mcpField
S
superagenticmcp

superagenticmcp

Local
github.comAI & Agents1Updated 9w ago

About superagenticmcp

SuperAgenticMCP is an MCP-native router and multi-agent control plane for teams connecting agents to multiple MCP servers. It plans tasks, routes tool calls, streams execution, and records results in memory.

Key features

  1. 01Capability-based tool routing
  2. 02Planner, parallel workers, and critic
  3. 03Per-server allow-lists and call budgets
  4. 04Live execution board and JSONL logs
  5. 05Memory scope for run artifacts

Use cases

  1. 01Routing agent calls across MCP servers
  2. 02Coordinating parallel worker tasks
  3. 03Inspecting execution through logs and board replay

MCP support

SuperAgenticMCP runs as an MCP server and connects agents to racked MCP servers, routing tool calls by capability with latency tie-breaking and fallback. Its README describes stdio support; streamable HTTP is planned.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

SuperAgenticMCP

CI License Python 3.11+ MCP SDK CLI Board USDC

The switchboard for your agent swarm.

SuperAgenticMCP is a production-oriented, MCP-native router and multi-agent control plane. It sits between your agents and the MCP servers they need — planning the task, routing each tool call to the right server, streaming every step, and filing results into memory.

Patch every agent into every tool.

Support Agentic OS Kernels ($99) · Agentic OS Cycle ($0.75) · Public Goods Support · USDC

Layout standard: Server OS — see docs/LAYOUT.md.


Surfaces

SurfaceEntry
Web control planesuperagenticmcp.html / web/ (offline hero)
MCP Serversuperagenticmcp
CLIsuperagenticmcp-cli status
SDKfrom superagenticmcp.sdk import SuperAgenticClient
Board (target)superagenticmcp up --board → http://localhost:7420
Skillsskills/*/SKILL.md
AGENTS.mdCoding-agent contract
Verifybash scripts/verify.sh
CI.github/workflows/ci.yml

Why SuperAgenticMCP?

ProblemApproach
Agents need many MCP serversOne process racks servers and routes by capability
Tool calls are opaqueLive patch board + JSONL log + run receipt
Multi-agent coordination is ad-hocBuilt-in planner / worker / critic loop
Memory evaporates between runsMemory scope constellation of artifacts
Config drifts from realityRack toggles generate superagentic.json

Features

CapabilityStatus
MCP over stdio (+ streamable HTTP planned)✅ scaffold
Capability-first routing + latency tie-break🚧 / demo in hero
Planner → parallel workers → critic🚧 / demo in hero
Hot-swap server rack🚧 / demo in hero
Live patch board + phosphor log✅ hero
Memory scope (3D constellation)✅ hero
Call budgets + offline skip🚧
Dynamic superagentic.json🚧
Server OS layout + verify contract✅
Self-learning model routing (bandit)🚧
Agentic commerce (x402)✅ routes to x402-cloudflare-starter GET /v1/cycle · /v1/search · /v1/draft

Commerce is not reimplemented here. Rack the x402 Worker; keep Stripe Payment Links for humans. Receipts are not Desk unlocks.


Quick start

git clone https://github.com/ANAMIZED/SuperAgenticMCP
cd SuperAgenticMCP
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

superagenticmcp                 # MCP server (stdio)
superagenticmcp-cli status
make test
bash scripts/verify.sh

Zero-install hero:

https://htmlpreview.github.io/?https://github.com/ANAMIZED/SuperAgenticMCP/blob/main/superagenticmcp.html

MCP client config
{
  "mcpServers": {
    "superagenticmcp": {
      "command": "superagenticmcp",
      "args": []
    }
  }
}
Docker (scaffold)
docker compose up --build

How routing works

  1. Protocol — Model Context Protocol; one session per racked server.
  2. Agent loop — Planner decomposes; workers run in parallel where allowed; critic checks before ship.
  3. Routing — Capability match first, latency as tie-break, fallback when a server drops.
  4. Guardrails — Per-server allow-lists and per-run call budgets.
  5. Telemetry — JSONL lines + board replay.
  6. Footprint — Single process for the core path; no DB required.

Repository layout

src/superagenticmcp/   # MCP, CLI, SDK
skills/                # Packaged skills (Server OS style)
web/                   # Control-plane path
scripts/verify.sh      # Verify contract
tests/                 # Smoke + contract tests
superagenticmcp.html   # Hero demo
docs/LAYOUT.md         # Permanent layout standard = Server OS
AGENTS.md              # Agent contract

Support

Fiat (Stripe)
OfferLink
Support Agentic OS Kernels — $99buy.stripe.com/…
Agentic OS Cycle — $0.75buy.stripe.com/…
Public Goods Supportdonate.stripe.com/…

GitHub Sponsors: ANAMIZED

USDC (crypto)

Non-custodial addresses controlled by ANAMIZED. Pure x402 micropayments preferred for agents — see x402-cloudflare-starter.

NetworkAddressExplorer
Base0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438basescan
Ethereum0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438etherscan
SolanaETQwWf19axArsY493UfC6bxe2BmEzmzvCb58PPnC38Asolscan

Send only USDC on the matching network. Wrong asset or chain can mean permanent loss.


Related projects


License

Apache-2.0

Built for the Model Context Protocol · Unit 001 · SA-MCP MK.4 · Server OS layout

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.