burn-mcp-server
Related Servers
Alternatives to burn-mcp-server
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceCognitive prosthetic for AI agents. Indexes conversation history from ChatGPT, Claude Code, Cursor, and Gemini CLI into searchable embeddings. 25 MCP tools including tunnel_state (resume where you left off), switching_cost (quantify context-switch penalty), thinking_trajectory (track idea evolution), and alignment_check (decisions vs principles). LanceDB + Parquet, 12ms recall, local-first.2571MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first markdown vault with a built-in MCP server (streamable HTTP). 16 tools and 2 resources for Claude Code / Desktop / Cursor: read/write/search plus context_for_query, find_orphans, weekly_digest, compare_notes, semantic_outline. Per-folder agent permissions, LanceDB vectors, local Xenova ONNX embedder swappable to Ollama. Single Bun binary. AGPL.33AGPL 3.0
- AlicenseAqualityAmaintenanceLocal-first knowledge graph MCP server — hybrid BM25 + vector + graph retrieval over your personal vault with provenance-grade extraction. 8 tools for Claude Desktop including search, archaeology, and graph write.1425 PyPI3MIT
- AlicenseAqualityDmaintenanceMCP server that connects any AI to your Obsidian vault. Save articles from your phone, search across notes, build a compounding knowledge base. 15 tools, three transport modes (stdio, HTTP, cloud), zero-install Google Drive OAuth onboarding.156 npmMIT
- AlicenseAqualityAmaintenanceA local, read-only MCP server that makes bookmarks from browsers, read-later apps, and export files accessible to AI assistants, enabling search, triage, and summarization without sending data anywhere.849 npmMIT
- AlicenseAqualityAmaintenancePrivacy-first local memory vault every AI shares over MCP. Markdown + SQLite on your machine; Claude, ChatGPT, Cursor, and any MCP client read and write it live. No cloud, no account, no telemetry124MIT
TDQS
Scored across 26 tools
Several tools have clear boundaries (e.g., move_flame_to_spark vs move_flame_to_ash), but get_bookmark and get_article_content are explicitly identical, and list_vault/search_vault plus list_sparks/search_sparks overlap heavily. The descriptions help, but the duplicate is a direct ambiguity.
Most tools follow a consistent verb_noun snake_case pattern (search_vault, list_sparks, create_collection). Minor deviations exist: 'get_collections' is actually a list operation, and 'fetch_content' uses a different verb than 'get_article_content', but these are small and do not undermine the overall consistency.
With 26 tools, the count exceeds the 25+ threshold for being too heavy. Many operations are repetitive (e.g., individual moves vs batch_triage) and could be consolidated, making the surface feel bloated for what is essentially a bookmark management domain.
The lifecycle (Flame to Spark to Vault to Ash) is well covered, but there is no explicit 'create bookmark' tool since fetch_content only fetches and doesn't necessarily save. Additionally, there are no update or delete operations for bookmarks, and no way to remove a bookmark from the Vault or delete collections, leaving significant gaps.