$ loading_
Add enforced agent governance and read-only reference tools for safer MCP use.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.levelsofself/nervous-system" MCP server from askskill: Run: claude mcp add 'io-github-levelsofself-nervous-system' -- npx -y mcp-nervous-system
Use nervous-system in the current MCP client, apply its enforced rules to the next agent task, and first explain how those rules will constrain your behavior.
A governed behavior summary, followed by rule-constrained execution in later steps.
Analyze the problem under nervous-system constraints, using only its read-only reference tools and performing no write or modification actions.
An analysis grounded in read-only reference information with no side effects.
Explain the role of nervous-system in the current MCP client and show how it helps an agent remain safer while performing a task.
A description of the tool’s role plus an example of task execution with safety boundaries.
Developers or product teams can use it to enforce rules when integrating LLM agents, reducing the risk of unsafe behavior. It fits scenarios where agents need consistent safety boundaries.
When an agent needs reference information without changing external state, this tool provides read-only support. It is suitable for low-risk tasks that should avoid write-side effects.
If a team uses agents across different MCP clients, this tool can provide consistent governance constraints. The description states it is safe to use in any MCP client.
It provides governance for LLM agents, including 7 enforced rules and read-only reference tools. Its goal is to help agents operate more safely in MCP clients.
The provided description only explicitly mentions “read-only reference tools” and does not describe write capabilities. Based on the available information, it is best understood as emphasizing read-only reference access and behavioral constraints.
The provided material does not include installation steps, dependencies, or key requirements. What we can confirm is that it is described as safe for use in any MCP client; for exact setup details, see the source repository.
Add policy enforcement to stdio MCP servers and block denied tool calls.
Govern agent decisions with auditable evidence, confidence calibration, and policy-based handoffs.
Manage notes securely with policy controls, approvals, and prompt injection detection.
Safely run shell commands via MCP with session and process control.
Helps LLM agents discover, register, and run local and remote MCP tools.
Govern and audit AI agents with safety checks, reasoning, and session controls.