Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Description from the maker (original English)
GLPI helpdesk and assets in Claude: find tickets, follow up and reassign after a yes.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
GLPI_URL, GLPI_LOGIN, GLPI_PASSWORD, GLPI_SAMPLEValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"glpi": {
"command": "uvx",
"args": [
"mojood-glpi-mcp",
"--stdio"
],
"env": {
"GLPI_URL": "your-value",
"GLPI_LOGIN": "your-value",
"GLPI_PASSWORD": "your-value",
"GLPI_SAMPLE": "your-value"
}
}
}
}Run this in your terminal
claude mcp add glpi --env GLPI_URL=your-value --env GLPI_LOGIN=your-value --env GLPI_PASSWORD=your-value --env GLPI_SAMPLE=your-value -- uvx mojood-glpi-mcp --stdioFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"glpi": {
"command": "uvx",
"args": [
"mojood-glpi-mcp",
"--stdio"
],
"env": {
"GLPI_URL": "your-value",
"GLPI_LOGIN": "your-value",
"GLPI_PASSWORD": "your-value",
"GLPI_SAMPLE": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"glpi": {
"type": "stdio",
"command": "uvx",
"args": [
"mojood-glpi-mcp",
"--stdio"
],
"env": {
"GLPI_URL": "your-value",
"GLPI_LOGIN": "your-value",
"GLPI_PASSWORD": "your-value",
"GLPI_SAMPLE": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
GLPI_SAMPLE envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account askmojood, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: GLPI_URL, GLPI_LOGIN, GLPI_PASSWORD
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Vexa, emailmd, MCP WhatsApp Cloud
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Ask Claude about your IT helpdesk and assets in plain words: what's urgent and who owns it, what a person holds and whether any of it is broken, what a ticket says. Add follow-ups and reassign tickets from the same chat, with a confirmation step before anything changes.
Built by Mojood Connect as a working demo for GLPI. It runs against any GLPI 9.5–12 through its REST API. This repository includes a local GLPI with SAMPLE data for the IT department of a made-up company, Harbor Trading, so you can try it without touching a real instance.
| Tool | What it does | Changes anything? |
|---|---|---|
find_tickets | Find tickets, highest priority first: status, requester, technicians, groups, deadline, linked assets | No |
get_ticket | One ticket with its description and every follow-up in order, private ones marked | No |
person_overview | The assets a person holds (state, and any open ticket about each) and the tickets they asked for | No |
needs_attention | Tickets with no owner, past their time to resolve, high priority and above, waiting on the requester | No |
add_followup | A follow-up on a ticket: private to technicians unless asked otherwise | Yes, after confirmation |
update_ticket | Reassign to a group, add a technician, or change the priority | Yes, after confirmation |
How changes are made safe. A call to add_followup or update_ticket without a confirmation changes nothing: it returns a plain summary ("On #1 ("VPN drops every 10 minutes at the Riyadh office"): reassign it to Network team (from Service desk).") and a one-time code. The change happens only when the same request comes back with that code, within 10 minutes. A code works once, and only for the request it was issued for. The server's instructions tell the model to show the summary and wait for the user's yes. Follow-ups carry "via Claude (Mojood Connect demo)", and GLPI records every change in the ticket's history under the signed-in user.
The server signs in as one GLPI user and acts with that user's profile and rights.
Needs Docker (with Compose), uv and Python 3.13.
scripts/reset.sh # local GLPI on http://localhost:8095, filled with the SAMPLE helpdesk
uv run --env-file .env glpi-mcp # MCP server on http://127.0.0.1:8006/mcp (Streamable HTTP)
docker/compose.yml follows GLPI's own docker-compose.example.yml (glpi-project/docker-images), pinned to GLPI 12.0.1 and MySQL 8.4, on 127.0.0.1 only and in UTC. scripts/up.sh gives GLPI's default accounts (glpi, tech, normal, post-only) generated passwords, creates the demo's API user and switches the REST API on; every password stays in the git-ignored files docker/.env and .env, and nothing is printed.
Claude Desktop: add this to claude_desktop_config.json (Settings › Developer), with the path to this folder:
{
"mcpServers": { "glpi": { "command": "uv", "args": ["run", "--directory", "/path/to/glpi-mcp", "--env-file", "/path/to/glpi-mcp/.env", "glpi-mcp", "--stdio"] } } }
Then ask: "What urgent tickets are open, and who owns them?", "What does Sara have, and is any of it broken?", "Add a note to the VPN ticket that the firewall logs point to the IPsec tunnel, and reassign it to the network team."
Your own GLPI: set GLPI_URL, GLPI_LOGIN, GLPI_PASSWORD (a GLPI user; the REST API and login-credential access switched on in Setup › General › API) and GLPI_SAMPLE=0.
Harbor Trading's IT: three sites, three groups (Service desk, Network team, Field support), four technicians, eight staff, 16 assets (laptops, monitors, phones, warehouse scanners) and ten tickets. Times are set relative to the moment it is seeded, so there is always a major incident with no owner, two tickets past their deadline, one waiting on the requester and some solved history. Everyone and everything in it is made up.
uv run --env-file .env pytest # unit tests (a fake GLPI API), plus live tests when the local GLPI runs
This demo signs in as one user. A production server for GLPI customers would add sign-in through GLPI 11+'s OAuth for each technician, so Claude sees exactly their entities and profile; hosting with an audit log of every tool call; and more of the API (problems and changes, knowledge base, contracts, software and licences). That is what Mojood Connect builds.
Apache 2.0. GLPI is a trademark of Teclib'; this project is not made or endorsed by Teclib'.