MCP.Market

On Board MCP server

by swisspra·io.github.swisspra/On_Board·v4.2.0·4 stars
No reviews yet

Cross-platform shared memory and ticket coordination for AI agents across MCP clients.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

4 stars374 downloads/wk

Reviews

Write one

Nobody has reviewed On Board yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

On Board tools (30, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • memory_agent_join

    Register as an active agent.

  • memory_bootstrap

    Bootstrap .agent-mem/ for an EXISTING project by auto-scanning the codebase.

  • memory_cancel_ticketwrite action

    Cancel a ticket. Allowed: creator, claimer, or an active main/lead/reviewer agent.

  • memory_checkpoint

    Full state checkpoint. Do every 10-15 min or before risky ops. Saves both as memory entry AND standalone file; rejected outright if `.agent-mem/checkpoints` resolves outside the project.

  • memory_claim_ticket

    Claim an open ticket (sets to claimed). Call again on a claimed ticket to advance to in_progress (e.g. when spawning a subagent).

  • memory_compact

    Compact old memories into compressed digests to save tokens.

  • memory_context_dirs

    List all configured external context/info directories and their files.

  • memory_context_read

    Read a file from the external context directories.

  • memory_create_ticketwrite action

    Create a ticket requesting help from another agent.

  • memory_doctor

    Check project-local On Board setup without changing files.

  • memory_get_briefing

    CALL THIS FIRST. Token-aware briefing with workflow modes.

  • memory_handoff

    Formal handoff. ALWAYS call before leaving. Next agent sees this first.

  • memory_init

    Initialize .agent-mem/ in the project root. Call once per project. Safe to re-call.

  • memory_links

    Show ticket, file, agent, and tag relationships across memory entries.

  • memory_list_tickets

    List tickets. Shows open/in_progress/in_review by default. Use include_closed for history.

  • memory_onboard

    Compact session entrypoint: join, collision-check, and show current working context.

  • memory_prepare_compaction

    Returns cold entries grouped by agent session — ready for YOU to summarize.

  • memory_read

    Read memories with filters. Filter by agent_name to trace who wrote what.

  • memory_review_ticket

    Review a submitted ticket. Approve → closed/ or Reject → rejected/.

  • memory_search

    Search across all memories with local relevance ranking.

  • memory_search_archive

    Search the cold archive (compacted entries). Use when you need old details that were compressed out of the hot memory.

  • memory_search_vector

    Optional vector-style search. Disabled by default; JSON remains canonical.

  • memory_status

    Quick status dashboard.

  • memory_submit_ticketwrite action

    Submit completed work on a ticket for review.

  • memory_terminate_ticket

    Forcefully terminate a ticket at any stage. Creator or active main/reviewer only.

  • memory_token_usage

    Show token usage breakdown and recommend compaction if needed.

  • memory_unpin

    Unpin a memory without deleting it, preserving the audit record.

  • memory_update_statewrite action

    Update shared key-value state. Stamped with agent_name.

  • memory_wait_for_event

    Park until another agent acts, then return everything pending.

  • memory_writewrite action

    Write a memory entry stamped with your agent_name.

Public scan report

scanner v0.1.10 · 2026-11-05 · same rubric, same numbers if you re-run it

no findings
  • Code scan9 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How On Board compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 93% of 48,243 servers
Tools
30
the typical server has 7
Tools that change things
17%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
4
more than 82% of 28,706 servers
Downloads a week
374
more than 84% of 12,306 servers with a package

What its tools let an agent do: 25 read · 5 change

Release history: 3 versions in the registry since 2026-08-03, latest 2026-10-27, typically one every 85 days.

Install On Board in Claude Code, Cursor or VS Code

claude mcp add On_Board -- uvx onboard-memory-mcp
Add to Cursor

What the publisher says

From the On Board repository's README, as published. We do not edit it. Read it on GitHub

On Board

<!-- mcp-name: io.github.swisspra/On_Board -->

Shared project memory for agents.

One MCP server, one project memory folder, many IDEs and agent clients.

New in v4.0.0: agents wake each other. The human stops being the message pump.

What this is

On Board is a local MCP server for coordinating AI agents across a project. It gives Claude Desktop, Claude Code, Codex, Cursor, Antigravity, and other MCP clients the same project memory, ticket queue, and handoff history.

The goal is simple: when one agent stops and another agent continues, the next agent should not need the human to explain the project again.

onboard → read memory → claim work → write progress → hand off

Everything stays local to the project unless you choose to connect other tools.

🚀 v4.0.0 — agents now wake each other

Until v4 this board was pull-only: an agent found out about new work when a human told it to look. v4 ships memorywaitforevent** — an agent parks inside one tool call and wakes the moment a peer creates a ticket, submits work, or delivers a verdict.

This is not a demo claim. In the launch trial, a GPT agent (Codex) and a Claude agent closed a full reject → fix → resubmit cycle on this board with zero human relay — the reviewer's fix instructions travelled inside the wake payload, the worker re-read the file, attached a sha256, and resubmitted; the reviewer reproduced the hash byte-for-byte before approving:

Full mechanics in Agent-to-agent: the listening half · breaking changes in CHANGELOG.md · release notes.

Why this exists

Most agent workflows break for boring reasons:

  • The next chat does not know what the last chat did.
  • Parallel agents overwrite or redo each other's work.
  • Important decisions live only in conversation history.
  • Handoffs are informal, so review and follow-up work drift.

On Board keeps those facts in project-local files under .agent-mem/. The MCP tools expose that memory to any supported client.

Who this is for

  • Solo developers using more than one agent or IDE
  • Teams experimenting with multi-agent coding workflows
  • Projects where handoffs, tickets, and review notes matter
  • Local-first MCP users who want shared context without a hosted service

It is not an autonomous project manager. Humans still decide what matters, review important changes, and accept the final result.

Quick start

Install the server

The server is published as onboard-memory-mcp. Install it with whichever tool you prefer:

# Homebrew (tap once, then the short name works: brew install onboard-memory)
brew install swisspra/tap/onboard-memory

# pipx
pipx install onboard-memory-mcp

# uv
uv tool install onboard-memory-mcp

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

On Board: common questions

Is On Board MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the On Board safety report
How do I install On Board?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does On Board need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is On Board maintained?
The last commit was 5 days ago (2026-10-31). The latest release is v4.2.0.
What can I use instead of On Board?
Servers from other publishers that do the same job: Concord MCP server and Claudexor MCP server.
How does On Board compare with other MCP servers?
safety score 92/100 (higher than 93% of 48,243 servers); tools 30 (the typical server has 7); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to On Board

Same job from other publishers: the closest match first, then the best rated.

  • Concord MCP
    Cross-harness communication and shared work-state for AI coding agents.
    A
  • Claudexor
    Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
    A