The ai-runtime-guard server is a policy-enforcing intermediary for AI agents, providing controlled file operations and command execution with safety checks, logging, backups, and approval gates.
Execute commands (execute_command): Run shell commands subject to full policy evaluation (workspace containment, command-tier rules, Script Sentinel checks) and human approval gates; destructive patterns are blocked or require explicit approval.
Read files (read_file): Read text files from within allowed workspace paths.
Write files (write_file): Create or overwrite files with policy enforcement, automatic logging, and backup creation.
Edit files (edit_file): Apply targeted text replacements with pre-edit backup support.
Delete files (delete_file): Delete after policy checks, with optional pre-delete backup for safety.
List directories (list_directory): List directory contents with metadata, respecting path and depth policies.
Restore backups (restore_backup): Restore files from AIRG backup manifests, supporting dry-run planning and token-gated apply.
Inspect server info (server_info): Retrieve runtime identity details, build ID, workspace root, and base directory.
The server enforces workspace/path boundaries, supports per-agent policy overlays (AIRG_AGENT_ID), and includes security hardening via Script Sentinel and universal agent posture enforcement. All allowed, blocked, and pending actions are logged for auditing, and an optional web GUI enables policy editing, approvals, and agent management.
Your agent can say anything. It can only do what policy allows.
AI agents with filesystem and shell access can delete files, leak credentials, or execute destructive commands, often without the user realizing until it is too late.
Runtime Guard sits between your AI agent and your system, enforcing policy on every file and shell action before it executes. Install once, configure your rules, and your agent operates within the boundaries you set. Works with Claude Code, Claude Desktop, Cursor, Codex, and any MCP-compatible client. No retraining, no prompt engineering, no external account required.
agent -> execute_command("rm -rf /tmp/build")
✗ BLOCKED destructive command pattern: rm -rf
matched_rule: destructive_command | decision: blocked
agent -> execute_command("git push --force")
⏸ APPROVAL REQUIRED awaiting operator
token: a4f2b9 | expires: 10min | check GUI to approve
agent -> write_file("README.md", ...)
✓ ALLOWED backup created before write
backup_location: ~/.local/state/airg/backups/2026-03-18Related MCP server: Stage0 Authorization MCP Server
pipx install ai-runtime-guard
pipx ensurepath # if airg* commands are not found
# open a new terminal
airg-setup
airg-doctorAfter setup, open http://127.0.0.1:5001 and add your first agent from Settings -> Agents.
Alternative quick start (venv):
python3 -m venv .venv-airg && source .venv-airg/bin/activate
python -m pip install --upgrade pip
python -m pip install ai-runtime-guard
airg-setup (guided, recommended: select/create workspace during setup; includes telemetry opt-in prompt, default Yes)
airg-doctor
Open GUI Settings -> Agents, add agents manually, and apply MCP config/hardening from there.
Source-clone path:
git clone --branch main https://github.com/runtimeguard/runtime-guard.git
cd runtime-guard
python3 -m venv .venv-airg && source .venv-airg/bin/activate
python -m pip install --upgrade pip
python -m pip install .
airg-setup
airg-doctor
Unattended automation-only setup (CI/non-interactive):
airg-setup --defaults --yes --workspace /absolute/path/to/workspace
See docs/INSTALL.md for the full install reference.
Prevention
Blocks destructive commands (rm -rf, privilege escalation, sensitive file access) before they run
Auto-backs up any file before destructive or overwrite operations
Control
Gates risky commands behind explicit human approval via local GUI or API
Enforces workspace and path boundaries keyed to AIRG_WORKSPACE
Supports per-agent policy overlays keyed to AIRG_AGENT_ID
Configurable network policy with allowlists, denylists, and monitor/enforce modes
Visibility
Logs every allowed, blocked, and pending action to activity.log
Indexes events into reports.db for a dashboard view of agent behavior
Hardening
Script Sentinel: detects attempts to launder blocked commands through scripts
Universal agent hardening: GUI-driven posture enforcement including hooks, sandboxing, and native tool restrictions (support varies by client)
Runtime Guard is built as an MCP server because MCP provides the interception point you need. When your agent issues a tool call, Runtime Guard evaluates it against policy before execution. For clients that support pre-tool hooks (like Claude Code), AIRG can also deny the agent's native file and shell tools, forcing risky operations through the policy layer.
This approach is the closest to kernel-level enforcement without requiring system privileges or modifying your agent, and it works across any MCP-compatible client without per-agent engineering.
Developers and operators running AI agents who want deterministic guardrails on what an agent can actually do to their system, without giving up agent autonomy or rewriting their workflow.
Platform | Clients |
macOS | Claude Code, Claude Desktop, Cursor, Codex |
Linux | Claude Code, Claude Desktop, Cursor, Codex |
Enforcement depth varies by client. MCP policy enforcement is universal; hook-based native tool restriction and sandboxing depend on what each client exposes.
For Codex, AIRG supports both user-scope (~/.codex/) and project-scope (<workspace>/.codex/) artifacts. Project-scope enforcement requires the workspace to be trusted in the user-layer ~/.codex/config.toml before Codex will load the project .codex/ files. AIRG writes Codex tool approval stanzas only in the project-scoped .codex/config.toml.
What AIRG is designed for: reducing accidental damage from agent mistakes, hallucinated commands, and policy-evasion patterns.
What AIRG is not: a full malicious-actor containment platform.
Known enforcement boundary:
AIRG enforces policy only on actions routed through AIRG MCP tools
Native client tools outside MCP (e.g. Claude Code's built-in Bash, Glob, Read, Write, Edit) bypass AIRG unless the client is configured to restrict them
For strict enforcement, use Settings -> Agents in the GUI to apply hook-based native tool restrictions where supported
AIRG_WORKSPACEThe default project root for guarded agent operations. execute_command runs from this directory, file tools evaluate path policy relative to this root, and traversal outside the root is blocked. Multiple workspaces are supported. Each agent profile should set workspace explicitly in its MCP config.
AIRG_AGENT_IDThe runtime identity key used for activity and report attribution, per-agent policy override resolution, and posture state in Settings -> Agents.
AIRG includes a local web control plane at http://127.0.0.1:5001 for policy editing, approvals, agent profile management, reports, and telemetry control.
Service commands:
airg-service install --workspace /absolute/path/to/airg-workspace
airg-service start | status | stop | restart | uninstallAIRG supports optional anonymous telemetry to help prioritize improvements. It is opt-in during setup (default: Yes) and can be toggled any time from Policy -> Advanced -> Anonymous telemetry.
No command text, file contents, paths, prompts, usernames, or machine identifiers are collected
One aggregate payload per UTC day
Payload preview available in the GUI before enabling
Full details in docs/telemetry.md
Delete a single file after policy checks and optional pre-delete backup.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It mentions 'policy checks and optional pre-delete backup,' which adds behavioral context beyond a bare 'delete file.' However, it doesn't disclose failure modes, reversibility, or authentication needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, front-loaded with action and context. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with output schema, description covers policy and backup but leaves parameter details unclear. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must compensate. It does not explain what 'path' should be (e.g., absolute vs relative) or what 'ctx' is. It adds minimal value beyond parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete), the resource (a single file), and adds specific context (policy checks and optional pre-delete backup). This distinguishes it from siblings like edit_file, read_file, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like restore_backup or edit_file. It does not mention prerequisites, limitations, or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Apply targeted text replacements in an existing file with backups.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| old_text | No | ||
| new_text | No | ||
| replace_all | No | ||
| edits | No | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description only mentions backups but does not disclose replacement behavior, permissions, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence) but under-specified given the tool's complexity with 6 parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is incomplete, lacking parameter explanations and contextual details despite having an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description adds no meaning to any of the 6 parameters, including the required path.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool does 'targeted text replacements in an existing file' and mentions backups, distinguishing it from write_file and delete_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when or when not to use this tool compared to siblings like write_file or delete_file.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a shell command after full AIRG policy and approval checks.
The command is evaluated against network/workspace containment, command-tier policy, Script Sentinel continuity checks, and optional confirmation gates before execution.
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | ||
| retry_count | No | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description effectively discloses key behavioral traits: safety checks like AIRG policy, network containment, command-tier policy, Script Sentinel continuity checks, and confirmation gates. However, it does not mention the mutability (destructive potential) or the output format (though output schema exists).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, with the purpose stated first. Every sentence adds value (purpose + safety context), and there is no redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, no parameter descriptions in schema or description, and an output schema that is not mentioned, the description fails to provide a complete picture. It covers safety checks but omits critical param semantics and output expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds no information about any of the three parameters (command, retry_count, ctx). An agent cannot understand what 'retry_count' or 'ctx' mean or how to use them, which is a severe gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Execute a shell command', which is a specific verb and resource. It distinguishes from sibling tools (file operations and server_info) by being the only command execution tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'after full AIRG policy and approval checks' but provides no explicit guidance on when to use this tool versus alternatives (e.g., when not to use it or what prerequisites are needed). No sibling tools compete directly, but the description could clarify scenarios where command execution is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List directory entries with metadata, honoring path and depth policy.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so description must cover behavior. It states 'honoring path and depth policy' but does not explain what that policy is, nor whether the operation is read-only, paginated, or recursive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded with purpose. However, it sacrifices necessary detail for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, two parameters, and an output schema, the description should clarify behavior, parameter roles, and output meaning. It fails to explain the depth policy and the optional ctx parameter.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must explain parameters. It mentions 'path' indirectly but does not describe 'ctx' or how depth policy affects listing. Minimal addition beyond schema structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'list' and resource 'directory entries with metadata'. It clearly states the action and what is returned, distinguishing it from file manipulation siblings like delete_file and write_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., read_file for file content). The mention of 'depth policy' implies constraints but is not explained.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a text file from the workspace after path-policy enforcement.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'path-policy enforcement' but omits behaviors such as error handling, size limits, or encoding. For a simple read tool, more detail would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 9 words, front-loading the core information. Every word is purposeful with no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple read tool with an output schema, but it lacks details on file type, encoding, or error scenarios. It does not fully contextualize when to use this vs list_directory.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate. It adds meaning for 'path' (the file to read) but completely ignores 'ctx'. The parameter semantics are insufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Read') and the resource ('text file from the workspace') with an additional qualifier ('after path-policy enforcement'). This distinguishes it from siblings like write_file, delete_file, and edit_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit when-to-use or when-not-to-use guidance. It implies use for reading file content but does not contrast with list_directory or other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Restore files from a recorded AIRG backup manifest.
Supports dry-run planning and token-gated apply mode when restore confirmation is required by policy.
| Name | Required | Description | Default |
|---|---|---|---|
| backup_location | Yes | ||
| dry_run | No | ||
| restore_token | No | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses support for dry-run planning and token-gated apply mode, but does not mention other behaviors such as file overwrite policy, permission requirements, or error handling. This is insufficient for a restore operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the core purpose and adding key behavioral notes. Every word earns its place with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 4 parameters and an output schema. The description covers dry-run and token modes, which are critical, but lacks details on backup_location format, context object usage, and outcome (e.g., overwrite behavior). For a restore tool, more context is needed to avoid user error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds meaning for 'dry_run' (planning mode) and 'restore_token' (gated apply), but 'backup_location' is only vaguely described as 'recorded AIRG backup manifest' and 'ctx' is not mentioned. Coverage is partial.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Restore files from a recorded AIRG backup manifest,' specifying a precise verb and resource. Sibling tools are file operations unrelated to backup, so this tool is well-distinguished.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions dry-run and token-gated modes, implying when to use them, but does not explicitly state when not to use the tool, prerequisites (e.g., existence of manifest), or alternatives. Since no sibling backup tools exist, the lack of alternatives is acceptable, but the guidance is still minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return runtime identity details for this AIRG server instance.
Includes build id, active workspace root, and resolved base directory.
| Name | Required | Description | Default |
|---|---|---|---|
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It indicates the tool returns identity details but does not disclose whether it requires permissions, error behavior (e.g., if server is unavailable), or performance characteristics. Adequate but could be more explicit about safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: one stating the overall purpose and one listing the included items. Every word serves a purpose with no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values are documented elsewhere, but the description does not mention edge cases, error conditions, or the purpose of the undocumented parameter. For a simple informational tool, it is mostly adequate but incomplete regarding the parameter.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter 'ctx' which is optional and nullable, but the description does not mention it at all. With 0% schema description coverage, the description fails to add any meaning to this parameter, leaving an agent without guidance on what 'ctx' represents.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns runtime identity details for the AIRG server, listing specific items like build id, active workspace root, and resolved base directory. This is a specific verb+resource combination that is distinct from sibling tools like file operations or restore_backup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. As a diagnostic tool, it could be used for configuration validation, but the description does not mention context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Write full file content with policy checks, logging, and backup support.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| content | Yes | ||
| ctx | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It mentions 'policy checks, logging, and backup support' but does not detail authorization requirements, file overwrite behavior, backup creation details, or size limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no extraneous information. Every word earns its place, conveying the core action and key features efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the three parameters (two required) and existing sibling tools like 'edit_file', the description lacks crucial details: how overwriting works, error conditions, backup behavior, and differentiation from similar tools. Although an output schema exists, the description does not supplement it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description adds minimal parameter semantics. 'content' is implied as the full text to write, but 'path' and 'ctx' are not described. No parameter definitions are provided in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Write full file content', identifying the verb and resource. It adds 'with policy checks, logging, and backup support', which hints at additional capabilities. However, it does not explicitly differentiate from the sibling tool 'edit_file', which might handle partial updates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives like 'edit_file' or 'delete_file'. The description implies full content overwriting but lacks explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v2.3.1edit_filev1.5.0delete_fileexecute_commandlist_directoryread_filerestore_backupserver_infowrite_fileScored across 8 tools
Each tool targets a distinct operation: file read/write/edit/delete, command execution, directory listing, backup restore, and server info. No two tools have overlapping purposes.
All tool names follow a consistent snake_case verb_noun pattern (e.g., delete_file, execute_command, server_info). No mixing of conventions.
8 tools is well-scoped for a runtime guard. Each tool earns its place by covering essential file, command, backup, and info operations without bloat.
Covers core CRUD-like operations for files, plus command execution and backup. Minor gaps like missing move/copy or directory creation tools, but agents can work around with existing tools.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
