Skip to main content
Glama
bemnetbeshah

Interview Prep MCP Server

by bemnetbeshah

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort for HTTP transports. Checked first for platform hosts.8000
MCP_HOSTNoHost for HTTP transports.127.0.0.1
MCP_PORTNoPort for HTTP transports. PORT is checked first for platform hosts.8000
DATABASE_URLNoPostgres connection URL. Takes precedence over SQLite when set.
MCP_TRANSPORTNoFastMCP transport, for example `stdio` or `streamable-http` depending on the installed MCP SDK.stdio
OIDC_AUDIENCENoJWT audience required for public OIDC launch, usually `interview-prep-mcp`.
OIDC_JWKS_URLNoJWKS endpoint for validating OIDC access tokens.<issuer>/.well-known/jwks.json
OIDC_ISSUER_URLNoEnables public OIDC/JWT bearer-token verification when set.
MCP_BEARER_TOKENNoEnables static bearer-token auth when set and OAuth is unset.
OAUTH_LOGIN_SECRETNoEnables approval-secret OAuth for ChatGPT Developer Mode when set.
OIDC_SUBJECT_CLAIMNoJWT claim used as the stable study owner subject.sub
MCP_DEFAULT_SUBJECTNoOwner subject used for local unauthenticated runs and simple single-subject auth.bem
PUBLIC_SERVICE_NAMENoName shown on public informational pages.Interview Prep MCP
OIDC_REQUIRED_SCOPESNoRequired access-token scopes for MCP tool calls.study:read study:write
PUBLIC_CONTACT_EMAILNoSupport/privacy contact shown on public pages.support@example.com
RATE_LIMIT_PER_MINUTENoIn-memory per-subject MCP tool-call limit per service instance.120
INTERVIEW_PREP_DB_PATHNoSQLite database path.data/interview_prep.sqlite3
MCP_ALLOW_UNAUTHENTICATED_HTTPNoAllows unauthenticated HTTP only for non-public development.false

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_studiesB

Return all active study areas.

list_topicsA

Return active topics within a study.

list_subtopicsA

Return active subtopics within a topic with current mastery state.

get_due_subtopicsA

Return the spaced-repetition queue sorted by overdue-ness.

get_subtopic_historyA

Return attempts, trend, and state for one subtopic.

export_my_dataA

Export all study data for the authenticated user.

delete_my_dataA

Hard-delete all study data for the authenticated user after explicit confirmation.

log_attemptA

Record a quiz attempt and update SM-2 scheduling state.

create_studyB

Add a new study area.

create_topicA

Add a topic under a study.

create_subtopicA

Add a subtopic under a topic.

update_subtopicC

Edit a subtopic's name or description.

delete_studyB

Soft-delete a study while preserving history.

delete_topicA

Soft-delete a topic while preserving history.

delete_subtopicA

Soft-delete a subtopic while preserving history.

Prompts

Interactive templates invoked by user choice

NameDescription
review_due_itemsStart a spaced-repetition review session using due subtopics.
create_study_planCreate or extend a study hierarchy through MCP tools.
review_progressInspect study progress and weak spots without changing data.
account_data_requestHandle export or deletion requests with the correct account-data tools.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 15 tools

Disambiguation5/5

Each tool targets a distinct resource or action: study hierarchy reads/creates/deletes, attempt logging, due queue, history, and data privacy. list_subtopics and get_due_subtopics are clearly different because one returns all subtopics while the other returns the spaced-repetition queue.

Naming Consistency5/5

Tool names follow a consistent verb_noun pattern with hierarchical nouns: list_*, create_*, delete_*, and get_*. Pluralization is predictable, and no mixed casing or vague verbs are present.

Tool Count5/5

15 tools is at the upper bound of the ideal range, but each tool earns its place by covering study hierarchy management, spaced-repetition workflow, history inspection, and user data controls. The scope matches the server's stated purpose without unnecessary redundancy.

Completeness3/5

The core hierarchy and spaced-repetition workflow are well covered, but update_study and update_topic are missing while update_subtopic exists. This creates an incomplete CRUD surface for higher-level resources; agents cannot rename or edit a study or topic without deleting and recreating it.

Maintenance

ActivityMaintained
ResponsivenessNo issues