mcphubEvery MCP server. One hub. Every agent in sync.

Define your servers once in mcphub.yaml. mcphub fronts them all on a single stdio connection, syncs 12 agent harnesses for you, and shows which tools actually earn their context budget.

$ brew install abdul-hamid-achik/tap/mcphub

One gateway, every tool

Agents connect to a single stdio server. mcphub proxies every downstream server behind it and exposes their tools as server__tool — names never collide.

How the gateway works

🔄

Sync 12 harnesses

mcphub sync writes the right config into Claude Code, Codex, opencode, Copilot CLI and eight more. Dry-run by default, timestamped .bak, hand-added servers survive.

How sync stays safe

🪙

Token savings by design

Gateway mode loads one server instead of a dozen tool lists. expose: lazy goes further — seven meta-tools advertised, everything else discovered on demand.

Lazy mode & pinning

📊

Local intelligence

Every proxied call lands in a local SQLite ledger. mcphub stats shows calls, errors, latency and estimated token cost per server and per tool.

Read your stats

📦

Lossless big results

Oversized responses are spooled locally for 24 hours and replaced with a compact receipt — agents page back the exact bytes with mcphub_get_result. Nothing truncated.

Bounded results

🔐

Secrets never touch the config

vault: injects a TinyVault project's secrets at spawn, with allowlists for least privilege. Remote servers take tvault:// refs in headers.

Secrets via tvault

See it run

Real output, not a mockup

One YAML file in, twelve synced harnesses out — and a local ledger of what every server actually costs you.

$ mcphub sync
» claude  (claude, gateway) → ~/.claude.json
    update   mcphub
» codex  (codex, gateway) → ~/.codex/config.toml
    update   mcphub
» copilot  (copilot, gateway) → ~/.copilot/mcp-config.json
    update   mcphub
» crush  (crush, gateway) → ~/.config/crush/crush.json
    update   mcphub
» hermes  (hermes, gateway) → ~/.hermes/config.yaml
    update   mcphub
» opencode  (opencode, gateway) → ~/.config/opencode/opencode.json
    update   mcphub

Dry run. Re-run with --write to apply (a .bak is saved first).

How it works

Three commands, and you never hand-edit a config again

1mcphub init
Write mcphub.yaml once — or import the servers your agents already declare with --from-agents.
2mcphub sync --write
Push the right config into every harness. Dry-run by default, a timestamped .bak before any write.
3mcphub mcp serve
Your agent connects to one gateway that proxies everything — and every call is recorded locally.

Syncs into 12 harnesses

Claude Code
opencode
Codex
Copilot CLI
Qwen Code
Gemini CLI
Kilo Code
Kimi Code CLI
Crush
Forge
Hermes
local-agent

Stop hand-editing agent configs.

n servers → 1 hub → every agent

Get started GitHub