# 1Claw Vault (io.github.1clawAI/1claw-mcp@0.52.0) > Source: > Published: 2026-08-18 22:27:14+00:00 [← Index](/leaderboard) # 1Claw Vault HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning. The current version, v0.52.0, was published to the official MCP registry on 2026-08-18. It is distributed as @1claw/mcp on npm, filed under Security by this index, and declares 5 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; [the index's current counts](/stats) put this record in context. ## Using 1Claw Vault in Claude, Cursor, Gemini CLI, Cline, or Zed? MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and **HOLDs the call** when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use **Install this server** for that). Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less ``` uv tool install mcpindex-gate && mcpindex-config-wire ``` [method](/methodology) Semantic screen flagged a possible manipulation pattern in the description; review before your agent calls this tool. `mcpindex.integrity.description` failLOWevidence“prompt-injection capability”via static_description - - Semantic screen only - the deterministic conformance probe has not run on this server - - Confidence is reported but not yet calibrated (v1) - - Screen reads the tool description, not the live behavior - - advisory - - registry description only no input schema - - screen model 8b - - Still current: the description we screened is unchanged, re-checked against the registry - - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page. Own this server? [Screen its description →](/screen) ## That verdict was true at screening time (snapshot 2026-08-18). Contracts can change after screening, with no version bump. The gate pins 1Claw Vault’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday. [See your first HOLD in 2 minutes →](/guides/install-the-gate-first-hold) Related: [how to trust an MCP server](/guides/how-to-trust-an-mcp-server) · [screen before install](/guides/screen-mcp-server-before-install) · [silent contract drift](/guides/mcp-silent-contract-drift) People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land. ``` [Independent trust record for 1Claw Vault](https://mcpindex.ai/server/io-github-1clawai-1claw-mcp) - screening verdict, registry provenance, and contract drift monitoring. Independent trust record for 1Claw Vault - screening verdict, registry provenance, and contract drift monitoring. ``` A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does. ``` [![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-1clawai-1claw-mcp)](https://mcpindex.ai/server/io-github-1clawai-1claw-mcp) mcpindex verdict ``` `ONECLAW_AGENT_API_KEY` Agent API key (ocv_...). Exchanged for a short-lived JWT; auto-discovers agent ID and vault. Recommended for stdio. `ONECLAW_AGENT_ID` Optional agent UUID when pinning identity (usually auto-discovered from the API key). `ONECLAW_VAULT_ID` Optional vault UUID when the agent can access multiple vaults. `ONECLAW_BASE_URL` Vault API base URL (default https://api.1claw.xyz). `ONECLAW_LOCAL_ONLY` Set to true for security-only mode (inspect_content only; no vault credentials). [methodology](/methodology) [squirrelscancom.squirrelscan/squirrelscan](/server/com-squirrelscan-squirrelscan) Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP. [Arkon Vaultio.github.Havix0101/arkon-vault](/server/io-github-havix0101-arkon-vault) Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools. [io.github.4DA-Systems/4da-mcp-serverio.github.4DA-Systems/4da-mcp-server](/server/io-github-4da-systems-4da-mcp-server) Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.