding input parameter
The description states this tool 'requires the student to have connected their ScholarNet account... (a token from ScholarNet Settings)' but the input schema has no field to supply such a token. This mismatch suggests the credential is expected to be sourced from somewhere else (e.g., stored context, environment variables, or a prior message), which could induce the agent to search for and expose a stored secret/token when none was explicitly provided by the user in this call.
mediumgenerate_quiz
Implicit credential/session requirement not represented in schema
Same issue as ask_ai_tutor: the tool claims to require a 'connected ScholarNet account' but provides no parameter for any token/session id, creating ambiguity about how authentication is actually verified and encouraging the agent to look for credentials outside the declared inputs.
mediumgenerate_flashcards
Implicit credential/session requirement not represented in schema
Like the other 'connected account' tools, this description implies a required authentication token that is absent from the schema, which is inconsistent and could lead the agent to attempt retrieving or reusing a stored credential from an unrelated source.
mediumlist_my_flashcards
Data-listing tool with unverifiable auth requirement
This tool can enumerate a student's saved flashcard sets but has no schema parameter for identifying/authenticating the student, despite the description saying a connected account is required. Without an explicit account/session identifier, it's unclear how the tool scopes data access, raising a risk of cross-user data exposure if the backend infers identity from ambient/session state controlled elsewhere.
mediumlist_my_quizzes
Data-listing tool with unverifiable auth requirement
Similarly to list_my_flashcards, this tool lists private saved quizzes but takes no input parameters to identify or authenticate the requesting student, despite the description claiming a connected-account requirement, which is a mismatch worth verifying to avoid unauthorized data disclosure.
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowgenerate_study_plan
Requires student email for a stateless generation task
The tool description states the plan is 'sent/saved' to the student's email, but generating a study plan from a syllabus doesn't functionally require PII. This creates an incentive to collect and transmit personal contact information to an external service for every use, which could be used for marketing or profiling beyond the tool's stated purpose.
lowgenerate_thesis_statement
Unnecessary email collection for simple text generation
Generating thesis statement options from a topic has no functional need for an email address, yet the tool requires it. This pattern of mandatory PII collection across multiple 'free' tools should be reviewed for data-harvesting risk and clear user consent, especially since the AI agent would be silently forwarding the user's email without necessarily disclosing why.
lowgenerate_citation
Unnecessary email collection for citation formatting
Formatting a citation is a stateless text-transform operation; requiring a student email address to perform it is disproportionate to the tool's function and results in PII being sent to an external system for no clear technical reason.
Embed this badge

Show your MCP server’s security grade

MCP security grade F

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/64002fa1-8320-4753-aa98-9fe0cc20a282)](https://gateturbo.com/report/64002fa1-8320-4753-aa98-9fe0cc20a282)

Scanned 9/10/2026 · This is a point-in-time snapshot of the server’s public tools. Re-scan.

Connect this server safely with gate.

Continuous re-scans, drift alerts, per-tool allow/ask/block, and a log of every call.

Monitor it — free