"Data science and deep learning papers" matching MCP servers:

Enables users to link their Ed Discussion, Moodle and OnTrack accounts through a cloud-hosted SSO broker and then browse course materials, threads, deadlines, grades, tasks and attendance-code evidence from an OAuth-capable MCP client. Course discovery and binding tools let users associate courses across platforms, with per-user scoped access and revocation controls.

Lets MCP clients safely investigate live business data across multiple enterprise APIs by giving each subject a consistent scoped pseudonym and surfacing disagreements between sources as findings.

Enables Claude or any MCP-capable assistant to explore and query a small business's sales, payments, invoices, and expenses through read-only SQL tools, while personal-data columns and write operations are refused by the database policy.

Enables agents to detect and redact PII and secrets in text, HTML, and PDF documents before they reach an LLM, with reversible placeholder, mask, or hash redaction, and to list supported detectors and redaction styles.

Enables agents to validate data safety before storing, transmitting, or logging data, preventing GDPR/HIPAA/PCI-DSS violations with clear verdicts like SAFE_TO_PROCESS, REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE.

Seven read-only tools help AI agents review public breach disclosures, organization histories, incident timelines and aggregate statistics. Preserve source attribution, redaction and incomplete-coverage warnings. Local threat-text triage needs no key; no breached data, credentials or private records are collected.

Lets AI agents and developers inspect and query local MySQL, Redis, and MongoDB instances over STDIO or authenticated loopback HTTP, with read-only defaults and allowlisted non-production writes that require explicit opt-in. Production connections always reject writes, and database-enforced read-only accounts are recommended.

Enables searching for relevant tables and retrieving data from Microsoft Sentinel's data lake using natural language, supporting security hunting scenarios like password-spray detection and impossible travel checks.

Enables MCP clients such as Claude, ChatGPT and Cursor to answer business questions about sales, customers, orders and spreadsheets in natural language by reading live Postgres/SQLite databases and Google Sheets without exporting files or gaining write access. Guardrails include AST-based read-only SQL validation, read-only database roles, row/byte caps with pagination, PII masking, bearer-token auth for remote HTTP use, and a full JSONL audit log of every tool call.

Enables organisations to connect a database so people can query it through an MCP client, authenticating through the organisation's own identity provider. Every question is parsed and checked against role-based table, column and row limits before running, with all decisions recorded in an audit trail.

GDPR Chapter V runtime guard for cross-region agent transfers. Supports adequacy decisions, SCCs, BCRs, and IDTA.

Enables AI coding assistants to audit datasets against DAMA-DMBOK quality dimensions, sanitize PII, generate differential-privacy synthetic twins, compress prompt context, and export dbt schema tests and interactive HTML reports. It supports development against sensitive data with zero real records exposed to external LLMs.

Enforces identity-based access control and audit logging for MCP servers, letting you grant fine-grained tool permissions to users and systems while failing secure by default.

Enables authenticated organization members to submit, query, and manage schema-validated structured records directly from ChatGPT, with membership requests and approval workflows gating access. All operations are tenant-isolated, permission-checked, and audited, so records are only reachable by approved members of the owning organization.

Middleware that converts existing APIs/DBs into MCP tools with secure credential injection, data scoping, and immutable audit logs.

Enables querying Red Hat security data including CSAF advisories, CVEs, and OVAL streams through natural language.

Enables Claude Code to work with personal data that stays on the local machine, running SQL, Python, and file/schema inspection in a sandboxed compute-to-data setup that returns only aggregates, schemas, synthetic fixtures, and pseudonymized results. Raw records, file names, and protected values never reach the Anthropic API, so Auto mode can stay hands-off.

Enables AI agents to securely reach enterprise tools and other agents through a governed gateway with pinned tool definitions, delegated authorization, content inspection, human approval, and signed audit trails.

Enables named, authenticated callers to run read-only introspection of a Google Cloud project and to read and write per-tenant notes that stay isolated between callers. Every request is scope-checked against a reviewed policy, rate-limited per caller, and audited without ever logging argument values.

Enables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.