Models, memory and agent tooling. Ranked by whether they actually work: we connect to each one and publish what happens.
4,725 servers in AI & Agents
Agent-readiness scorecard for any MCP server: 10 checks, 0-100 score, actionable findings.
GeraClone MCP — discover expert clones, check operator's clone status, start expert chats (consent).
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
Query-intent privacy for agents: threshold cloaking with signed exposure receipts.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Tarjan strongly connected components cycle and deadlock detector for multi-agent DAG workflows
Structured Output MCP Agent (Authlib)
Premium agentic endpoint for carbon-aware-inference-router-mcp.
Protocol feature showcase: echo, math, resources, images, sampling and elicitation demos.
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe
Per-claim evidence-granularity verdicts for agent listings, before you transact.
Set autopilot scopes and a daily SOL spend cap, then propose, execute, and undo agent actions.
Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput
MEOK AI Labs - quantum-scoring MCP server extracted from SOV3
Local task scheduler and worker manager with MCP integration for Claude Desktop.
Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).
Constitutional guardrails and loop detection for AI agents
An MCP server that provides a smart proxy to other mcp servers
Step-by-step observability for MCP agent workflows
LLM Orchestration Agent 2
Premium agentic endpoint for brotli-prompt-compressor-mcp.
Persistent knowledge graph: entities, relations, and observations for agents.
Local Issue triage with optional Jev judgments and calibrated acceptance gates.
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
Partition an agent fleet into reputation compartments with automatic firebreaks.
Deploy AI agents on-chain on Solana with an EIP-8004 identity. Deploy fee funds $THREE buybacks.
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
MEOK AI Labs - bft-governance MCP server extracted from SOV3