AI & Agents MCP servers

Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).

Hundreds of x402-paid APIs as MCP tools, auto-discovered from Coinbase Bazaar. USDC on Base+Solana.

EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.

Search verified agents and production agent-first AbsoluteJS packages.

Verify agent actions against the system of record and get signed completion receipts.

Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.

Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools

252 AI Skills: MBTI, fact-check, deep analysis. Alipay pay-per-use. Free 10 calls/day.

Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.

Manually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB.

Run the Intelliverse platform from any agent: apps, API keys, knowledge bases, email, media, chat.

Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.

Search 17,900+ open-source AI agents by capability, ranked by GitHub traction. Free, no key.

MCP server for Callimachus: local index and search of your AI coding-agent threads

Local mandate gate and proof trail for AI agents that take consequential actions.

Circulara Observe MCP plugin - meters your AI agents' token spend and carbon, free tier.

Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.

Your project's decision history for agents: decisions, dead-ends, constraints - queryable, local.

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.

Webhook & callback layer for AI agents: create a URL, wait_for_callback, and verify over MCP.

Call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key

AI safety middleware — detects self-harm and criminal intent in LLM prompts.

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

Model Context Protocol server for AgentRAM. Persistent memory for AI agents.

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients

Single MCP hub: discover, add, audit, and govern MCP servers across every AI client.