---
title: "1claw"
description: "Secure secrets management, multi-chain signing, agent memory, automations, and 155 tools (offered per agent entitlement, in toolsets) for AI agents via 1Claw vault."
canonical: https://agentpluginsdirectory.com/plugins/1claw
last-updated: 2026-09-26
---

# 1claw
Secure secrets management, multi-chain signing, agent memory, automations, and 155 tools (offered per agent entitlement, in toolsets) for AI agents via 1Claw vault.
- Slug: 1claw
- Publisher: 1Claw
- Repository: https://github.com/1clawAI/1claw-mcp
- Manifest: plugin.json
- Version: 0.63.0
- License: MIT
- Category (editorial): security
- Skills: 1 (secrets-management)
- MCP servers: 1 (1claw)
- Stars: 2
- Repository created: 2026-02-20
- Repository last pushed: 2026-09-23
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/1claw
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What 1claw does, in the publisher's words

> ⭐ Star 1clawAI/agent-templates: ready-to-run agent templates wired to 1Claw. It is our single starred repo.

Connect Cursor, Claude Desktop, VS Code, or any MCP client to your 1claw vault. The server exposes tools for secrets, signing, execution bindings, memory, automations, and more. Values are fetched at call time and are not cached in the model's context beyond the moment they are used.

Most teams use this instead of copying API keys into agent prompts or MCP config files. You register an agent, grant policy access to specific secret paths, and point the client at mcp.1claw.co or a local stdio process. The server handles JWT exchange and refresh from a single ocv_ key.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/1clawAI/1claw-mcp/HEAD/README.md

## MCP servers

- 1claw: transport: stdio; command: npx -y @1claw/mcp; env: ONECLAW_AGENT_API_KEY

Read from the plugin's own mcp.json. Environment variable names only, never values.