Skip to main content
Glama
fquiroga

Panorama MCP Server

by fquiroga
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Panorama MCP Server

A read-only Model Context Protocol server for Palo Alto Panorama policy review.

The server is intentionally narrow:

  • reads security rules through the PAN-OS XML API;

  • normalizes rule fields into deterministic sets;

  • finds exact duplicates, broader coverage, conflicts, and partial overlaps;

  • returns evidence and a preclear decision;

  • never commits to Panorama or pushes to managed firewalls.

This is a companion implementation for the blog post Running Palo Alto Panorama MCP Servers. It is not an official Palo Alto Networks product.

Prerequisites

  • Python 3.11 or newer.

  • Network access from the server host to Panorama management HTTPS.

  • A dedicated read-only Panorama API administrator or service account.

  • An API key injected through a secret manager or a protected environment.

  • A lab or non-production device group for the first rollout.

Do not use a superuser key. Do not disable TLS verification in production.

Related MCP server: LimaCharlie MCP

Install

Using uv:

cd panorama-mcp-server
uv venv
source .venv/bin/activate
uv pip install -e '.[dev]'
cp .env.example .env

Using pip:

python -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -e '.[dev]'
cp .env.example .env

Set the required values in .env:

PANORAMA_URL=https://panorama.example.net
PANORAMA_API_KEY=the-read-only-key
PANORAMA_VERIFY_TLS=true
PANORAMA_DEVICE_GROUP=shared
PANORAMA_RULEBASE=pre-rulebase

The API key is passed only to the outbound Panorama request and is never included in tool results or application logs.

Run the server

For a local MCP client using stdio:

panorama-mcp

For a development Streamable HTTP endpoint:

panorama-mcp --http

The official MCP Python SDK serves Streamable HTTP at the SDK default endpoint. Confirm the exact endpoint and authentication requirements in the MCP host before exposing it beyond localhost. This project does not add HTTP authentication; put a remote deployment behind an authenticated gateway and network policy.

Example local client configuration:

{
  "mcpServers": {
    "panorama-readonly": {
      "command": "/absolute/path/to/panorama-mcp-server/.venv/bin/panorama-mcp",
      "env": {
        "PANORAMA_URL": "https://panorama.example.net",
        "PANORAMA_API_KEY": "injected-by-the-client-secret-manager"
      }
    }
  }
}

Do not put a real API key in a committed client configuration.

Available tools

list_device_groups

Lists the device groups visible to the configured API key.

get_security_rules

Reads and normalizes security rules from one device group and rulebase.

Arguments:

{
  "device_group": "shared",
  "rulebase": "pre-rulebase"
}

search_policy_coverage

Accepts a normalized request and returns exact duplicates, broader coverage, conflicts, and partial overlaps.

Example request:

{
  "device_group": "shared",
  "rulebase": "pre-rulebase",
  "source_zones": ["app"],
  "source_addresses": ["reporting-subnet"],
  "destination_zones": ["data"],
  "destination_addresses": ["postgres-prod"],
  "applications": ["postgresql"],
  "services": ["service-postgresql"],
  "action": "allow"
}

preclear_rule_request

Runs the deterministic policy comparison and returns:

  • blocked when an exact duplicate, broader same-action rule, or conflict is found;

  • review-required when there is only a partial overlap or no matching rule;

  • the matching rule, position, classification, and reason;

  • explicit unknowns for candidate changes, locks, and commit queue state.

The unknown operational checks are deliberate. This first version does not pretend that a read of the rulebase proves that no administrator is changing Panorama. Collect those checks through your approved change-management integration before allowing a write workflow.

Implementation steps

  1. Create a dedicated read-only Panorama account scoped to the device groups the agent needs.

  2. Generate the API key using the organization’s approved secret-management process.

  3. Deploy this server close to Panorama, with egress limited to the Panorama management URL.

  4. Run the tests and verify the server with MCP Inspector or your MCP host.

  5. Test duplicate, broader coverage, conflict, partial overlap, out-of-scope, and API failure cases against a lab.

  6. Add an audit sink that records request IDs, user identity, tool name, scope, result classification, and Panorama task IDs without secrets.

  7. Keep this server read-only while tuning false positives and false negatives.

  8. Add candidate writes only in a separate service, with separate credentials, human approval, change ID, preview, validation, commit, and push gates.

Security model

This project intentionally does not expose arbitrary XML, arbitrary XPath, commit, push, or delete tools.

Recommended production controls:

  • use a read-only API role and separate credentials for mutation;

  • keep TLS verification enabled;

  • pin dependencies and verify the container image;

  • run as a non-root user with a read-only filesystem;

  • restrict outbound network access to Panorama;

  • do not log API keys, authorization headers, cookies, or full XML that may contain sensitive data;

  • treat rule descriptions, tags, and object names as untrusted data;

  • require deterministic server-side checks before any future write;

  • keep candidate commit and firewall push as separate approved actions;

  • test rollback and audit procedures in a lab.

Docker

Build and run locally:

docker build -t panorama-mcp-server ./panorama-mcp-server
docker run --rm -i \
  --env-file panorama-mcp-server/.env \
  panorama-mcp-server

For a shared HTTP deployment, do not publish port 8000 directly to a management network. Use an authenticated reverse proxy, HTTPS, network policy, and short-lived credentials.

Test and lint

pytest -q
ruff check .

The tests are offline and do not contact Panorama. An integration test suite should use a disposable lab or a mocked HTTP transport with sanitized XML fixtures.

Limitations

  • The project supports PAN-OS XML API rule reads only.

  • The device-group XPath assumes a standard Panorama configuration tree.

  • Candidate changes, locks, and commit queue state are returned as explicit not-collected values.

  • No configuration mutation, commit, push, delete, or arbitrary command execution is exposed.

  • Object-group expansion is not performed by this version; unresolved object semantics must remain review-required.

References

  • Palo Alto Networks: Panorama Commit, Validation, and Preview Operations

  • Palo Alto Networks: About the PAN-OS API

  • Model Context Protocol: Security Best Practices

  • Model Context Protocol Python SDK

Available Tools

4 tools
get_security_rulesB

Fetch normalized security rules from one Panorama device group and rulebase.

ParametersJSON Schema
NameRequiredDescriptionDefault
rulebaseNo
device_groupNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries behavioral weight: 'Fetch' implies a read operation, 'normalized' indicates output transformation, and 'from one...' implies a single scope. It does not disclose error handling, pagination, permissions, or null-parameter behavior, but the verb and scope give basic behavioral orientation.

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?

The description is a single front-loaded sentence with no filler; every word adds meaning. It is appropriately sized for the tool's simple scope.

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

Completeness2/5

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

Although an output schema exists, the description leaves key contextual gaps: no parameter semantics, no behavior when both optional fields are omitted, and no routing to sibling tools. For a tool with zero annotations and 0% schema coverage, this is not complete enough for confident invocation.

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

Parameters2/5

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

Schema description coverage is 0%, and the description only repeats the fields' names (device group, rulebase) without explaining allowed values, formats, defaults, or null behavior. It adds slight meaning by saying 'from one', but it does not compensate for the undocumented schema.

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

Purpose4/5

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

The description uses a specific verb ('Fetch'), a concrete resource ('normalized security rules'), and a scope ('one Panorama device group and rulebase'), making the operation clear. It distinguishes this from sibling tools like list_device_groups and preclear_rule_request through the object and scope, though it does not name alternatives explicitly.

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

Usage Guidelines3/5

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

The description implies use when an agent needs normalized security rules scoped to a single Panorama device group and rulebase. However, it does not explicitly contrast this with siblings such as search_policy_coverage or state when not to use it, so the guidance is implied rather than direct.

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

list_device_groupsA

List Panorama device groups visible to the configured read-only API key.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses that the operation is read-only and visibility-limited, which is valuable behavioral context. It does not cover edge cases like pagination or empty results, but that is minor for a parameterless listing tool with an output schema.

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?

The description is a single, front-loaded sentence with no filler or redundancy. It states the operation, resource, and scope efficiently, making it easy for an agent to parse quickly.

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?

For a parameterless read-only list tool with an output schema, this description is complete. It identifies what is listed, the resource context, and the access boundary enforced by the read-only API key, leaving no critical information missing.

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?

The tool has zero parameters, so the schema provides no parameter semantics. The description adds useful context by defining the scope of the listing through the API key's visibility, which satisfies the baseline for parameterless tools.

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 uses a specific verb ('List') and names the exact resource ('Panorama device groups'), while clarifying the scope ('visible to the configured read-only API key'). This distinguishes it clearly from sibling tools like get_security_rules and search_policy_coverage.

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

Usage Guidelines3/5

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

The description implies when to use the tool—when listing device groups visible to the configured API key—but does not explicitly state when not to use it or mention alternatives. Usage context is clear enough for a simple read-only listing, but there is no direct guidance about sibling tools.

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

preclear_rule_requestB

Run deterministic read-only preclear checks before a rule change is considered.

ParametersJSON Schema
NameRequiredDescriptionDefault
requestYes
rulebaseNo
device_groupNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations provided, the description carries the behavioral disclosure burden. It usefully discloses that the operation is read-only and deterministic, which signals safety and reproducibility. However, it does not describe what the checks actually validate, what failure/success looks like, or any side effects or prerequisites, leaving meaningful gaps.

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?

The description is a single, tightly written sentence with no filler. Key qualifiers ('deterministic', 'read-only') are front-loaded, but the sentence is slightly jargon-heavy and could benefit from a brief expansion to define 'preclear checks' without becoming verbose.

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

Completeness2/5

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

Given the opaque required request object, three undocumented parameters, and absence of annotations, the description is not sufficient for correct invocation. An output schema may exist, but it does not make up for missing input semantics, so the overall context remains incomplete.

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

Parameters1/5

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

Schema description coverage is 0%, and the description does not compensate. The required 'request' object, 'rulebase', and 'device_group' parameters are left entirely unexplained, so an agent cannot determine what content the request object should contain or how the optional parameters influence the check.

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

Purpose4/5

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

The description states a specific action ('Run ... preclear checks') and a clear resource/timing ('before a rule change is considered'). It distinguishes the tool from the get/list/search siblings by framing it as a pre-change validation step. The term 'preclear' echoes the tool name, but the added 'deterministic read-only' qualifier clarifies the nature of the operation.

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

Usage Guidelines4/5

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

The description gives an explicit trigger context: use this before a rule change is considered. This is clearer than merely implying usage, but it does not enumerate alternatives or explicitly say when not to use it relative to the sibling tools, so it falls short of a 5.

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

search_policy_coverageA

Find exact duplicates, coverage, conflicts, and partial overlaps without changing Panorama.

ParametersJSON Schema
NameRequiredDescriptionDefault
requestYes
rulebaseNo
device_groupNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden of behavioral disclosure. 'Without changing Panorama' is a clear, essential non-mutation guarantee, which is especially valuable given the search/analysis nature of the tool. It does not disclose permissions or performance characteristics, but the most critical safety trait is present.

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?

The entire description is a single front-loaded sentence: it begins with the action, specifies the scope (duplicates, coverage, conflicts, overlaps), and appends the key constraint (no mutation). There is no filler, repetition, or wasted wording.

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

Completeness2/5

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

The tool has a complex, required request object and no parameter descriptions, yet the description does not explain what goes in that object or how rulebase/device_group affect the search. The output schema may document return values, but invocation semantics are far too thin for an agent to call this tool correctly without additional inference.

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

Parameters1/5

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

Schema description coverage is 0%, and the description provides no guidance on the three parameters (request, rulebase, device_group). The required 'request' object is completely opaque, with additionalProperties true and zero explanation, so an agent has no idea how to construct a valid invocation.

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 uses a specific verb ('Find') and names concrete resources (exact duplicates, coverage, conflicts, partial overlaps), while adding a non-mutation guarantee. This clearly differentiates it from siblings like get_security_rules, which retrieve rules, and preclear_rule_request, which likely modifies state.

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

Usage Guidelines3/5

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

The description implies this is a policy-analysis tool but does not explicitly state when to prefer it over siblings or list exclusions. An agent can infer the use case from the verb and resources, but there is no direct routing guidance like 'use instead of get_security_rules when assessing overlap.'

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: fetching rules, listing groups, searching for policy overlap, and running preclear checks. There is no ambiguity in what each tool does.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_, list_, search_, preclear_), using snake_case throughout. The naming is predictable and clear.

Tool Count5/5

With only 4 tools, the server is tightly scoped to read-only policy analysis and preclear workflows. Each tool earns its place, and the count falls well within the ideal 3-15 range.

Completeness4/5

The set covers the core read-only workflow: list accessible groups, fetch rules, analyze coverage/conflicts, and run preclear checks. Minor gaps exist (e.g., no direct rule-detail retrieval for a single rule), but the essential operations are present and coherent.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • LimaCharlie MCP

    geoffbelknap
    A
    license
    C
    quality
    B
    maintenance
    A local MCP server for the LimaCharlie security platform that provides investigation, administration, and content-review workflows via a broad read-only tool surface with explicit organization scoping and audit logging.
    100
    MIT

  • Cisco FMC MCP Server

    lbreukel1
    A
    license
    Not graded
    quality
    D
    maintenance
    A read-only MCP server for Cisco Firepower Management Center (FMC) 7.4.x, allowing LLMs to query firewall configuration, search network objects, and check deployment status through natural language.
    Apache 2.0

  • CloudGuard MCP

    kishoreqwerty
    F
    license
    Not graded
    quality
    C
    maintenance
    A read-only MCP server for inspecting AWS resources, detecting misconfigurations, and estimating costs across EC2, S3, and IAM, enabling agents to safely query and analyze cloud infrastructure.

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/fquiroga/panorama-mcp-server'

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