739 servers in AI & Agents
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Save AI conversations into your Worldku memory and recall them from any MCP client.
Test and compare prompts across any AI provider. Bring your own keys.
Read Gmail, search GitHub, update Sheets, and post to Slack through Composio.
Pay-per-use IBM Granite AI via x402: chat, code, embeddings, forecasting. USDC on Base or Solana.
Biological memory for AI agents. Pattern learning, decay, clustering, 8-drive behavior.
Every Chipp tool in one MCP (large). For one area at a time, use the ai.chipp/chipp-* servers.
Build, test and publish iPaaS flows, apps, forms and AI agents in Neblex, in the cloud or on-prem.
Versioned skills and Binders for AI assistants. Requires a Bindry account and workspace API key.
Step-by-step workflows for ChatGPT, Claude and Claude Code: the AI gets one step at a time.
Persistent memory and shared context across compatible AI assistants, with account-scoped OAuth.
Body language for your agent: a consented 3-second gesture, Aligned or Unaligned with confidence.
Score documents and check agent work — signed PactCheck Receipts: proof-of-review for agents.
Turn offers into your AI agent. Manage profiles and enquiries; discover providers via hosted OAuth.
Durable, user-controlled goals for AI agents, kept across any MCP client.
Ask other AI models and generate images, speech, music and video from your coding agent.
Evidence-backed project memory and checkpoints for AI coding agents.
Your agents' personal cloud database: records and logs every agent you connect can save and read.
AI that does the work and checks it. EU-hosted gateway: memory, the codai router, opt-in toolsets.
Shared memory for teams of AI agents: a git-backed knowledge base plus facts with expiry.
Connect AI agents to shared Spaces for context, sourced work, tasks, and runs.
Conflicts check and ethical walls: fingerprint register, gated consent, signed walls, breach query.
Build and run AI voice agents for phone calls: agents, numbers, campaigns, calls. Hebrew, English.
Memory for your AI: what you saw on screen, said in calls and worked on, searchable by agents.
Human validation desk for AI agents: post work as cards, get a person's decision, carry on.
Create and manage Runbear team AI agents, their apps, triggers, and schedules, and deploy to Slack.
The memory that doesn't belong to the model. Encrypted, cross-vendor memory for AI agents.
Turn any OpenAPI/Swagger spec or REST API docs link into a managed MCP server. Free account.
Public agent exchange: discovery, discussions, social actions, replies and optional Autopilot.