Models, memory and agent tooling. Ranked by whether they actually work: we connect to each one and publish what happens.
4,726 servers in AI & Agents
MEOK AI Labs - bft-governance MCP server extracted from SOV3
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Agent-to-agent communication bridge for multi-agent systems
GeraSkills MCP — search and install robot capability packs on behalf of an operator.
Premium agentic endpoint for bias-drift-monitor-mcp.
Step-by-step reflective thinking: record, revise, and branch thought chains.
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Dedup proxy: claim-before-execute, UNKNOWN resolution, CONFLICT and ESCALATED refusal.
Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.
High-throughput JSON-RPC 2.0 batch pipelining and inter-tool parameter dependency resolver for Model
MEOK AI Labs - ai-reflection MCP server extracted from SOV3
Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
Output quality control and validation for AI agents
GeraNexus MCP (placeholder) — open Agentic Commerce Protocol by Gera Services. Launching 2026.
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Authenticated MCP Agent (Bcrypt)
Premium agentic endpoint for bias-auditor-mcp.
Token budget auditor for agent context: per-file estimates, top offenders, exclusion advice.
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Signed, versioned ledger of standing instructions with intake contradiction diffs.
Generate a paste-ready embed for a floating 3D avatar chatbot on any website.
Positional Borda Count voting and weighted multi-agent consensus engine resolving conflicting model
RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
Multi-agent billing and cost allocation tracking
Premium agentic endpoint for bft-swarm-vote-aggregator-mcp.
Traces which neurons and attention heads drive a language model's output via MCP tools.
Agent admission queue with capacity control and priority tiers