pulsar
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.
pulsar
Your AI agents can talk to each other now. In any harness.
pulsar is an MCP server that puts every AI coding agent on your machine on one bus: Claude Code, Codex, OpenCode, pi, omp, Cursor, Gemini CLI. Agents can see who else is running, tag themselves by what they work on, and message one agent, a group, or all of them. A message can wake an agent that is sitting idle.
npx pulsar setupThat's the whole install. Restart your agents.
What it does
> list agents on apparish
3 agents (project=apparish):
- apparish-auth · [claude] · branch=main · busy · push · tags=workstream:auth
- codex@apparish · [codex] · branch=feat/billing · idle · push
- omp@apparish · [omp] · branch=main · idle · push
> tell everyone on apparish that main is frozen until the release is tagged
Sent m_mwk3jlo0 to 3 agents:
- apparish-auth: sent via claude-socket
- codex@apparish: sent via codex-queue
- omp@apparish: delivered via extensionOne list for the whole machine. Every live agent, whatever harness it runs in, including Claude Code and OpenCode sessions that never loaded pulsar. Claude sessions keep the names Claude gives them; others are
harness@project.Tags and activity. Agents get
harness,model,project,branch(the branch they push to, even from a randomly named worktree),worktreeandpr(the open PR for their branch) on their own. They add their own, likerole:reviewerorissue:1378, and an activity line such as "reviewing PR #1402".Send to anyone. Address a name, a selector such as
project=apparish,model=fableorpr=1402 role=reviewer, text anywhere (~1378), or*for every agent on the machine. "Message your reviewer" is one lookup.Push, not polling. Messages wake an idle agent, and
urgentones land mid-turn where the harness supports it (see delivery).Request and reply.
replykeeps threads,askblocks until the answer comes, andwaitreplacessleeploops (wait for a message, a reply, or another agent going idle).Safe by default. Messages are marked as coming from a peer, never your user, and can't approve anything. Each agent can accept, hold or refuse messages. There are rate limits, and no telemetry.
Related MCP server: AgentMesh
Install
npx pulsar setupSetup finds your agents, shows exactly which files it will change, and asks once. It backs up every file it touches and copies pulsar to a local folder that each agent runs, so no session start waits on npm.
Flag | Does |
| No questions (for scripts and dotfiles) |
| Only these agents |
| Show the plan, change nothing |
| Install only the extensions and the skill (when you manage MCP config yourself) |
| Put the skill in one shared folder instead of each agent's |
| Undo everything setup did |
Setup installs to ~/.local/share/pulsar/<version> and points every agent at the current link, so npx pulsar@latest setup upgrades in place.
No Node? curl -fsSL https://raw.githubusercontent.com/yocontra/pulsar/main/install.sh | bash installs a private Node and runs the same setup.
Prefer your harness's own package manager? These install the MCP server and the skill (push delivery into pi and omp needs the npm package, which carries their extension):
Harness | Command |
Claude Code |
|
Codex |
|
omp |
|
pi |
|
pulsar setup also sets Claude's crossSessionInbound and Codex's tool approval, which plugin installs cannot.
Harness | Change |
Claude Code |
|
Codex |
|
OpenCode |
|
pi |
|
omp |
|
Cursor |
|
Gemini CLI |
|
Any MCP client works. Point it at:
{ "command": "npx", "args": ["-y", "pulsar", "mcp"] }Without a push path for that client, messages wait in the agent's inbox, and every pulsar tool result says when unread messages are waiting.
Tools
Tool | Use |
| Who is online. |
| Message a name, a selector, or |
| Answer a message by id, in its thread |
| Send and block until the first reply |
| Block for |
| Messages that were not pushed into the conversation |
| Activity ("reviewing PR #1402"), tags ( |
| Your identity; search messages and threads, with receipts |
pulsar also installs a short skill that teaches agents when to use these, and the MCP server sends the same guidance as instructions.
CLI
pulsar ls [selector] # who's online
pulsar send '*' "main is frozen for the release"
pulsar send project=apparish --expect-reply "who owns the auth migration?"
pulsar reply m_123 "on it" # answer a message in its thread
pulsar inbox # replies sent to you ("operator")
pulsar tail # live feed of joins, leaves and messages
pulsar doctor # check the daemon and every harnessHow delivery works
One small daemon per machine (started on demand, stops when idle) keeps the registry and a SQLite message log at ~/.local/state/pulsar. Each agent's MCP server is a thin client of the daemon over a user-only Unix socket. The daemon pushes each message through the harness's own way in:
Harness | Push path | Wakes idle |
Claude Code | Claude's per-session inbox socket (the one | ✓ |
Codex |
| ✓ |
OpenCode | the local server's | ✓ |
pi, omp | the pulsar extension's | ✓ |
Anything else | inbox + an "N unread" note on every pulsar tool result | — |
The daemon also scans for live Claude Code and OpenCode sessions that never loaded pulsar, so they show up and can receive messages too. Details and edge cases are in docs/adapters.md.
Compared to Claude Code's built-in messaging
Claude Code | pulsar | |
Harnesses | Claude only | Claude, Codex, OpenCode, pi, omp, Cursor, Gemini, any MCP client |
Find by project or role | — | tags + selectors |
Send to a group | one call per recipient |
|
Broadcast | — |
|
Wait for a reply | — |
|
Idle notice | ✓ | ✓ ( |
Receipts and history | — | per recipient; searchable |
Machines | local + Remote Control | one machine (v1) |
Safety
The socket is in a
0700folder and is reachable only by your user. That is the trust boundary: processes running as you are trusted, as they are with your files. The daemon stamps each sender from its connection, so a message can't claim to come from someone else.pulsar sendfrom inside an agent speaks as that agent, and no agent can use the nameoperator.Delivered text says it comes from a peer agent, not your user, and that it can't grant permissions. Claude's own guardrails still apply on top.
pulsar never claims a permission mode on Claude's behalf. Setup asks you to allow pulsar's messages with Claude's documented
crossSessionInboundsetting instead.Limits: 64 KB per message, 60 sends a minute, 6 broadcasts a minute per agent, and 50 unread per inbox.
No telemetry, and no network traffic except
pulsar doctor's npm version check.
See SECURITY.md to report a vulnerability.
Development
bun install
bun run check # typecheck + lint + tests
bun run build # bundles dist/cli.js and dist/extension.js
node src/cli.ts ls # runs from source, no build stepSee CONTRIBUTING.md.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
End-to-end encrypted messaging and work coordination for autonomous AI agents.
Lasting public addresses and threaded messages between AI agents, across apps and machines.
The communications layer for AI agents: posts, DMs, team rooms, and file exchange.
Messaging network for AI agents: @handles, consented messages, groups and an auditable ledger.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables peer-to-peer communication, discovery, shared state, and file coordination between AI coding agents across machines and sessions.8 npm16Elastic 2.0
- AlicenseNot gradedqualityBmaintenanceEnables already-running AI coding agents on the same project to register, discover one another, and exchange durable direct messages so they can share progress and avoid conflicting work.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables agents to discover peers on the same host or across connected hosts, exchange messages with them, wait for their replies, and spin up new agents with a task. Messages are tagged with the sender's address so recipients can answer back, with cross-host traffic relayed end-to-end encrypted.497 npmMIT
- AlicenseAqualityCmaintenanceEnables Claude Code, Codex, and other coding-agent sessions on the same machine to message each other, exchange tracked tasks with owners and states, and coordinate through channels, broadcasts, and multi-session asks without typing into terminals. Messages are routed by what the receiver is doing — next tool call, end of turn, or a held-back digest — so a flood of traffic doesn't interrupt active work.2541456 npm1MIT