aggregator-mcp
Related Servers
Alternatives to aggregator-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceLocal-first external brain for Claude Code, Codex, and any MCP client. Stores decisions, entities, and session artifacts in one SQLite file and exposes MCP tools for recall, page, promote, review, graph-query, and source-status.113 npm5MIT
- AlicenseAqualityCmaintenancePersistent memory + FTS5 full-text search for Claude Code conversation history. Indexes ~/.claude/projects/ JSONL into SQLite, exposes 10 MCP tools (store/recall/search memories, browse sessions, get summaries) plus prompts. Includes a web UI for visual exploration1062 npm95MIT
- FlicenseNot gradedqualityCmaintenanceCollects session JSONL from Codex and Claude Code into local SQLite memory, exposed through MCP with tools for memory context, search, get, put, forget, sleep, and status.-
- AlicenseAqualityDmaintenanceA universal, local-first MCP hub that indexes personal files (documents, code, etc.) and provides private semantic search via hybrid dense+BM25 retrieval, enabling agents like Claude Desktop to query your data without sending it to the cloud.176MIT
- AlicenseNot gradedqualityDmaintenanceA local, SQLite-backed code index for Claude Code, exposed over MCP, enabling targeted code retrieval without external APIs.95 PyPI1MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory MCP server for Claude Code. Store, search, and retrieve memories across sessions using hybrid vector + keyword search powered by SQLite, FTS5, and sqlite-vec.14 npm1MIT
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: aggregator_ingest provides human-gated instructions for refreshing data, aggregator_search_memory queries the indexed history, and aggregator_capabilities returns metadata about the cache. There is no overlap between searching, initiating ingest, and inspecting capabilities.
All tools share the consistent 'aggregator_' prefix and snake_case convention, making them easily recognizable. The slight inconsistency is that 'ingest' and 'search_memory' are verb-oriented while 'capabilities' is a noun, but this does not hinder predictability.
Three tools is on the low side but reasonable for a focused read-only search service. The set covers the essential actions (search, inspect capabilities, and a human-gated ingest instruction), so it does not feel excessively thin.
The search and capabilities tools cover querying and introspection well, but aggregator_ingest is a non-functional gate—it only returns instructions to run a CLI command, providing no programmatic way to refresh the data. This is a notable gap for agents that need current data, though it is intentional per security requirements.