Все MCP-серверы

Local-first, MCP-native persistent memory for AI agents — a single Rust binary with embedded SQLite, hybrid FTS5 + dense-vector search, and optional AES-256-GCM encryption. Fully offline, no cloud

A PostgreSQL Model Context Protocol (MCP) server acting as a robust persistent super memory, task tracker, and multi-agent coordination hub for AI assistants

Natural language PostgreSQL queries with automatic streaming, read-only safety, and universal database compatibility

provides AI-powered PostgreSQL performance tuning capabilities

Hosted MCP server that parses TypeScript and Python codebases into Neo4j knowledge graphs for blast radius analysis, dead code detection, dependency tracing, and architectural context

Governed PostgreSQL DBA operations — slow-query, bloat, and blocking-lock RCA, index management, vacuum/analyze, and replication lag (35 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback

Power BI MCP server with device code auth, enhanced refresh (table-level polling with retry), refresh diagnostics with root-cause error catalog, DAX queries with RLS simulation, PBIP source locating, and scheduled refresh reports

Connect LLMs to Power BI semantic models. Browse workspaces, tables, and measures, run DAX queries, and automatically page large results via local CSV

Zero-config persistent memory for AI agents with local SQLite. Mind Palace web dashboard, time travel (rewind/replay sessions), agent telepathy (cross-client memory sharing), code mode templates, morning briefings, and progressive context loading. 25 tools, 6 resources, 4 prompts

Oracle for AI agents that need to think past obvious answers. One tool, one reading. Free tier included

On-chain calculated crypto indicators (EMA, RSI, Bollinger Bands, Volatility) for 22 tokens via Chainlink oracle. 484 indicator feeds, 4 timeframes, free trial faucet

MCP Server for Qlik Cloud API that enables querying applications, sheets, and extracting data from visualizations with comprehensive authentication and rate limiting support

Open-source customer feedback platform with built-in MCP server. Agents can search feedback, triage posts, update statuses, create and comment on posts, vote, manage roadmaps, merge duplicates, and publish changelogs

63 deterministic quant finance tools for AI agents — options pricing, risk metrics, portfolio optimization, Monte Carlo, technical indicators, crypto/DeFi, and FX/macro. 1,000 free calls/day, no API key

Query SQL databases (SQLite, PostgreSQL, BigQuery, Databricks) in natural language through a business semantic layer — glossary, metrics, and a data dictionary grounded against your real schema

Inspect and operate Redis-backed job queues (Asynq and BullMQ): per-state counts, job detail with decoded payload and last error, and faithful retry/delete running each library's own scripts. Read-only mode for production

MCP server for RAGStack serverless knowledge bases. Search, chat with AI-generated answers, upload documents/media, scrape websites, and analyze metadata through an AWS-powered RAG pipeline (Lambda, Bedrock, S3, DynamoDB)

Persistent coding memory for AI assistants — hybrid search, knowledge graph, token-efficient context. MCP stdio (28 tools), npm @ratary/mcp-server , optional remote Streamable HTTP. Self-host D1, Postgres, MariaDB, or Docker

Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph with PPR traversal, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB + SQLite, zero external dependencies

Connect Redash to Claude — natural-language SQL with safety guards (blocks DROP/TRUNCATE, PII detection), BIRD-based smart table selection, plus saved queries, dashboards, widgets, and alerts

Local full-text code search for AI coding agents. Trigram-indexed, sub-100ms queries across large codebases, offline, 18 languages

Session continuity engine that solves session orientation. Boot reports with gap detection and 100-point scoring, structured end-session capture with typed continuity records, and BM25 memory search. 7 tools, local SQLite + FTS5, zero API keys

Structural observability for AI conversations. Detects loops, stuck states, breakthroughs, and convergence across 17 channels without analyzing content

Search and discover rescue dogs from European and UK organizations with AI-powered personality matching and detailed profiles