fw-context-mcp
Related Servers
Alternatives to fw-context-mcp
- AlicenseAqualityAmaintenanceKnot is a semantic and structural codebase indexer designed for AI coding agents and developers navigating large projects. It combines vector search and graph traversal to find code by meaning, analyze impact via reverse dependencies, and explore file architectures.65MIT
Related Servers
- FlicenseNot gradedqualityBmaintenanceProvides graph-native code intelligence for coding agents, enabling them to navigate repositories through compact SQLite-backed symbol graphs and retrieve full source only for relevant symbols.-
- AlicenseNot gradedqualityDmaintenanceProvides intelligent code indexing with 15 MCP tools for symbol extraction, hybrid search (FTS5+vector), call graphs, and incremental indexing of local folders and remote repos, enabling token-efficient code retrieval for AI agents.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, and change-impact analysis.2MIT

Semantic Code Search MCPofficial
FlicenseNot gradedqualityDmaintenanceProvides AI coding agents with structured access to indexed codebases via semantic search, symbol analysis, and file reading tools.12-- AlicenseNot gradedqualityAmaintenanceExposes a codebase's symbol graph and symbol-aware editing tools to AI agents, enabling targeted symbol lookup, impact analysis, and atomic multi-file edits with reduced context tokens.12 npmMIT
- FlicenseNot gradedqualityBmaintenanceBuilds a semantic knowledge graph of C++ code and exposes 9 MCP tools for AI assistants to search classes, functions, inheritance, callers, callees, overrides, and more.3-
TDQS
Scored across 39 tools
The search tools heavily overlap: search_code, search_bodies, search_content, semantic_search, smart_search, and lookup_symbol all find code but with subtly different scopes, requiring the agent to internalize lengthy 'when to use' rules. The reindex pair reindex_file and reindex_file_impl are nearly identical in name and description. Some tools are distinct (get_vector_table, find_dead_code), but the search family creates real selection risk.
Naming is a mix of get_*, find_*, search_*, lookup_, list_, reset_, reindex_, check_, and configure_ verbs. Within groups it is consistent (find_callers, find_callees_recursive, find_references), but find_all_callers_recursive vs find_callers_recursive vs find_callers and reindex_file vs reindex_file_impl break the pattern. The recurring shared args and project/variant/image suffixes are consistent, but verb style is not unified.
39 tools is on the heavy side for a code-intelligence server. The core domain — search, call graph, symbols, files, build/index management — is broad but the count is inflated by near-duplicate tools (reindex_file/reindex_file_impl, search_code/search_content overlapping bodies, six search tools). A well-scoped set would sit closer to 20-25 tools.
The surface covers the firmware-analysis domain very well: symbol lookup, text search, call graphs, references, data flow, inheritance, dead code, vector tables, file reading, index health, project discovery, and LLM config. Missing operations are minor — there is no tool to list all symbols in a namespace or to get diffs between build variants (only per-build querying), and no explicit index-trigger tool beyond reindex_file, but these are workaround-level gaps.