Agentsync (Remote) MCP Server

Self-hosted Cloudflare Worker remote transport for agentsync (streamable-HTTP).

Local serverstdioPython

What is the Agentsync (Remote) MCP server?

Self-hosted Cloudflare Worker remote transport for agentsync (streamable-HTTP). Exposed over MCP by the agentsync (remote) mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

A Cloudflare Worker MCP server that makes claude.ai on your phone a peer in the agentsync coordination mesh — the same claims.json, the same agentsync branch, the same overlap and compare-and-swap rules as local agentsync, with no git and no local clone.

  • URLs get recorded in places request bodies never do. — Browser history,
  • The Worker itself does not log it. — Every log line records the route as
  • A leaked token makes the holder a full peer in your mesh — — able to claim,

Its toolset

Everything the assistant can do here goes through one of these:

  • Fail — closed auth is tested** — wrong token, unset AUTH_TOKEN, and non-/mcp
  • survey — The whole board: every peer's claim, your conflicts, the mailbox
  • claim — Claim work; blocked if it overlaps an active peer (CAS-safe)
  • check_conflicts — Re-check your claim against peers, optionally on one branch
  • update_status — Move your claim through planning / in-progress / done
  • release — Mark your claim done (done never blocks peers)
  • history — Recent commits on the coordination branch (local + remote interleaved)
  • mailbox — Human-in-the-loop notes: ask from the desktop, answer from the phone
  • Variable — Set it to
  • REPOYour coordination repo, as owner/name (the repo whose agentsync branch will hold claims.json). This is the one you must change
  • AGENT_ID — Leave as jonny-mobile, or pick an id for this peer
  • BRANCH — Leave as agentsync unless you want a different coordination branch

Configuration

You will need 3 environment variables: AGENT_ID, CLAIMS_PATH, AUTH_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

The server ships on npm as wrangler, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agentsync (Remote)'s toolset — Fail, survey, claim and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jarmstrong158; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agentsync (Remote).
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agentsync (remote) mcp server does with a few real requests.

Available tools

ToolWhat it does
Failclosed auth is tested** — wrong token, unset AUTH_TOKEN, and non-/mcp
surveyThe whole board: every peer's claim, your conflicts, the mailbox.
claimClaim work; blocked if it overlaps an active peer (CAS-safe).
check_conflictsRe-check your claim against peers, optionally on one branch.
update_statusMove your claim through planning / in-progress / done.
releaseMark your claim done (done never blocks peers).
historyRecent commits on the coordination branch (local + remote interleaved).
mailboxHuman-in-the-loop notes: ask from the desktop, answer from the phone.
VariableSet it to
REPO**Your** coordination repo, as owner/name (the repo whose agentsync branch will hold claims.json). This is the one you must change.
AGENT_IDLeave as jonny-mobile, or pick an id for this peer.
BRANCHLeave as agentsync unless you want a different coordination branch.
CLAIMS_PATHLeave as claims.json.
SecretValue

How to install the Agentsync (Remote) MCP server

{
  "mcpServers": {
    "agentsync-remote": {
      "command": "npx",
      "args": ["-y", "wrangler"],
      "env": {
        "AGENT_ID": "your-value",
        "CLAIMS_PATH": "your-value",
        "AUTH_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
AGENT_IDConfiguration value read at startup.Optional
CLAIMS_PATHFilesystem location the server is allowed to use.Optional
AUTH_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Agentsync (Remote) to Fail.
  • Use Agentsync (Remote) to survey.
  • Use Agentsync (Remote) to claim.

Frequently asked questions

It connects Agentsync (Remote) to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Fail, survey, claim, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentsync (Remote) directly.