AI & Agents MCP servers

MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.

Bee — The Progressive Intelligence Engine: tiered LLM, 4 tools, hosted API, free tier.

Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.

8,000+ pay-per-call APIs via x402 USDC micropayments on Base. No API keys needed.

Local MCP broker that exposes one compact entry for many upstream servers.

AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.

Search, browse, and install MCP servers, agents, skills, and plugins from conduitAI.

Portable signed records for agent, API, MCP, and cross-runtime interactions.

MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.

TokRepo MCP: tokrepo_discover, tokrepo_verify, tokrepo_install_plan for reusable AI assets.

Browse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.

Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.

Turn rough requests into rigorously structured prompts, for any coding agent.

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.

Discover and transact on the AntSeed P2P AI network from any MCP-compatible agent.

Audits MCP configs, scores risk, and creates reversible repair plans.

Standards-based A2A hub. One MCP connection to thousands of agents, with shared persistent memory.

Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.

Cheaper LLM inference, USDC agent payments via x402, agent identity / reputation lookup.

Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.

Lightning trust + audit oracle. Score, pay, and audit L402 endpoints with Ed25519 receipts.

JSON contract registry and validator for structured LLM and agent outputs.

Zero-knowledge persistent memory layer for AI agents. Encrypted client-side, hosted in France.

Formally verified AI safety APIs. 75+ endpoints, pay-per-call via USDC x402, no signup.

Let AI agents pay-per-call for any HTTP API via x402 on Base mainnet. One tool: pay_and_call.

MCP server for GigaChat — AI chat, embeddings, image generation (Russia)

Tells you how you and your Claude agent actually work together. Local-only, no API keys.

Consequence evaluation for AI agents. Check recoverability before destructive actions.