45Trust score 45 of 100, Fair
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
Registry
Loading the directory
Category
AI and memory
MCP servers for embeddings, vector stores, model gateways, and long-term memory.
45Trust score 45 of 100, Fair
RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
Registry
45Trust score 45 of 100, Fair
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Registry
45Trust score 45 of 100, Fair
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Registry
45Trust score 45 of 100, Fair
LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
Registry
45Trust score 45 of 100, Fair
Real-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP.
RegistryRemote
45Trust score 45 of 100, Fair
One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.
Registry
45Trust score 45 of 100, Fair
Track how 350+ AI models mention your brand — manage projects, run scans, analyze results
Registry
45Trust score 45 of 100, Fair
Local-first AI context and memory server for cross-tool coding continuity.
Registry
45Trust score 45 of 100, Fair
Read-only Qdrant vector DB for AI agents — collections, info, browse points, count, search.
Registry
45Trust score 45 of 100, Fair
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Registry
45Trust score 45 of 100, Fair
Persistent memory, task coordination, and HITL queue for AI coding sessions.
RegistryRemote
45Trust score 45 of 100, Fair
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Registry
45Trust score 45 of 100, Fair
Scan website legal docs for missing or stale compliance clauses. Rule-based, no LLM.
Registry
45Trust score 45 of 100, Fair
AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.
Registry
45Trust score 45 of 100, Fair
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Registry
45Trust score 45 of 100, Fair
Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.
Registry
45Trust score 45 of 100, Fair
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
Registry
45Trust score 45 of 100, Fair
Efficient context management: code search, evidence packs, and memory for coding agents.
Registry
45Trust score 45 of 100, Fair
Graph-based memory system for LLMs with knowledge graphs and semantic search.
Registry
45Trust score 45 of 100, Fair
MCP server for persistent, semantic memory across AI sessions
Registry
45Trust score 45 of 100, Fair
Inject, parse, and strip [N] citation markers in RAG outputs.
Registry
45Trust score 45 of 100, Fair
Clean raw HTML into LLM-ready text before agents spend tokens.
Registry
45Trust score 45 of 100, Fair
Stealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.
Registry