Shared versioned state for multi-agent AI workflows
Connect Agenthold to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Shared versioned state for multi-agent AI workflows. The agenthold mcp server is what makes that connection.
When two agents update the same value, the second write quietly destroys the first. No error, no exception, just wrong data and a system that keeps running. agenthold is an MCP server that gives agents shared, versioned state with conflict detection built in. Think of it as git for your agents' working memory.
The server ships on PyPI as agenthold, 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.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
agenthold_register — Register yourself and receive a unique agent ID. Must be called once before using agenthold_claim or agenthold_releaseagenthold_claim — Claim exclusive access to a resource before modifying it. Requires a registered agent_idagenthold_release — Release your claim with an explicit outcome describing what you did. The outcome is preserved in the free-state record and shown to the next claimantagenthold_status — Check whether a resource is available or currently claimed. Does not require registrationagenthold_wait — Wait for a claimed resource to become available. Blocks the agent turn until the holder releases, or the timeout expiresAuthentication — To require a bearer token on every HTTP request, set one or more tokens. Prefer the environment variable so the token doesn't appear in processConfiguration is passed through the environment: AGENTHOLD_AUTH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agenthold's toolset — agenthold_register, agenthold_claim, agenthold_release and 3 more — is a fair guide to whether it matches your workflow. It is maintained by edobusy; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| agenthold_register | Register yourself and receive a unique agent ID. Must be called once before using agenthold_claim or agenthold_release. |
| agenthold_claim | Claim exclusive access to a resource before modifying it. Requires a registered agent_id. |
| agenthold_release | Release your claim with an explicit outcome describing what you did. The outcome is preserved in the free-state record and shown to the next claimant so they don't act on stale assumptions. Requires a registered agent_id |
| agenthold_status | Check whether a resource is available or currently claimed. Does not require registration. |
| agenthold_wait | Wait for a claimed resource to become available. Blocks the agent turn until the holder releases, or the timeout expires. |
| Authentication | To require a bearer token on every HTTP request, set one or more tokens. Prefer the environment variable so the token doesn't appear in process listings: |
### 2. Add to your MCP client config
```json
{
"mcpServers": {
"agenthold": {
"command": "agenthold",
"args": ["--db", "/path/to/state.db"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AGENTHOLD_AUTH_TOKEN | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.