glpi-mcp
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., "@glpi-mcpget CIA fields for computer 42"
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.
GLPI MCP Server
A Model Context Protocol (MCP) server for interacting with GLPI (Gestionnaire Libre de Parc Informatique) via its REST API.
This server empowers AI assistants (like Claude) to manage your GLPI inventory, tickets, and specifically CIA (Confidentiality, Integrity, Availability) security fields directly.
Features
Core GLPI Operations:
List, Get, Create, Update, Delete items (Computers, Tickets, Users, etc.).
Native GLPI Search API support.
Advanced CIA Management:
Dedicated tools to view and update Security/CIA fields (
data_sensitivity,critical_asset,max_downtime).Batch Updates: Update thousands of assets in a single request.
Future-Proof: Supports custom/future plugin fields via dynamic parameters without code changes.
Robust Authentication:
Supports modern header-based auth and legacy body-based auth (
/apirest.php).Built-in handling for OAuth plugin quirks.
Related MCP server: GLPI MCP
Installation
npx -y glpi-mcpConfiguration
You need to provide the following environment variables to authenticate with your GLPI instance:
Variable | Description | Required | Example |
| The full URL to your GLPI API endpoint. | Yes |
|
| The unique App Token generated in GLPI (Setup > General > API). | Yes |
|
| The User Token from your personal settings. | Yes* |
|
| OAuth Access Token (if using OAuth). | No** |
* Either GLPI_USER_TOKEN or GLPI_OAUTH_TOKEN is required.
** GLPI_OAUTH_TOKEN takes precedence if both are provided.
Claude Desktop Configuration
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"glpi": {
"command": "npx",
"args": ["-y", "glpi-mcp"],
"env": {
"GLPI_API_URL": "https://glpi.example.com/apirest.php",
"GLPI_APP_TOKEN": "your_app_token_here",
"GLPI_USER_TOKEN": "your_user_token_here"
}
}
}
}Available Tools
1. Standard Item Management
glpi_list_items: List generic items (Computer, Ticket, User, etc.).glpi_get_item: Get details of a specific item.glpi_create_item: Create a new item (e.g., Ticket).glpi_update_item: Update standard fields of an item.glpi_delete_item: Delete or purge an item.glpi_search: Advanced search queries.
2. CIA / Security Fields Management 🛡️
Designed for working with the Generic Object or Fields plugins that add CIA ratings to assets.
glpi_get_cia_fields
View the current security ratings of an asset.
Args:
itemType(e.g., "Computer"),id.
glpi_update_cia_fields
Update security ratings for a single asset.
Args:
itemType,iddata_sensitivity(e.g., "Confidential")critical_asset(1 or 0)max_downtime(integer)other_fields(JSON string): Important! Use this to update any new fields you add to GLPI later without updating this server.Example:
'{"new_custom_field": "some_value"}'
glpi_update_cia_fields_batch
Update security ratings for multiple assets at once. Ideally used by scripts or for bulk policy application.
Args:
itemTypeids(Comma-separated string:"42, 43, 44")data_sensitivity,critical_asset,max_downtimeother_fields
Examples
Batch Update Computers
Assign "Confidential" sensitivity to Computers with IDs 100, 101, and 102.
{
"name": "glpi_update_cia_fields_batch",
"arguments": {
"itemType": "Computer",
"ids": "100, 101, 102",
"data_sensitivity": "Confidential",
"critical_asset": 1
}
}Future-Proofing with other_fields
If you add a new field called compliance_level to GLPI tomorrow, you can update it immediately:
{
"name": "glpi_update_cia_fields",
"arguments": {
"itemType": "Computer",
"id": 50,
"other_fields": "{\"compliance_level\": \"high\"}"
}
}Troubleshooting
2FA/OTP Error on Publish: If you are trying to publish this package yourself and see OTP errors, use the provided helper script:
./publish_with_otp.sh.403 Forbidden: Verify your
GLPI_APP_TOKENandGLPI_USER_TOKEN. Ensure the user has write access to the specific assets.Authorization Header Missing: Typical with the GLPI OAuth plugin. Ensure you are using the
/apirest.phpendpoint in your URL, or configure the plugin to acceptuser_token.
License
ISC
Available Tools
9 toolsglpi_create_itemD
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | JSON string representing the item fields | |
| itemType | Yes | The type of item to create |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_delete_itemD
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the item to delete | |
| force | No | Permanently delete (purge) if true | |
| itemType | Yes | The type of item to delete |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_get_cia_fieldsD
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the item | |
| itemType | Yes | The type of item (e.g. Computer, NetworkEquipment, VirtualMachine) | |
| endpoint_override | No | Manual override for the plugin endpoint |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_get_itemD
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the item | |
| itemType | Yes | The type of item (e.g. Computer, Ticket) | |
| with_disks | No | Show associated disks | |
| get_hateoas | No | Show HATEOAS links | |
| with_devices | No | Show associated devices | |
| with_softwares | No | Show associated softwares | |
| expand_dropdowns | No | Show details for dropdown fields (params: expand_dropdowns=true) | |
| with_connections | No | Show associated connections |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_list_itemsD
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Field to sort by | |
| order | No | Sort order | |
| range | No | Range of items to return (e.g. "0-10") | |
| itemType | Yes | The type of generic object to list (e.g. Computer, Ticket, User) | |
| is_deleted | No | Include deleted items | |
| searchText | No | Filter/search criteria if simple text search is supported by basic list |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_searchD
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Basic query string | |
| itemType | Yes | The item type to search (e.g. Computer) | |
| rawParams | No | JSON string for advanced query parameters directly passed to search endpoint |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_update_cia_fieldsD
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the item | |
| itemType | Yes | The type of item (e.g. Computer) | |
| max_downtime | No | DEPRECATED | |
| other_fields | No | JSON string for other fields | |
| critical_asset | No | DEPRECATED | |
| integrityfield | No | Integrity Score (1-5) | |
| data_sensitivity | No | DEPRECATED | |
| availabilityfield | No | Availability Score (1-5) | |
| endpoint_override | No | Manual override for the plugin endpoint | |
| confidentialityfield | No | Confidentiality Score (1-5) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_update_cia_fields_batchD
| Name | Required | Description | Default |
|---|---|---|---|
| ids | Yes | Comma-separated list of IDs to update (e.g. "42,43,44") | |
| itemType | Yes | The type of item (e.g. Computer) | |
| other_fields | No | JSON string for other/future fields | |
| integrityfield | No | Integrity Score (1-5) | |
| availabilityfield | No | Availability Score (1-5) | |
| endpoint_override | No | Manual override for the plugin endpoint | |
| confidentialityfield | No | Confidentiality Score (1-5) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
glpi_update_itemD
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the item to update | |
| input | Yes | JSON string representing the fields to update | |
| itemType | Yes | The type of item to update |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no 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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
9 tool updates
v1.2.5- First observed
glpi_create_item - First observed
glpi_delete_item - First observed
glpi_get_cia_fields - First observed
glpi_get_item - First observed
glpi_list_items - First observed
glpi_search - First observed
glpi_update_cia_fields - First observed
glpi_update_cia_fields_batch - First observed
glpi_update_item
TDQS
Scored across 9 tools
The CRUD operations (list, create, get, update, delete) are clearly distinct, and the CIA fields tools are separate from item tools. However, glpi_search may overlap with glpi_list_items in function, and the generic 'item' term could cause confusion without descriptions.
Most tools follow a consistent verb_noun pattern (e.g., glpi_list_items, glpi_create_item), but glpi_search breaks the pattern by omitting the object. Overall, naming is clear and predictable.
With 9 tools, the server is well-scoped for basic GLPI item management and CIA field handling. The count is appropriate, neither too sparse nor overwhelming.
The tool set covers full CRUD for items, search, and specialized CIA field operations. Minor gaps exist, such as batch create/delete or listing item types, but the core functionality is complete.
Maintenance
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
Connect any AI assistant to Syncro: manage tickets, invoices, customers, assets, and more.
- PlixanaOAuthcom.plixana
Operate the Plixana CRM from any AI: contacts, deals, quotes, WhatsApp and metrics.
- mcp-serverOAuthcom.make
Give your AI agents the tools to build, manage, and run automation workflows.
- mcpOAuthcom.vibgrate
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create, search, and manage OTRS tickets and configuration items via the OTRS API.7Apache 2.0
- AlicenseBqualityCmaintenanceMCP server allowing an AI assistant to interact directly with your GLPI instance via its REST API, enabling ticket management, knowledge base operations, and statistics.404-
- AlicenseBqualityDmaintenanceIntegrates with GLPI IT4Solução API v2.3 (OAuth2) to manage tickets, computer inventory, and configuration parameters, with safety features like dry-run and rollback.24MIT
- AlicenseAqualityAmaintenanceEnables AI assistants to perform full CRUD operations on Snipe-IT inventory systems, managing assets, users, licenses, and more via 39 tools.4027MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/maimik/glpi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server