oss-analyzer
Related Servers
Alternatives to oss-analyzer
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceAn MCP server that extracts complete knowledge from any codebase — architecture, patterns, dependencies, API surface. Combines static analysis with AI-powered deep interpretation.8MIT
- FlicenseBqualityCmaintenanceEnables AI agents to perform comprehensive, zero-infrastructure codebase analysis through 24 MCP tools, covering security, quality, architecture, type safety, git history, and dead code detection with high precision and local privacy.45-

Celmis MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables querying indexed code across multiple repositories with file-level citations, reviewing pull requests, auditing dependencies, and exporting SBOMs and evidence packs through MCP tools.4AGPL 3.0- AlicenseAqualityAmaintenanceIndexes polyglot repositories into a local architecture graph resolving DI bindings, HTTP/gRPC/GraphQL routes, message queues, and ORM/SQL table lineage. Provides dozens MCP tools for call-chain tracing, blast-radius impact analysis, OpenCypher queries, and deterministic CI architectural gates.1625MIT

CodeGraphofficial
AlicenseNot gradedqualityBmaintenanceBuilds a semantic graph of codebases across 38 languages and exposes 42 MCP tools for structured code understanding, search, and impact analysis.162Apache 2.0- AlicenseNot gradedqualityCmaintenanceEnables agents to take software apart over MCP — native binaries, Go/Rust/.NET assemblies, WASM and EVM bytecode, Android and Flutter apps, firmware, databases, crashes and network captures — returning findings backed by code, references and explicit unknowns. Drives deep-analysis engines such as Hopper, Ghidra, IDA, JADX and Frida entirely locally, letting agents explain behavior or rebuild a feature in your own project.MIT
TDQS
Scored across 31 tools
Most tools have clearly distinct targets and actions: repo lifecycle, LSP operations, dataflow build/query, unit leasing, findings, claims, unknowns, and reports are all separable. A few pairs could be confused, such as oss_unit_complete vs oss_symbols_mark (both mark work as reviewed) and oss_unknown_update vs oss_claim_withdraw (both resolve records), but the descriptions differentiate them.
A strong oss_<resource>_<verb> pattern is used throughout (oss_repo_open, oss_unit_next, oss_finding_record, oss_claim_review). Minor deviations exist: noun-only tools like oss_capabilities and oss_doctor, plus singular/plural oscillation between oss_unknown_record and oss_unknowns_list, and oss_unit_next vs oss_units_list.
31 tools is heavy and sits at the upper boundary where the surface starts to feel fragmented across evidence, claims, unknowns, and units. The multi-stage audit workflow justifies much of it, but several groups (claim review/withdraw/pending, unknown record/update/list) could be consolidated without losing capability.
The surface covers the full lifecycle: repo open/list/status/close, inventory build, unit leasing and context, symbol marking, finding recording, independent review, unknown tracking, coverage/features/export reports, plus LSP and dataflow engines and a doctor/capabilities check. There are no obvious dead ends for the stated deep-audit purpose.