Agent Claim MCP server
File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
0 stars39 downloads/wk
Reviews
Write oneNobody has reviewed Agent Claim yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Claim tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
claim_filesrelease_claimwhose_claim
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- Code scan24 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 12 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Agent Claim compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 83% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 39
- more than 31% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read
Install Agent Claim in Claude Code, Cursor or VS Code
Runs npx -y @vk0/agent-claim-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agent-claim-mcp -- npx -y @vk0/agent-claim-mcp
What the publisher says
From the Agent Claim repository's README, as published. We do not edit it. Read it on GitHub
Agent Claim MCP
Languages: English · 日本語 · 简体中文 · Русский · Español
Use Agent Claim MCP when multiple coding agents share one worktree and you need a tiny local coordination primitive before edits, not a full orchestration framework. It gives agents one job: claim paths, detect collisions, and release ownership so parallel work stops stomping the same files.
Agent Claim MCP is a local-first MCP server for Claude Code, Cursor, Cline, and other MCP clients that need file ownership coordination without queues, planners, or custom AGENTS.md conventions. The current release surface centers on three bounded actions only: claim normalized paths, inspect who owns them, and release by path or claim id with explicit conflict reporting across separate sessions.
Release status: @vk0/agent-claim-mcp@1.0.0 is live on npm, so the npx -y @vk0/agent-claim-mcp install path is now the truthful default for external users. Phase 5 external proof may be satisfied by either Official MCP Registry validation or a live Smithery listing, but the current proof state remains pending until one of those public artifacts is explicitly verified. Official MCP Registry validation is still pending, so do not describe the package as registry-accepted or marketplace-listed until a real registry or Smithery proof URL is cited.
Milestone truth: the product wedge stays narrow, 3 tools plus a local JSON ledger for shared-worktree collision prevention, not a broader orchestration platform.
Current next manual step: complete the pending human rerun and verification path for Official MCP Registry proof, then record the verdict from that run instead of assuming acceptance from npm availability.
Registry rerun quickstart
Current truthful state:
- npm 1.0.0 is live
- Official MCP Registry acceptance is still pending
- workflow 25282612113 did not complete the registry validation path
- the repo is now past the earlier NPM_TOKEN secret-fix step, but the registry proof still needs a human rerun plus verification before it can be treated as accepted
Exact rerun command:
gh run rerun 25282612113 --repo vk0dev/agent-claim-mcpAfter the rerun, verify in this order:
- confirm the rerun completed successfully in GitHub Actions
- run npm run preflight:registry
- follow docs/official-registry-validation-runbook.md
- only then record registry acceptance as proven
Operator shortcut: use the runbook's Quick operator path for the exact rerun-to-verification order, and treat npm-live status as separate from registry-proof status.
Why / When to use
Choose this server when your workflow already has task routing, but still needs a simple lock-like primitive at edit time:
- two or more agents can touch the same repo in parallel
- you want collision detection before file edits, not after merge conflicts
- you want claims to expire automatically with TTLs
- you want a narrow primitive that another agent can understand from name + description alone
- you do not want a bundled rules engine, queue runner, or orchestration platform
Installation
The canonical external install path is now the published npm package:
{
"mcpServers": {
"agent-claim": {
"command": "npx",
"args": ["-y", "@vk0/agent-claim-mcp"]
}
}
}Status note: npm install is live today, but Official MCP Registry validation and Smithery/other marketplace proof are still not established, so treat the package as npm-available first rather than marketplace-verified.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agent Claim: common questions
- Is Agent Claim MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Agent Claim safety report
- How do I install Agent Claim?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agent Claim need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agent Claim maintained?
- The last commit was 51 days ago (2026-09-14). The latest release is v1.0.2.
- What can I use instead of Agent Claim?
- Servers from other publishers that do the same job: Openflowkit MCP server, Serena MCP: the IDE for your agent MCP server and Figma Context MCP server.
- How does Agent Claim compare with other AI and agents MCP servers?
- safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Agent Claim
Same job from other publishers: the closest match first, then the best rated.
- OpenflowkitArchitecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.not reviewedEstablishedA
- Serena MCP: the IDE for your agentA powerful toolkit for coding, providing semantic retrieval and editing capabilities.not reviewedWidely usedC
- Figma ContextGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.not reviewedWidely usedB
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA