Skip to main content
Glama

nucleus_governance

Destructive

Enforce file integrity and security posture by locking files against modification, switching security modes, and running automated verification and fix cycles.

Instructions

Enforce file integrity, security posture, and automated verification loops for the Nucleus Agent OS. Use this tool when you need to lock files against modification, switch security modes, or run auto-fix cycles. Do NOT use for task management (use nucleus_tasks), session state (use nucleus_sessions), or memory storage (use nucleus_engrams). Actions: 'lock' sets an immutable flag on a file preventing modification. 'unlock' removes that flag (destructive: re-enables writes). 'set_mode' switches between 'red' (restricted, blocks dangerous ops) and 'blue' (permissive) security modes. 'auto_fix_loop' runs a verify-diagnose-fix-retry cycle: it executes your verification_command, and if it fails, attempts to fix the file, then retries until the command passes or max retries exceeded. 'delete_file' permanently removes a file (destructive, irreversible). 'watch' monitors a file path and returns changes detected within the duration window. 'curl' proxies HTTP requests through Nucleus egress controls. 'pip_install' installs Python packages with governance audit logging. 'status' returns current security mode and lock state. 'list_directory' returns directory contents. Side effects: lock/unlock modify filesystem extended attributes. delete_file removes data permanently. Prerequisites: .brain directory must exist. Returns JSON with {success: boolean, data: object}. Example: {action: 'auto_fix_loop', params: {file_path: 'src/app.py', verification_command: 'python -m py_compile src/app.py'}} returns {success: true, data: {iterations: 2, fixed: true}}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesSelect the governance action to execute. 'auto_fix_loop' runs automated verification and repair. 'lock'/'unlock' control file immutability. 'set_mode' changes security posture between 'red' (restricted) and 'blue' (permissive). 'delete_file' is destructive and irreversible. 'status'/'list_directory' are read-only. 'curl' proxies external HTTP requests through egress controls. 'pip_install' installs packages with audit logging.
paramsNoAction-specific parameters as key-value pairs. auto_fix_loop: {file_path: string (required, path to verify), verification_command: string (required, shell command that returns exit code 0 on success)}. lock: {path: string (required, file or directory to make immutable)}. unlock: {path: string (required, file or directory to make writable again)}. set_mode: {mode: string (required, 'red' or 'blue')}. list_directory: {path: string (optional, defaults to .brain root)}. delete_file: {path: string (required, DESTRUCTIVE — permanently removes file)}. watch: {path: string (required, file or directory to monitor), duration: integer (optional, seconds to watch, default 30)}. curl: {url: string (required), method: string (optional, 'GET'|'POST'|'PUT'|'DELETE', default 'GET'), headers: object (optional), body: string (optional)}. pip_install: {package: string (required, PyPI package name)}. status: no parameters needed.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Disclose side effects (lock/unlock modify extended attributes, delete_file permanent removal), prerequisites (.brain directory must exist), and destructive actions. Annotations already set destructiveHint=true, readOnlyHint=false; description adds concrete context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is lengthy but well-structured: starts with general purpose, then usage guidelines, then systematic action breakdown. Each sentence earns its place given tool complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all actions, parameters, side effects, prerequisites, and return format (JSON success/data). Even includes an example. No output schema needed; description suffices.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds value with detailed parameter descriptions per action and a concrete example for auto_fix_loop, going beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states purpose: enforce file integrity, security posture, and automated verification loops. It distinguishes from sibling tools by explicitly excluding task management, session state, and memory storage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('lock files, switch security modes, run auto-fix cycles') and when not to use ('Do NOT use for task management...'), with alternative tools named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/eidetic-works/nucleus-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server