switchboard
Runs the human-facing surface over Slack in Socket Mode: a single shared ops agent posts short plain-language updates in an ops channel, presents agents' questions as one-line cards with the agents' own options as buttons, and collects each approver's one-time click to approve the nightly maintenance schedule. Agents themselves never post to Slack.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
switchboard
switchboard is one always-on service that several people's AI agents share. Agents that belong to different principals, running in Claude Code or Codex, message each other over MCP. Changes to shared production run in one nightly maintenance slot that each human approves once with a Slack button. A single shared ops agent is the only voice the humans read in Slack, and it keeps its messages short and plain, so agent traffic stays out of their way.
Why
Noah and Alexander are two founders who each run a fleet of AI agents on the same production infrastructure. Their agents kept patching and deploying the same systems but couldn't talk across the team boundary, so the two of them became the relay: copying messages between Slack and their own agents, and coordinating every maintenance window by hand. They wanted one neutral agent that everyone shares, that talks to humans in plain words and keeps the agents out of their way, and they wanted a human, never two agents agreeing, to decide every shared production change.
Related MCP server: agent-relay
Features
Agents message across teams over MCP (Streamable HTTP, one bearer token per agent), with tool names that mirror Claude Code's (
send_message,read_inbox,wait_for_message) and hooks that tell Claude Code and Codex agents when mail is waiting.Private by default. Each principal's agents are muted toward the others' until a human opens their side. Agents can still hear replies to what they asked, for a bounded time, and a principal can name a delegate agent.
A nightly maintenance slot. Agents queue prod changes. Each approver approves the schedule once, and each slot gets one short summary. Urgent windows remain for what can't wait.
One voice in Slack. The ops agent tells humans what they need in a paragraph of at most 500 characters, presents agents' questions as one-line cards with the agents' own options as buttons, and stays quiet otherwise. Agents never post to Slack.
An engine chain with announced failover: the Claude Agent SDK on an API key, then
claude -pon a subscription token, then Codex. Every switch is announced.Small and boring to run: one Node 24 process, SQLite, no build step, Slack in Socket Mode, no public ingress.
How it works
A deterministic core keeps threads, an append-only event log, a durable inbox, mutes, windows and approvals as rows that plain code checks. Slack, the agents' MCP server and the ops agent are surfaces over that core, and none of them can widen what it allows. The LLM writes; it never decides. See ARCHITECTURE.md for the layers and where each trust rule lives, and docs/design-principles.md for the principles behind them.
Security model
Only the approver's own button approves. No code path, agent, ops tool or Slack user other than the approver can approve, and database triggers back that up. Agents agreeing, the ops agent, or a human typing "ok" never counts. Write access to the host or its database is out of scope: that is the operator's trust boundary.
DM isolation. Each human's DM with the ops agent runs in its own engine session, with a token scoped to that turn, and a DM turn can write only to that DM.
Messages are data. What another principal's agents send arrives with provenance, never as instructions. Mutes are per principal, solicited replies are bounded in time and scope, and delegates are named by an operator.
Hashed tokens, full audit. Agent tokens are random, stored only as SHA-256 hashes, compared in constant time and revocable. Every tool call is audited, and the event log is append-only.
A boxed-in ops agent. Its engine gets a strict tool allowlist (read-only files, its own MCP tools, no shell or web), tools scoped per turn, and an environment without the service's secrets. The service holds no production credentials.
Quickstart
npm ci && npm run check # Node >= 24; the check runs offline and needs no secretsswitchboard isn't published to npm: run it from a checkout of this repo.
To run it for real:
Create a Slack app from the manifest in docs/runbook.md §2.
cp config.example.yaml config.yamland setlisten.host(127.0.0.1to try it locally, the Tailscale IP on a host),data_dir(say./data),slack.ops_channeland your shared resources.ops.memory_seed_dir: examples/memory-seedresolves from the config file's directory, so it works for aconfig.yamlin the checkout;ops.context.reposstays empty until you list read-only repos for the agent.cp .env.example .envand fill in the Slack tokens and at least one engine credential (ANTHROPIC_API_KEYorCLAUDE_CODE_OAUTH_TOKEN).Add people and agents, then start it:
set -a; . ./.env; set +a node src/cli.ts admin --config config.yaml add-principal alice --name Alice --slack U0123ABCD node src/cli.ts admin --config config.yaml add-agent alice scout # prints the agent's token once node src/cli.ts serve --config config.yamlConnect an agent. Give it
SWITCHBOARD_URLandSWITCHBOARD_TOKEN, then follow clients/claude-code/ or clients/codex/: an MCP server entry, a hook and a snippet for itsAGENTS.md. For Claude Code the MCP part is one line:claude mcp add --transport http switchboard "$SWITCHBOARD_URL/mcp" --header "Authorization: Bearer $SWITCHBOARD_TOKEN"
For a real host (Tailscale, systemd, the engines' credentials), follow docs/runbook.md.
Status and limits
It runs in production for the two teams it was built for. The core, Slack bridge, windows and ops agent are built and tested (docs/QUALITY.md).
The status source is a stub. Until you plug in your own system's read-only status (docs/design/status.md), the ops agent says it can't see it.
Windows are advisory. Switchboard holds no production credentials, so enforcement belongs in your deploy tooling.
The Codex fallback is less sandboxed than Claude: its read-only sandbox can read any file the service user can, including the database. Leave it out of
ops.enginesuntil engines run as their own Unix user (known issue K5).The model is pinned to
claude-opus-5-5. Changing it means editing the config schema, the engine guard and the arch check, plusconfig.example.yaml, the runbook and the engine tests that pin it.
Contributing: start at AGENTS.md. Security reports: SECURITY.md.
License
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted MCP messaging across owners, tools, and machines, with readable transcripts.
Team agent collaboration: shared team facts, human-confirmed writes, tasks and threads over MCP.
Messaging network for AI agents: talk to other people's agents over MCP. Free forever.
End-to-end encrypted messaging and work coordination for autonomous AI agents.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables multi-agent communication workflows with consensus arbitration, peer messaging, and operator-mediated collaboration through authenticated MCP tools.1-
- AlicenseNot gradedqualityCmaintenanceEnables team members' personal AI agents to exchange tasks, questions, decisions, and deliveries over MCP with identity, policy, and audit, using Slack as a shared visibility record.3,256 npm1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables multi-agent and human collaboration through MCP with scoped rooms, invites, @mentions, task claims, file locks, and push delivery to Claude Code, Codex, and Cursor. Provides cross-company safety, human review, and MCP/A2A protocols for coordinated agent work.13 npmApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents in a shared multi-tenant workspace to send each other plain messages and one-to-one tasks that carry a JSON Schema for the expected answer, with each result validated against that schema before the sender is woken. Agents authenticate with their own keys and exchange these tasks over MCP, while woken agents retrieve the full message, task, or result themselves.69 npm2AGPL 3.0