Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Check Point Management MCP Server Add access rule blocking 10.0.1.0/24 to 192.168.1.100 on port 443, then publish and install."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server for Check Point Management write-path workflows: draft an access rule, publish the session, install policy — the full compensating-control lifecycle, exposed as typed MCP tools with the same three-stage state machine as the real Management API.
Built with FastMCP v3. Originally built for a live orchestration demo at Tenable EXPOSURE 2026 (Boston), where an AI agent deployed a compensating firewall control for an unpatchable industrial asset under human supervision.
Check Point ships an official MCP server bundle. Its @chkp/quantum-management-mcp is the right read-side wrapper but is read-only by design — list rules, show objects, query topology, no writes. Compensating-control workflows (block traffic to an asset you can't patch yet) need add-access-rule, publish, and install-policy: an operator-supervised write path the official MCP intentionally doesn't expose.
This server fills that write-side gap with the three-stage lifecycle (draft → published → installed) matching the real Management API state machine — so an AI agent's audit trail reads exactly like a human operator's.
Related MCP server: Check Point CloudGuard WAF MCP Server
Does: expose the write-path contract — tool signatures, rule lifecycle, response shapes — mirroring Check Point's Management API (add-access-rule, publish, install-policy, show-access-rulebase).
Doesn't (yet): contact a real Smart-1 or Security Management Server. The backend is in-memory, which makes it safe for demos, agent development, and workflow testing out of the box. For production, the in-memory backend swaps for the official cp_mgmt_api_python_sdk talking to Smart-1 Cloud or on-prem — tool signatures and response shapes do not change.
Tool | Lifecycle stage | Description |
| read | List current rules in an access layer |
| draft | Add a rule in the current session (status: |
| draft → published | Commit drafted rules to the management server |
| published → installed | Push published rules to gateways — the rule actually enforces |
The deliberate two-gate publish/install split mirrors real Check Point operator workflow, giving a supervising human two natural checkpoints before anything enforces.
Python 3.11+
uv (recommended) or pip
No credentials needed — the backend is in-memory
git clone <repo-url> && cd checkpoint-mcp-server
uv sync
uv run checkpoint-mcp # stdio mode for Claude Desktop / Claude Code
uv run pytest -v # tests{
"mcpServers": {
"checkpoint": {
"command": "uv",
"args": ["run", "--directory", "/path/to/checkpoint-mcp-server", "checkpoint-mcp"]
}
}
}All tools return Markdown: rule tables with UID, source/destination/service/action, lifecycle status badges, and publish/install task summaries — shaped for LLM consumption and human-readable audit trails.
Python 3.11+, FastMCP v3, pydantic-settings, hatchling
Entry point: checkpoint_mcp.server:main (CLI: checkpoint-mcp)
In-memory state machine in state.py; vendor-shaped mock seed data in mock/data.py
In-memory backend: no real Check Point management server is contacted; state resets on restart. Production use requires swapping in the official SDK (interfaces are designed for it).
Access-control scope only: NAT rules, threat prevention, VPN, and object management are not covered.
Single session model: no concurrent session/locking semantics like a real multi-admin Management Server.
MIT
Add a new access rule to the current session.
The rule is created with status draft and is NOT committed or
installed -- it lives in the current management session only. The
orchestrator surfaces the draft to the operator for review, then
calls checkpoint_publish_session and checkpoint_install_policy
to move it through the lifecycle.
This is typically a human-gated step in a change workflow, reserved for network-policy changes.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Human-readable rule name (e.g. "Compensating control: hmi-pack-01 SMB"). | |
| layer | No | Access layer name. Defaults to the configured default layer. | |
| action | No | Action verb: one of Drop, Accept, Reject, Inform. Compensating-control default is 'Drop'. | Drop |
| source | Yes | Source object name(s). Use `Any` for unrestricted source. For compensating controls the typical value is `Any`. | |
| service | Yes | Service object name(s) (e.g. "smb", "tcp/445"). | |
| comments | Yes | Free-text justification stored on the rule. Reference the unpatchable CVE / CI and the iTop change ref so a future reviewer understands why the rule exists. | |
| destination | Yes | Destination object name(s). For compensating controls this is the unpatchable CI alias (e.g. "hmi-pack-01"). MUST be alias-scrubbed. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, destructiveHint=false), the description reveals that the rule is created as 'draft', not committed, lives only in the session, and surfaces for operator review. No contradiction with annotations.
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?
Six lines, each sentence adds value. Purpose is front-loaded in the first sentence. No wasted words.
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 7 parameters and a human-gated workflow, the description covers purpose, lifecycle, usage context, and ties to sibling tools. An output schema exists, so return values are not needed in the description.
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 100%, so the schema already documents parameters well. The description does not add new parameter information beyond what the schema provides, so baseline score of 3 is appropriate.
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 explicitly states 'Add a new access rule to the current session', specifying the action and scope. It distinguishes from sibling tools by detailing the draft lifecycle and referencing checkpoint_publish_session and checkpoint_install_policy.
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?
Explicitly says 'This is typically a human-gated step in a change workflow, reserved for network-policy changes', telling when to use it and implying it's not for automated direct commits. It also references the sibling tools for the follow-up steps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Push published rules on a layer to the named gateways.
This is the moment a compensating-control rule actually starts blocking traffic on the wire. The orchestrator pairs this call with the operator's third human-in-loop approval.
| Name | Required | Description | Default |
|---|---|---|---|
| layer | No | Access layer to install. Defaults to the configured default layer. | |
| targets | Yes | Gateway object name(s) to push the published policy to (e.g. ["xxxx-fw-us-01"]). At least one target is required. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, etc.), the description adds that this tool causes rules to start blocking traffic and requires human approval. It does not contradict annotations and provides useful behavioral context.
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?
Three sentences, front-loaded with the core action, followed by concise operational context. Every sentence is necessary and 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?
For a two-parameter tool with an output schema and annotations, the description fully explains the significance and context (compensating control, human approval), making it complete for agent understanding.
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 schema already describes both parameters (layer, targets) with 100% coverage. The description uses 'named gateways' which aligns with the 'targets' parameter but adds no syntactic or semantic detail beyond the schema.
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 uses a specific verb 'Push' and clearly identifies the resource ('published rules on a layer to the named gateways'). It also provides operational context about activating rules, which distinguishes it from sibling tools like 'list' or 'publish'.
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 implies when to use this tool: after publishing rules and with human-in-loop approval. It doesn't explicitly state when not to use or compare to alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List access rules in a given layer, optionally filtered by lifecycle status.
Mirrors the real Management API show-access-rulebase shape: each rule
carries a uid, name, source/destination/service object lists, action,
and a lifecycle status (draft/published/installed) reflecting where it
sits in the publish + install-policy workflow.
| Name | Required | Description | Default |
|---|---|---|---|
| layer | No | Access policy layer name (e.g. "XXXX-Corp Network"). Defaults to the configured default layer. | |
| status | No | Filter by lifecycle status: 'draft', 'published', or 'installed'. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context by explaining the API shape (each rule carries uid, name, object lists, action, lifecycle status) and the relationship to publish/install workflow. No contradictions.
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 concise (two sentences) with no fluff. The first sentence provides the primary purpose, and the second adds relevant detail about the API shape. Front-loaded and efficient.
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 existence of an output schema (explaining return values), the description sufficiently covers the tool's behavior. It explains the shape of individual rules and the lifecycle status concept. Combined with annotations, it provides a complete picture for a list operation.
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 100% for both parameters (layer and status), so the schema already documents their meaning. The description adds minor context about status being a lifecycle filter and the workflow, but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate.
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 lists access rules in a given layer with optional lifecycle filtering. It uses specific verb 'List' and resource 'access rules', and distinguishes from sibling tools (add, publish, install) by being a read operation.
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 explicitly state when to use this tool versus alternatives. It implies usage for listing, but provides no guidance on when to choose it over other tools or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Commit every drafted rule in the current session to the management server.
Drafted rules transition to published. Published rules survive across
sessions but do NOT yet enforce on gateways -- that requires
checkpoint_install_policy. Idempotent: calling with no drafts is a no-op.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds value beyond annotations: describes transition to 'published' status, cross-session persistence, and what the tool does NOT do. No contradiction with annotations.
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?
Two concise sentences plus a brief clarification. Every sentence carries essential information with no redundancy.
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?
Complete for a zero-parameter tool: explains what happens, how it relates to sibling, and idempotency. Output schema exists but not needed in description.
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?
No parameters exist, so the description correctly omits parameter details. Baseline 4 for zero parameters is appropriate.
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 uses specific verbs ('commit', 'publish') and resource ('drafted rules in current session'), and clearly distinguishes from sibling 'checkpoint_install_policy' by stating it does not enforce on gateways.
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?
Explicitly states when to use (to commit drafted rules) and when not (enforcement requires checkpoint_install_policy). Also notes idempotency to guide calling without drafts.
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. Dates show when Glama detected each change.
v0.1.0checkpoint_add_access_rulecheckpoint_install_policycheckpoint_list_access_rulescheckpoint_publish_sessionEach tool has a distinct and clearly defined purpose: listing rules, adding a draft rule, publishing the session, and installing the policy. There is no overlap or ambiguity between them.
All tool names follow a consistent `checkpoint_<verb>_<noun>` pattern with clear and descriptive verbs (list, add, publish, install). The naming is uniform and predictable.
Four tools is a reasonable scope for a focused policy management workflow. It covers the essential steps but could potentially include a few more without becoming overwhelming.
The tools cover the core lifecycle of creating, viewing, publishing, and installing access rules, but lack update and delete operations for individual rules. This may force agents to work around missing functionality.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Compliance frameworks (SOC 2, ISO 27001, CMMC, NIST, more) delivered to AI agents as MCP tools.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Give your AI agents the tools to build, manage, and run automation workflows.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tarhou/checkpoint-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
