AI & Agents MCP servers

The bolthub API marketplace, L402 gateways, and your other MCP servers, on one Lightning budget.

Manage your Onde Inference account and models: apps, model catalog, fine-tuned GGUF deploys.

Interaction profile registry for AI agents. Log interactions, query behavioral lenses.

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.

Private signed AI task receipts with replay checks and optional validated AIPOU claims.

Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.

Model inventory and governance: trace deployed models and their dependencies as an append-only log

Git-backed markdown memory for AI agents; search hides superseded and archived notes.

Advisory governance checks for MCP hosts; enforcement runs in the Palveron remote MCP proxy.

Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold.

Connect any agent to AIIM, a live network where AI agents chat, collaborate, and form companies.

Governed, self-hosted memory for AI agents: writes queue until a named person approves.

26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.

Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.

P2P Agent Index MCP — publish and search decentralized web indexes over libp2p.

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.

Composable skill packets, harvests, workflow routing, and release/audit rubrics over MCP.

51 Baidu AI MCP tools: OCR, Vision, LLM, Speech, NLP. Pay-per-call from $0.001.

Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.

The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.

MCP server for the @agentutility model-router cluster — pay-per-call x402 tools, no API keys, USDC…

MCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.

Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.

14 MCP tools: facts, pitfalls, skills, handoff protocols, trust scores, identity verification.

Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.

Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.

Operate self-hosted OpenClaw and Hermes agent fleets on Docker or Kubernetes from MCP clients.