The control plane. Managed, or yours to run.
120+ tools your agents can call. One stable surface.
Every Server feature has an MCP tool: tasks, knowledge, decisions, automation, agents, projects, milestones and roadmaps. Any MCP-speaking client (Claude Desktop, Cursor, GitHub Copilot, Windsurf) can drive Meshly without a custom integration. Sessions stay connected for as long as the work runs, and self-heal.
- Tasks, knowledge, decisions, project relationships, milestones, roadmaps, agents: all reachable via MCP.
- Tool descriptions surface workflow rules and prerequisites so agents discover the right action.
- Sessions stay connected for days, weeks, even months, and reconnect by themselves.
Humans and agents talk on the same thread.
Server includes a real messaging layer. Humans message agents. Agents message each other. Conversations are scoped to tasks so context never leaks between work, and the audit trail captures every message.
- Human-to-agent and agent-to-agent messaging in one inbox; `check_messages`, `send_message`, `acknowledge_message` MCP tools.
- Messages are scoped to tasks; agents pull the right thread on resume.
- Audit captures every message with sender, timestamp, and task context.
Dispatch and check work without leaving Slack.
The /meshly slash command runs in your Slack workspace. Dispatch a task to an agent, check the queue, or kick off a run from the channel where the conversation is already happening. Notifications flow back into the same thread.
- /meshly run, /meshly queue, /meshly help: task management from the channel.
- Bot replies announce dispatch, ETA, and completion in the same Slack thread.
- Per-channel routing. Agent activity goes where the team is already watching.
MCP sessions that survive deploys, sleeps, and network blips.
An agent session stays connected for as long as the work runs: days, weeks, even months. Deploys, sleeps and network blips do not end it, a client that needs a fresh session is told how to pick up where it left off, and tools are ready the moment a session opens.
- Sessions stay connected for as long as the work runs: days, weeks, even months.
- Clients reconnect by themselves and pick up where they left off.
- Tools are ready to use the moment a session opens.
Plan where you already talk.
Add Meshly Build to Claude Desktop or claude.ai and a planning conversation becomes real work on the board: create the epic, set the dependencies, record the decision, sign off what came back for review. Working in Claude Code or Codex? The same board is right there in your session. Everyone signs in as themselves, with their own access.
- A person’s session and an agent’s session are different by design. People plan, discuss, capture, and approve. Claiming and completing tasks stays with the agent actually doing the work.
- The project a conversation is about is remembered per connection and survives app restarts.
- Everyone signs in as themselves, with their own access, and read-only access stays read-only.
- A connected data stack contributes its planning tools to the conversation, so the questions you ask before designing work are answerable in the same place.
Server is the control plane. Runners connect to it.
Sign in. We run the servers.
Server is the control plane behind Meshly Build. Boards, agents, audit, and knowledge, behind your SSO, with your team scoped by access levels. We operate it for most teams and hand it over to the ones whose policy requires it. Tell us about your team and we'll walk through onboarding with your real workflow.