cks-mcp
Related Servers
Alternatives to cks-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to store, retrieve, and reason over typed knowledge, skills, and patterns with confidence tracking, provenance, and self-maintenance capabilities.-
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to build and explore a cognitive neuroscience-inspired knowledge graph with SQLite, supporting search, graph traversal, temporal sequences, and structured reasoning.24MIT
- AlicenseNot gradedqualityNot gradedmaintenanceProvides tools for semantic decomposition, proof search, knowledge graph operations, and neuro-symbolic reasoning that bridges neural LLMs with symbolic AI through RDF triples, lambda calculus, and compositional intelligence principles.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to create verifiable, replayable citations, search private knowledge bases, and publish Markdown with verified citation markers.MIT
- AlicenseNot gradedqualityAmaintenanceProvides exact, deterministic tools for math, dates, units, validation, and more to AI agents, returning precise answers with explicit assumptions and warnings instead of model guesses.MIT
- FlicenseAqualityDmaintenanceEnables Claude to search, query, and interact with an Enterprise Knowledge Management System (EKMS). Supports semantic search, knowledge recommendations, relationship graphs, and feedback recording for enterprise knowledge bases.7-
TDQS
Scored across 24 tools
Each tool targets a distinct operation (evolve, validate, serialize, merge, branch, etc.), and the descriptions are detailed enough to separate them. However, a few pairs like create_branch vs fork_sandbox and merge_knowledge vs merge_branch could still cause confusion if an agent only skims the names.
All tool names follow a consistent verb_noun pattern using lowercase and underscores (e.g., evolve_knowledge, merge_branch, query_subgraph). Even compound operations like detect_contradictions fit the pattern, making the naming highly predictable.
With 24 tools, the server sits in the upper range of what feels heavy for an MCP server. The domain is complex enough to warrant many operations, but the count borders on excessive; a few tools could potentially be consolidated without losing capability.
The tool surface covers the full lifecycle of knowledge structures: creation (construct_knowledge), exploration (query_subgraph, search_semantic), modification (evolve_knowledge, merge_branch), validation, branching, versioning, and export. Minor gaps exist such as no explicit get_session or delete_session, but close_session and the session-aware operations largely fill these needs.