GuardedServer
Related Servers
Alternatives to GuardedServer
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables 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.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with SQL Server Data Warehouses using natural language for automatic schema discovery and report generation. It ensures security by restricting operations to read-only SELECT queries through both code validation and database permissions.-
- FlicenseNot gradedqualityBmaintenanceEnables read-only discovery and retrieval of allowlisted catalog datasets with host-assigned roles, strict tool validation, SQLite read-only enforcement, and audit hash chaining. It supports querying bounded daily aggregates while preventing arbitrary SQL, file access, shell commands, credential use, or role escalation.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query a read-only data surface through typed tools, enforcing caller-specific row access, field masking, and withheld-row disclosure so they can retrieve entitled information without writes or silent data leakage.MIT
- AlicenseBqualityBmaintenanceEnables AI assistants and MCP clients to safely inspect allow-listed SQLite databases by listing tables, describing schemas, running capped read-only queries, sampling rows, and exporting CSV, with writes blocked unless explicitly enabled.7MIT
- AlicenseNot gradedqualityBmaintenanceEnables an LLM or MCP host to inspect and query a business database through read-only tools for listing tables, describing schemas, and running guarded SELECT queries with row limits, timeouts, and audit logging.MIT
TDQS
Scored across 3 tools
Each tool maps to a distinct step in a linear workflow: discover available queries (list_queries), inspect one query's contract (describe_query), and execute it (run_query). There is no overlap in purpose or resource targeting, so misselection is unlikely.
All three names follow a strict verb_noun snake_case pattern with a shared 'query' noun, and the verbs (list/describe/run) accurately signal the action. Highly predictable for an agent.
Three tools is the minimal complete set for a catalog-style execution server, and each earns its place in the discover-inspect-run sequence. Nothing is padded or redundant.
The read-only query lifecycle (discover, describe parameters, execute) is fully covered, including parameter placement, date formats, and row limits in the description. Minor gaps: describe_query does not expose result column schemas or output shape, and there is no way to surface query-level errors or examples before running.