AI & ML MCP Servers

Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.

Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.

Your versioned memory across every AI tool — context maps, personal memory, and tasks over MCP.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.

Render Markdown and LLM output into accessible PDF/UA-1 PDFs. No headless Chromium.

Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.

Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.

Wake-ups, webhook inboxes, TTL memory, watches and human approval for agents. Paid per call.

Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.

Korean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas.

Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.

NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.

Multi-level reasoning MCP server with configurable depth levels

Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.

Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.

Patent search, USPTO data, patent landscape & pgvector prior-art search for agents.

Leveraged-yield router on Morpho. List strategies, simulate, and build UNSIGNED txs.

Evidence-grounded, graph-connected, correctable memory for agents.

Grounds LLMs in real Church Slavonic: Wiktionary lemmas, dual-number paradigms, transliteration.

Local-first persistent project memory for AI coding agents across MCP clients and sessions.

Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.

Search 8.5M scientific papers with LLM TLDRs, citations, linked entities, figures, and full text.

Generate 18 diagram types from structured JSON natively. Built for LLMs and agents.