Clarik Mcp Server
Related Servers
Alternatives to Clarik Mcp Server
- AlicenseAqualityBmaintenanceSecurity, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.454 npm3MIT
Related Servers
- AlicenseAqualityDmaintenancePersistent memory + intelligent context for Claude Code. Save and reuse solutions, decisions, and patterns across projects.437MIT
- AlicenseAqualityDmaintenanceCross-surface persistent memory for Claude. Bridges context between Claude Chat, Code, and Cowork via local SQLite with full-text search.68 npm6MIT
- AlicenseAqualityBmaintenancePersistent memory for Claude Code. Automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + reranker) via MCP tools. 100% local, zero config, zero API keys, zero invoice.1634 npm7MIT
- FlicenseAqualityDmaintenanceSupercharges Claude Desktop with persistent semantic memory, sandboxed file I/O, live web search, and local emotional intelligence using a local ChromaDB and Hugging Face model.6-
- AlicenseNot gradedqualityBmaintenance2-5x longer Claude Code sessions before compaction. Saves 30-40% on input token costs. Remembers your rules and corrections so Claude stops repeating mistakes after compaction. Auto-runs in the background, just install once and forget about it.135 PyPI421MIT
- FlicenseCqualityDmaintenanceProvides long-term memory and lossless context management for Claude Code, enabling automatic context compression, cross-session memory sharing, and semantic search across all history.10-
TDQS
Scored across 20 tools
Each tool has a clearly distinct purpose, from memory operations (learn, recall, edit) to session management (checkpoint, export) and quality checks (hallucination detector, assumption checker). There is no ambiguity or overlap in their descriptions.
All tools follow a consistent pattern with the prefix 'clarik_' followed by a descriptive noun or verb-noun combination in snake_case (e.g., clarik_memory_learn, clarik_diff_reviewer). No mixing of conventions.
20 tools is on the higher end but justified by the server's broad scope covering memory, sessions, quality checks, and project indexing. Each tool serves a specific, non-redundant function.
The toolset covers memory lifecycle (save, edit, clear, archive, recall), session management (checkpoint, export, search), and quality assurance (hallucination, assumption, diff review). Minor gaps like undo for memory edits are present but not critical.