Skip to main content
Glama

server_fix

Destructive

Apply safe auto-fixes to a server after auditing. Preview fixes by default, apply only SAFE-tier fixes, and re-audit to measure score improvement.

Instructions

Apply safe auto-fixes to a server. Runs audit, filters SAFE tier fixes, creates backup, applies fixes, and re-audits for score delta. dryRun defaults to true (preview only). SAFE_MODE forces preview. SSH/Firewall/Docker fixes are FORBIDDEN and always rejected. Use checks and category params to target specific fixes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
serverNoServer name or IP. Auto-selected if only one server exists.
actionNoapply: run fixes (default), rollback: restore single fix, rollback-all: revert all applied fixes, rollback-to: revert down to specific fix-id, history: list fix operationsapply
dryRunNoPreview fixes without applying. Defaults to true. Forced to true when KASTELL_SAFE_MODE=true.
rollbackIdNoFix ID to rollback (e.g. fix-2026-03-29-001) or 'last'
checksNoSpecific check IDs to fix (e.g. ['KERN-SYNCOOKIES']). AND-filtered with category if both provided.
categoryNoCategory name to filter fixes (e.g. 'Kernel'). AND-filtered with checks if both provided.
topNoApply top N highest-impact SAFE fixes. Requires action:'apply'. Mutually exclusive with target.
targetNoApply SAFE fixes until score reaches this value (1-100). Requires action:'apply'. Mutually exclusive with top.
profileNoServer profile to filter applicable checks (built-in: web-server, database, mail-server; or custom profile name)
diffNoInclude per-fix diff preview in results
reportNoGenerate markdown fix report file in current directory
forceNoBypass regression gate and force baseline update

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Description adds significant behavioral context beyond annotations: runs audit before applying, creates backup, re-audits for score delta, dryRun default, forbidden fix categories. This complements the destructiveHint annotation by explaining the safety measures.

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

Conciseness5/5

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

Two sentences front-load the main purpose and workflow, then quickly cover key constraints. Every sentence adds value without redundancy or fluff.

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

Completeness4/5

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

The description explains the main workflow, default behavior, forbidden fixes, and targeting. It could elaborate on rollback actions beyond listing them, but overall provides sufficient context for a complex tool with 12 parameters and multiple actions.

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

Parameters3/5

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

Schema coverage is 100%, so parameters are well-documented. The description adds minimal new semantics for individual parameters (e.g., dryRun default reiterated) but does provide overall workflow context that helps with parameter usage.

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?

The description clearly states the tool applies safe auto-fixes to a server, detailing the workflow: audit, filter SAFE fixes, backup, apply, re-audit. This distinguishes it from sibling tools like server_audit (audit only) and server_maintain (likely different purpose).

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?

Provides explicit guidance: dryRun defaults to true (preview only), SAFE_MODE forces preview, SSH/Firewall/Docker fixes are forbidden, and use checks/category to target specific fixes. This helps agents decide when and how to use the tool.

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/kastelldev/kastell'

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