Skip to main content

GLPI client

Project description

This repo contains code for a MCP interacting with GLPI API to allow consuming it from any LLM. Additionally a lightweight client is available

Available tools
create_reservation
delete_reservation
info_computer
info_reservation
get_user
list_computers
list_reservations
list_users
update_computer
update_reservation

Requirements

  • Available glpi instance
  • Valid user and API token

Installation

You can either run as a container or install dependencies locally

pip3 install glpic

Using MCP

STDIO

Include the following configuration snippet In VSCode or Claude Desktop:

"mcpServers": {
    "glpi": {
        "command": "python3",
        "args": ["/path/to/glpic/src/glpic/mcp_server.py", "--stdio"],
        "env": {
            "GLPI_URL": "https://server/apirest.php",
            "GLPI_USER": "myuser",
            "GLPI_TOKEN": "mytoken"
            }
        }
    }

Streamable HTTP

For Streamable HTTP, first start the server in a terminal:

glpimcp

or via a container (with additional env variables to avoid defining headers on client side)

podman run -p 8000:8000 -d --name glpi --entrypoint=/usr/local/bin/glpimcp quay.io/karmab/glpic

You can also set env variables prior to launching or in the container to avoid defining headers on client side). For instance

podman run -p 8000:8000 -d --name glpi -e GLPI_URL=https://glpiserver/apirest.php -e GLPI_USER=myser -e GLPI_TOKEN=mytoken --entrypoint=/usr/local/bin/glpimcp quay.io/karmab/glpic

You can then point to the server from your client with a modified snippet and specifying credentials via headers if needed

"mcpServers": {
         "glpi": {
             "command": "/usr/local/bin/npx",
             "args": ["mcp-remote", "http://your_server:8000/mcp", "--allow-http",
             "--header", "GLPI_URL: https://glpiserver/apirest.php",
             "--header", "GLPI_USER: myuser",
             "--header", "GLPI_TOKEN: mytoken"]
        }
    }

For Claude Code, you can add the mcp directly from command line:

claude mcp add --transport http glpi http://your_server:8000/mcp -H "GLPI_URL: https://myserver/apirest.php" -H "GLPI_USER: myuser" -H "GLPI_TOKEN: mytoken"

Using client

Store your creds in any env file such as glpic.env.sample and set data accordingly. You can then use glpic and access similar functions

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

glpic-99.0.202510220836.tar.gz (9.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

glpic-99.0.202510220836-py3-none-any.whl (9.2 kB view details)

Uploaded Python 3

File details

Details for the file glpic-99.0.202510220836.tar.gz.

File metadata

  • Download URL: glpic-99.0.202510220836.tar.gz
  • Upload date:
  • Size: 9.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for glpic-99.0.202510220836.tar.gz
Algorithm Hash digest
SHA256 2a37d5e164e47e083884ecb242feaf77651f0ec3a24dcfcce96f6e72fb3e8c98
MD5 72e770d07870cc174a0e7b42ec038daf
BLAKE2b-256 3b21722877b5f9c7b388b71627b0c81a3962d20cb0d674d5e6961841ad058549

See more details on using hashes here.

File details

Details for the file glpic-99.0.202510220836-py3-none-any.whl.

File metadata

File hashes

Hashes for glpic-99.0.202510220836-py3-none-any.whl
Algorithm Hash digest
SHA256 1eff65e27a6f018c9cfa0fc5f9e94d4d6483a579714fc215c704726e67f0f950
MD5 db25d5471ceabdae94dbeb9a7e5c0daf
BLAKE2b-256 a650d0731646dd1c3afbcafc9c7e0e0bbb5e2812935276ce99ac1f326bc0cc2d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page