Network Ai MCP Server

AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex

Remote serverstreamable-httpPython

What is the Network Ai MCP server?

AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS. Exposed over MCP by the network ai mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

If Network-AI is useful to you, consider giving it a star ⭐ — it helps others find the project.

Its toolset

Everything the assistant can do here goes through one of these:

  • Model — interaction lifecycle governance (v5.13)** — GovernedModelGateway absorbs the model refusal → fallback → billing chain (cross-model fallback
  • Per-sub — agent fallback** — FanOutFanIn steps and TeamRunner tasks each carry their own fallback agent and per-request retry budget (RetryBudget), because a
  • context_pack — token-budgeted, relevance-ranked context brief for a task (use instead of dumping the whole board into your window)
  • blackboard_search — ranked top-K search over blackboard entries (semantic when an embedder is wired, lexical otherwise)
  • audit_query — query the append-only audit log
  • fsm_transition — write FSM state transitions to the blackboard
  • Risk — Status
  • Problem — How Network-AI solves it
  • File — Role

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Network Ai's toolset — Model, Per-sub, context_pack and 6 more — is a fair guide to whether it matches your workflow. It is maintained by jovansapfioneer; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Network Ai.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the network ai mcp server does with a few real requests.

Available tools

ToolWhat it does
Modelinteraction lifecycle governance (v5.13)** — GovernedModelGateway absorbs the model refusal → fallback → billing chain (cross-model fallback, fallback-credit repricing, effort governance, thinking-block handoff) behind o
Per-subagent fallback** — FanOutFanIn steps and TeamRunner tasks each carry their own fallback agent and per-request retry budget (RetryBudget), because a turn can refuse independently across an agent and its sub-agents.
context_packtoken-budgeted, relevance-ranked context brief for a task (use instead of dumping the whole board into your window)
blackboard_searchranked top-K search over blackboard entries (semantic when an embedder is wired, lexical otherwise)
audit_queryquery the append-only audit log
fsm_transitionwrite FSM state transitions to the blackboard
RiskStatus
ProblemHow Network-AI solves it
FileRole

How to install the Network Ai MCP server

{
  "mcpServers": {
    "network-ai": {
      "command": "npx",
      "args": ["-y", "network-ai-server"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Network Ai to Model.
  • Use Network Ai to Per-sub.
  • Use Network Ai to context pack.

Frequently asked questions

It connects Network Ai to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (Model, Per-sub, context_pack, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Network Ai directly.