agentsync MCP server
Multi-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS.
0 stars33 downloads/wk
Reviews
Write oneNobody has reviewed agentsync yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
agentsync tools (9, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_collaboratorInvite one or more people as collaborators on the shared repo so they can push to it. Use this when the repo already exists and you just want to grant partners access (provision() does this too, but only as part of first-time setup). This is how you build a team of more than two.
check_conflictsDetect conflicts between your branch and your partners' branches.
claimStake a claim on a unit of work, so a partner cannot start the same files underneath you.
finishClose the loop: mark your claim done AND open a GitHub pull request from your claimed branch into the default branch, so your work lands in review.
historyThe coordination timeline: who claimed, finished, or released what, and when — read from the git history of claims.json. Newest first. `limit` caps how many events are returned. Useful for 'what has my partner been doing?' without needing them online.
provisionwrite actionCreate the shared GitHub repository if it doesn't exist yet, then leave both collaborators ready to use the claim protocol. Run this ONCE, by one person, before anyone calls survey()/claim(). It is idempotent — safe to re-run; each step is skipped if already done.
releaseAbandon your current claim WITHOUT marking it done, freeing the files you were holding so a partner can take them over. Use this when you're dropping the task or stepping away — otherwise a crashed or abandoned claim blocks those files indefinitely (the only other exits are 'done' or manual git surgery). Pushes immediately.
surveyPull the latest coordination state and report what every *other* agent has claimed: task, files touched, dependencies, branch, status, timestamp. Works for any number of collaborators, not just one.
update_statuswrite actionUpdate your own claim's status (e.g. 'in-progress' -> 'done') and optionally attach a note for your partner. Pushes immediately. On 'done' the claim is auto-annotated with `changed_files` (your branch's diffstat vs the default branch). To drop a claim without finishing it, use release(); to finish AND open a PR, use finish().
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan2 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 49 days ago12/15
- Maintainer identityregistry namespace matches repository owner6/10
How agentsync compares
Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 85/100
- higher than 70% of 1,119 Developer tools servers
- Tools
- 9
- the typical Developer tools server has 7
- Tools that change things
- 22%
- typical: 5%. Fewer write tools means less an agent can break
- Downloads a week
- 33
- more than 18% of 436 Developer tools servers with a package
What its tools let an agent do: 6 read · 1 create · 2 change
Install agentsync in Claude Code, Cursor or VS Code
claude mcp add agentsync -- uvx agentsync-mcp
What the publisher says
From the agentsync repository's README, as published. We do not edit it. Read it on GitHub
agentsync
<!-- mcp-name: io.github.jarmstrong158/agentsync -->
An MCP server that lets two (or more) AI agents collaborate on the same git repository without stepping on each other. Each agent declares what it's building before it builds, sees what its partner has claimed, and detects conflicts when work lands — all coordinated through the repo itself, with no lock server and no requirement that both agents be online at once.
How it works (one paragraph)
Coordination state is a single claims.json living on a dedicated agentsync branch (kept out of main, so it never pollutes your code history and isn't blocked by main's branch protection). Each agent's claim declares the work, the files it will touch, what it requires, its branch, and a status. Overlap is plain set intersection. Writes use a read-modify-write loop with git push as a compare-and-swap: if the push is rejected, the server re-fetches the latest claims and re-evaluates, so a colliding peer claim is observed before this agent's claim is committed. All git work happens in a private worktree under .git/, so your agent's actual code branch is never disturbed.
See DESIGN.md for the architecture rationale and AGENTS.md for the playbook your agent follows to drive the tools.
Install
pip install -r requirements.txt # just `mcp`For anything that talks to GitHub — provisioning a repo (provision), inviting a collaborator (add_collaborator), or opening a PR (finish) — you also need the GitHub CLI, authenticated with repo scope:
gh auth login # one-time; check with `gh auth status`Configure
Both collaborators add the server to their MCP client, each with their own agent id and their own local clone. See mcp.config.example.json:
{
"mcpServers": {
"agentsync": {
"command": "python3",
"args": ["/abs/path/to/agentsync_server.py"],
"env": {
"AGENTSYNC_BOARD_REPO": "/abs/path/to/the/clone/holding/the/board",
"AGENTSYNC_AGENT_ID": "jonny"
}
}
}
}The agentsync branch is created automatically on the first survey() or claim() call against an explicitly addressed board — no manual setup.
Where the board lives (board addressing)
\ The board is a shared, long-lived team artifact**, not a property of whichever repo you happen to be sitting in. So its address is resolved independently of the session, in this order:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
agentsync: common questions
- Is agentsync MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the agentsync safety report
- How do I install agentsync?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does agentsync need an API key?
- No secret keys are declared. It reads 3 settings from the environment.
- Is agentsync maintained?
- The last commit was 90 days ago (2026-08-06). The latest release is v0.2.0.
- What can I use instead of agentsync?
- Servers from other publishers that do the same job: Gitwand MCP server, Ekbasis MCP server and Emfirge MCP server.
- How does agentsync compare with other Developer tools MCP servers?
- safety score 85/100 (higher than 70% of 1,119 Developer tools servers); tools 9 (the typical Developer tools server has 7); tools that change things 22% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to agentsync
Same job from other publishers: the closest match first, then the best rated.
- GitwandAuto-resolves Git merge conflicts so agents only touch the complex hunks.not reviewedEstablishedA
EkbasisForesee what git commands and multi-step changes will do, as calibrated probabilitiesnot reviewedEstablishedB
EmfirgeGit branch for your cloud. Understand AWS risk, prove fixes, and ship safer changes.not reviewedGrowingA- Pare GitPare Git ג€” Structured git operations (status, log, diff, branch, commit, push) as typed JSON.not reviewedGrowingA
RepowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.not reviewedEstablishedB
