A
licenseNot graded
qualityB
maintenanceA Docker-based MCP server providing codebase memory and search tools. It enables storing/retrieving memories, regex search of code, and file summarization for AI assistants.
13,717 npm
MIT
willow-mcp
Related Servers
Alternatives to willow-mcp
Related Servers
- FlicenseNot gradedqualityCmaintenanceA local MCP server providing general utility tools, persistent note storage, and keyword-searchable knowledge base via Streamable HTTP, enabling multiple agents to share the same data.37 npm-
- FlicenseNot gradedqualityCmaintenanceEnterprise MCP server providing a suite of tools including file, database, GitHub, Slack, calendar, email, vector search, and Python execution, with safe defaults and OpenAI integration for automatic tool selection.-
- AlicenseNot gradedqualityDmaintenanceA production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.64MIT
- AlicenseNot gradedqualityAmaintenanceServes as a single local MCP entry point that proxies configured upstream MCP tools to multiple coding agents, keeps sessions warm, serializes exclusive services, and provides SQLite-backed task, lock, and memory tools.MIT
- AlicenseNot gradedqualityDmaintenanceMCP tool server providing SQLite database access for AI agents.MIT
- AlicenseAqualityBmaintenanceMCP server for managing and searching multi-tenant knowledge bases backed by SQLite with FTS5, enabling AI agents to persist and retrieve content via full-text search.131MIT
TDQS
C2.9/5.0
Scored across 144 tools
Disambiguation3/5
The set spans many coherent sub-domains, and descriptions often cross-reference siblings (counter-verbs, companion tools), so many tools are distinguishable. However with 144 tools there are overlapping families — knowledge_* vs kb_*, store_*/lineage_*/fork_*, session_*/dispatch_*/handoff_*, human_required_* vs grove_human_required — that will cause misselection under context pressure. The detailed docstrings help, but the surface is too crowded for clean mental separation.
Naming Consistency3/5
Nearly all names are snake_case, but prefixes are applied inconsistently: knowledge_ and kb_ name the same KB, session_/handoff_/verify_handoff split one lifecycle, and generic names (whoami, diagnostic_summary) sit beside domain-prefixed ones. The pattern is readable but not predictable enough for a 144-tool surface.
Tool Count1/5
144 tools is far beyond the 3–15 sweet spot and exceeds the 50+ 'extreme mismatch' threshold; even for a broad orchestration platform, this volume imposes severe selection and context costs and suggests many tools should be consolidated or split into separate servers. It is a maximal-surface design rather than a well-scoped tool set.
Completeness4/5
Coverage is broad across many domains — SOIL store CRUD/search/purge, KB ingest/search/verify/flag/retract, dispatch and handoff lifecycles, forks, envelopes, tasks, code graph, Grove, governance — so most core workflows have a path. Some lifecycle edges are absent (e.g., task/dispatch cancel, attestation update/delete), but they are minor relative to the overall surface.
Maintenance
ActivityActive
ResponsivenessWithin a week