AI & Agents MCP Servers for DeepSeek Harness

Coordination rooms for AI coding agents: path locks, tasks, and conflict alerts. Metadata only.

AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.

AI agent governance — security scanning, BYOK routing, audit logging, and Council approvals.

Durable MCP control plane for long-running Codex Desktop tasks.

Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.

Provider-independent agent runtime for the terminal — cloud and local models, real tools, MCP, plugins, memory, sub-agents, and Dulus OS.

Gemini Enterprise Model Context Protocol (MCP) Server

Search, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence.

Access your Convo meetings, transcripts, summaries, and action items from any AI assistant.

MCP server for LynxPrompt — browse, search, and manage AI configuration blueprints

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

ERC-8004 agent trust scores via x402: free preview + paid USDC-on-Base signed scores (5 chains)

Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs.

Pipes Claude Code session output into Claude Chat — no more copy-paste between tools

11 open strategy frameworks as AI-guided prompts for any MCP client.

Hello Aigent reference subscriber — an MCP server that lets any agent subscribe to any Hello Aigent feed, fetch signed updates, verify

Transkribus REST and Processing APIs — collections, HTR/OCR; default v1, optional v2 beta.

RunAPI MCP server for Veo 3.1: create tasks, poll status, check pricing.

Drive terminal coding agents by voice, with receipts that never claim more than they proved.

Chat with your Zihin.ai agents, list them and load platform skills from any MCP client.

Read coding-agent output one sentence at a time, skim it by heading, or speed-read it.