nds-mcp
Related Servers
Alternatives to nds-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceLets an MCP client query SQLite databases through validated, forced read-only, row-capped, time-limited and logged operations, so AI agents can explore data without risking writes or runaway queries. It also ships an eval harness that measures how accurately a model answers benchmark questions via text-to-SQL through the server.4MIT
- AlicenseNot gradedqualityDmaintenanceA pure SQLite structured long-term memory MCP server for AI agents, featuring adaptive Ebbinghaus forgetting curves, hierarchical memory tiers, trust feedback, and anomaly detection—all fully offline with deterministic scoring.MIT
- AlicenseNot gradedqualityDmaintenanceMCP tool server providing SQLite database access for AI agents.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server enabling natural-language querying of SQLite databases via schema discovery, GraphRAG retrieval, and safely guarded read-only SQL execution.-
- AlicenseNot gradedqualityDmaintenanceLocal MCP server for indexing personal knowledge into SQLite with hybrid search, chunk-level citations, memory tools, and agent orchestration.4MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server providing SQLite database access for AI agents, enabling SQL execution, schema inspection, CRUD operations, and data export.MIT
TDQS
Scored across 26 tools
Most tools have clearly distinct purposes, targeting specific databases and data types. A few pairs, like nds_get_decay vs nds_query_decay_feedings and nds_get_mass vs nds_find_nuclide, could cause minor confusion, but the descriptions provide enough context to differentiate them.
Tool names consistently start with 'nds_' but mix verbs like get, query, list, search, find, and interpolate. There are also noun-style names such as nds_info and nds_catalog, so the pattern is not fully uniform, though still readable and descriptive.
With 26 tools, the server is on the heavy end, exceeding the typical 3-15 tool range. However, the broad scope covering multiple nuclear databases (NUBASE, AME, ENSDF, JENDL, EXFOR, CODATA) justifies a larger tool surface, making it borderline but not excessive.
The tool surface covers major nuclear data types: nuclide properties, masses, decay, levels, gammas, cross sections, EXFOR, and constants. Minor gaps exist, such as no direct access to raw ENDF-6 BLOB payloads and TUNL data only for A≤20, but these are workable limitations.