"Running queries in Apache Superset" matching MCP servers:

A comprehensive MCP server for Apache Superset. Gives AI assistants full control over your Superset instance — dashboards, charts, datasets, SQL Lab, users, roles, RLS, and more — through 137 tools.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Blocks AI coding assistants from installing non-existent packages and accessing non-existent files.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

An MCP authorization server implementing OAuth2/OIDC flows, supporting dynamic client registration, PKCE, consent screens, and client ID metadata documents for MCP authorization.

MCP server for ai-scanner that enables AI agents to scan codebases for LLM usage, AI frameworks, and exposed secrets.

Authentik MCP provides seamless integration with Authentik's API, supporting both full-featured and diagnostic modes. These enable secure, automated user, group, and system management through MCP-compatible tools.

Offline MCP server that checks and scans your own AI prompts and outputs against a local compliance rule corpus. Returns rule ID, severity, citation, and remediation per finding — no API key, Apache 2.0.

MCP server for offline verification of signed artifacts — receipts, manifests, and audit bundles. MIT licensed, works without accounts or API calls. Tools: self_test, verify_receipt, verify_bundle, explain_artifact.

Scans diffs, files, and snippets for leaked secrets like AWS keys, GitHub tokens, and private keys, returning redacted findings while running fully locally without network calls.

Demonstrates agent-native platform onboarding with human-in-the-loop API key provisioning, plus live usage and rate-limit queries via Anthropic Admin APIs.

The accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.

Enables AI agents to investigate synthetic fraud cases by pulling transactions, running deterministic rules evaluations, pivoting across devices, and recording auditable case files with provenance.

Provides MCP tools for Sytadel identity and access management, enabling user listing, service account management, session anomaly queries, policy generation, and access reviews.

Lets an LLM explore a cryptic legacy ERP schema in plain language through a semantic layer (table listing, column descriptions, published dictionary) and run single read-only SELECT queries that return capped results. Enforces safety at the database engine level: only reads are authorized, sensitive columns are masked to NULL, queries are aborted after a few seconds, and every call is written to an append-only audit log.

MCP server for connecting to SQL Server in readonly mode. Allows any MCP client to explore the schema and run SELECT queries against a SQL Server database.

Enables LLMs to safely query databases through a secure gateway that masks PII, enforces role-based table access, rate limits requests, and logs all queries, with Prisma support.

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.

Local execution gate and stdio MCP proxy for AI agents, with tool policies, expiring leases, approvals and operator kill. Starts with two read-only setup tools; protection requires a trusted downstream server and private operator configuration. Not an OS sandbox. Apache-2.0.

A local memory layer for AI coding tools that stores user preferences, lessons, and project context as local files, exposed via MCP so different AI tools can share the same understanding of you.

Exposes 79 cybersecurity skills and 12 orchestrator agents over MCP, with a typed 11-field output contract, an enforced resolvable-evidence gate (no verdict without a resolvable source), and human-approval gating for every mutating action. Apache-2.0, stdlib-only.

MCP server for secure read-only PostgreSQL queries with automatic PII masking, pseudonymization, and strict SQL guards to enforce data privacy compliance.

Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role.

Bawbel MCP Server lets any agent scan MCP servers and skill files for security vulnerabilities mid-conversation. Seven tools covering server-card scanning, conformance scoring, rug pull detection, and AVE threat intelligence queries. Powered by the AVE standard with OWASP MCP Top 10 mapping on every finding. Free, Apache 2.0, no API key required.

A security-hardened Postgres MCP server that enables LLM agents to run safe, read-only SQL queries with enforcement via SQL-AST inspection and read-only transactions.

Enables AI coding assistants to enforce repository rules and block unauthorized file edits or commands, even after context compaction, by running as a local zero-config MCP server.

An MCP server that lets Claude query a mock business SQL database in plain language through read-only tools, with server-side guardrails that enforce SELECT-only queries and block access to sensitive payment data.

Provides an MCP interface to a full Kali Linux environment running in Docker, enabling AI assistants to execute security tools like nmap, sqlmap, and metasploit. It allows users to start/stop the container, run shell commands, and transfer files for security testing and educational purposes.

Enables running shell commands and persistent sessions with secrets stored in local secure storage injected into child processes at exec time based on rules. Guarantees secret plaintext never reaches the model context, returning only names, masks, and redacted output.

Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or HTTP/SSE) and blocks destructive tool calls before they execute, with TOFU catalog pinning against rug pulls and tool-poisoning/result-injection scanning. Single Rust binary, Apache-2.0.