scplus-mcp
Related Servers
Alternatives to scplus-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceLocal-first code intelligence MCP server that enables coding agents to search code, inspect structure, read exact ranges, and explore Git history with explicit token budgets.23Apache 2.0
- AlicenseNot gradedqualityAmaintenanceMCP server for local-first code intelligence, providing structural code graph, semantic search, and impact analysis to AI agents.2MIT
- AlicenseNot gradedqualityAmaintenanceProvides coding agents with searchable codebase context through an MCP server, enabling hybrid BM25 and semantic search, symbol graph navigation, and dependency mapping over an incrementally maintained repository index.85Apache 2.0
- FlicenseNot gradedqualityAmaintenanceProvides a local-first code indexing and search engine for coding agents via MCP, enabling precise codebase queries, symbol lookup, and freshness-aware retrieval.-
- AlicenseAqualityAmaintenanceA local-first MCP server that enables AI tools to safely inspect and search code repositories, providing indexing, deterministic BM25 search, code outlining, and context bundles without code modification.91MIT
- AlicenseNot gradedqualityAmaintenanceA unified code-intelligence gateway MCP server that gives coding agents a single safe API to search, trace, and understand any codebase using graph, LSP, and semantic engines, with a local-first privacy model and a safe-null contract.MIT
TDQS
Scored across 21 tools
Several tools have overlapping purposes, such as tree/skeleton/outline for file structure and symbol/word/search for lookup, making it easy for an agent to select the wrong one. Descriptions help but do not fully resolve the ambiguity, and groups like research/cluster/find_hub blur boundaries further.
Names are a mix of single words (status, tree, symbol, outline, lint) and verb_noun phrases (validate_index, repair_index, restore_points, find_hub, blast_radius) with no consistent pattern. This inconsistency makes it harder to predict related tool names or infer their function.
At 21 tools, the surface is borderline heavy, though the server covers a broad and complex domain. Some tools could be consolidated (e.g., skeleton vs outline), but the count is not extreme enough to be problematic.
The toolset covers the full lifecycle of indexing, validation, repair, retrieval, dependency tracing, linting, code writing, and restoration. The main gap is the absence of a raw file-content read tool, but this appears to be an intentional design to favor structural summaries over full-body reads.