2,175 servers in AI & Agents
Official DeepSeek MCP server for chat, completion, model listing, and balance endpoints.
Invoke a Watson Orchestrate agent via MCP. Configure with WO_AGENT_ID.
Persistent memory for AI tools. Local-first knowledge graph with hybrid search.
Persistent memory + context layer for AI dev teams. 17 tools via MCP.
API marketplace for AI agents — 100 services, 87 free, one API key
Autonomous AI development system with persistent task queue and background execution
HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants
Graph-vector memory for AI assistants using FalkorDB and Qdrant
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
MCP server that loads and serves skills from a mounted directory with hot reload.
Content-addressed semantics: fail-closed handshakes over 617 cognitive patterns.
Tool selection, Cohere-compatible reranking, and on-chain pricing-truth for agents
x402 directory for AI agents: 1,700 pay-per-call APIs, USDC on Base, 5 free trials per wallet.
Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
Shared memory router for AI agents: save/search/recall, session-start injection, review inbox.
Search your AI chat history from Claude, Cursor, Codex, and other MCP clients.
Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more.
Self-hosted agent continuity server with bounded, recoverable memory and restart orientation.
Non-custodial 402 payments for agents. 88-tool stdio seller MCP + hosted keyless buyer twin.
Manage your Hamilton Harness AI rep: knowledge, rules, orders, tests and conversations.
技能库维护 MCP server：损坏扫描/改前备份/决策日志/体检（skill-evolution 机械环节工具化），uvx 一行接入
Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
Runtime governance enforcement for AI agents. Zero token overhead.
Zero-knowledge encrypted vault for AI agents. EU-hosted persistent storage.
Query OpenTelemetry traces from agent runs through MCP.
Change control for what AI agents learn: humans promote, releases are signed, rules can be recalled
Persistent knowledge graph: entities, relations, and observations for agents.
Store, query, and create YAML workflow playbooks for LLM agents.
Human approval gate for AI agents: risk-scored requests that only a person can approve