"A search query containing special characters and SQL injection-like encoding" matching MCP servers:

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

An MCP server for identifying SQL injection vulnerabilities in web applications using various techniques like error-based, time-based, and union-based scanning. It supports bulk URL processing, WAF bypass strategies, and authenticated testing across multiple database systems.

Enables security researchers to evaluate AI system defenses against prompt injection attacks through a comprehensive set of test vectors and analysis tools.

An MCP server for prompt injection boundary enforcement that scans URL content using a tiered LLM model strategy.

Blocks indirect prompt injection by tracking data provenance, not text patterns. Enables safe agent interaction with untrusted content.

A local MCP server for secure database querying from Claude Code, with Apple Keychain credential storage, permission-based access control, and audit logging.

Enables AI assistants to safely explore and query MySQL, MariaDB, PostgreSQL, SQLite and StarRocks databases through read-only tools for schema listing, table description, schema search, row sampling, query execution, and plan explanation. Enforces least-privilege accounts, engine-level read-only sessions with timeouts, parsed SQL guardrails, and column masking so runaway or unsafe queries are refused.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

Gives AI coding tools reviewed access to PostgreSQL, MySQL, SQL Server, and SQLite databases, letting read-only queries run instantly while every data or schema change pauses for human approval in a review dialog. It also exposes schema introspection for agents and a way to open the connection manager.

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.

Scans MCP servers for prompt-injection, tool-poisoning, and SSRF vulnerabilities using 30+ canonical rules across 5 severity tiers, with optional signed safety reports for procurement.

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.

WAF for AI agents — block prompt injection before it reaches the LLM.

Enables AI assistants to safely run read-only SQL against SQLite databases through whitelist-validated queries, capped result sets, and confined file paths. It also exposes schema inspection so models can discover tables and columns before querying.

A governed SQL gateway for untrusted AI agents, providing controlled access to PostgreSQL, MySQL, and OceanBase with RBAC, field ACLs, row policies, and cost controls.

Enables AI assistants to explore and analyse local CSV, Parquet or JSON files through validated read-only SELECT queries, with schema discovery, profiling and query-plan tools. Results are capped, timed, PII-masked and audit-logged inside a locked DuckDB sandbox that cannot write, reach the network or read other files.

Enables agents to run SELECT-only queries and inspect table metadata against configured databases via MCP Proxy, with timeouts, row and byte caps, and audit logging.

Enables assistants to inspect schemas and run bounded, read-only SQL queries over synthetic retail data with database-enforced guardrails, resource limits, and blocked write attempts.

Enables LLMs to propose UPDATE/DELETE SQL that is run in a transaction, measured, and rolled back, requiring human approval before applying to prevent unauthorized changes.