MCP servers › io.github.novalo-dev › prestashop-mcp-server
MCP server · registry snapshot 2026-11-06 · last checked 2026-11-06
prestashop-mcp-server MCP server
Registry name io.github.novalo-dev/prestashop-mcp-server
O'So MCP Server for PrestaShop — the publisher's title
by novalo-dev · GitHub account (the registry's namespace rule)repository: same ownerSource ↗Website ↗
Lets Claude, ChatGPT or Cursor connect to PrestaShop, with each employee approving what they may do. — the publisher's description
Summary
io.github.novalo-dev/prestashop-mcp-server is a remote MCP server listed in the official MCP registry at version 1.2.2, under the namespace of the GitHub account novalo-dev. Its linked repository, github.com/novalo-dev/Prestashop-MCP-Server, belongs to the same GitHub account.
Record checks
5 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 2 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Repository
- public
- Last tested
- not tested
Tool list
Not read: It requires a setting the publisher marks as required (for example a URL part or a configuration value) that has no default, so we did not start it. So there is no tool-list size and no result from the three APIs.
How fresh this is
- Live-tested
- no
- Last tested
- not tested
- Latest version
- 1.2.2, published 2026-11-05 (registry, as of the 2026-11-06 snapshot)
- First listed version
- 2026-11-03 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 3 versions listed, 2026-11-03 to 2026-11-05; 3 in the 90 days before the 2026-11-06 snapshot.(versions still listed in the registry only)
Most recent 3 versions
1.2.2· 2026-11-051.2.1· 2026-11-041.2.0· 2026-11-03
- Registry data
- snapshot 2026-11-06
- Package and repository
- checked 2026-11-06
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 1.2.1 (published 2026-11-04) → 1.2.2 (published 2026-11-05), between the registry lists of 2026-11-05 and 2026-11-06.
The publisher’s GitHub release note for v1.2.2 (“O'So MCP Server 1.2.2”), published 2026-11-05.
Read the release note (the publisher’s text, shown as plain text, cut at 4,000 characters)
### Added **Switch off a whole group of tools at once.** On **Tools and prompts**, the tools are now grouped by the permission an assistant is given for them - **Orders - read**, **Orders - changes**, **Catalog - read** and so on - and each group has its own two switches, one for the assistants connected over MCP and one for the built-in assistant. A group switched off holds back every tool in it, including the ones a later update adds to it, and every prompt that needs it; the assistants are no longer offered that permission when they connect. Switching the group back on gives each tool the switch it had. The built-in assistant can read and change these group switches too, after your approval. **See which products are ready for AI assistants.** The new tool `somcp_audit_product_entities` scores each product of your catalogue on the data an answer engine needs to describe it - brand, barcode, manufacturer reference, features, a long enough description, a summary, images with captions, weight, condition, a real category and a meta description - and lists the least complete products first, naming for each one what is missing under the label of its product page. It reads one language and changes nothing; fill the gaps with the catalogue tools. **Check whether AI crawlers can read your shop.** The new tool `somcp_check_ai_crawler_access` tells you, for each of the main AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bingbot and more), whether your robots.txt lets it fetch your home page, a product page and a category page, with the exact rule that decides it, and whether those pages ask it not to index them. It reads your robots.txt and your pages and changes nothing; whether to open your shop to a crawler stays your choice, and the tool for writing the robots.txt is `somcp_generate_robots_txt`. **Check the pages buyers look for before they trust your shop.** The new tool `somcp_audit_store_policies` looks for your legal notice, terms and conditions, shipping, returns, privacy, about us and contact pages, and says for each one whether it was found and how, whether it is **Displayed**, whether **Indexation by search engines** is on, how many words it has and whether your home page links to it. It also reports the settings these pages go with: the terms to accept at checkout, returns and their time limit, and the delivery time texts of your products. When several pages could be the same one, it lists them so you choose. It changes nothing, and what these pages say stays your responsibility. **Read your shop's llms.txt.** The new tool `somcp_get_llms_txt` shows the llms.txt at the root of your shop, the plain text summary some AI tools look for, with its size, its last change and the address where it is asked for, and says whether it was written by O'So MCP Server. It warns when there is none, when your shop sits in a folder, when the file is too large, or when it does not start with a title line. llms.txt is a proposed convention, not a standard: no AI tool is bound to read it. The tool changes nothing. ### Changed **The SEO settings read now cover the rest of the SEO and URLs page.** The tool that reads the shop's SEO and URL settings now also reports the two Apache options (MultiViews and mod_security), the option that puts the attributes in the product meta title, the address pattern of the module pages, and, for each language, whether its addresses carry the ISO code - including, on PrestaShop 9, the option that keeps the default language without a prefix. Reading the settings still changes nothing, and an unexpected field is now refused instead of ignored. **The Tools and prompts lists are folded by group.** Each group shows how many of its tools or prompts are on in each column, and opens with a click; the search opens the groups it finds something in. The **Asks for** and **Requires** columns are gone, to keep the lists readable: the back office right each tool needs is listed in the tools table of th
Source: the official MCP Registry list on 2026-11-05 and on 2026-11-06; release notes from the GitHub Releases API, checked 2026-11-06.
What it is
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
This entry needs values of your own (marked < > or { } in the config below), so there is no one-click link: paste the config and fill them in.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://{shop}/module/somcp/mcpCursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"prestashop-mcp-server": {
"url": "https://{shop}/module/somcp/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"prestashop-mcp-server": {
"type": "http",
"url": "https://{shop}/module/somcp/mcp"
}
}
}Claude Code
claude mcp add --transport http prestashop-mcp-server "https://{shop}/module/somcp/mcp"Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"prestashop-mcp-server": {
"type": "streamableHttp",
"url": "https://{shop}/module/somcp/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"prestashop-mcp-server": {
"httpUrl": "https://{shop}/module/somcp/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.prestashop-mcp-server]
url = "https://{shop}/module/somcp/mcp"Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"prestashop-mcp-server": {
"url": "https://{shop}/module/somcp/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url "https://{shop}/module/somcp/mcp" --transport http- The URL contains parts in { } that the entry marks as variables; replace them with your own values.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Repository github.com/novalo-dev/Prestashop-MCP-Server | Opens publicly | matches | api.github.com · 2026-11-06 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.novalo-dev
- GitHub owner
- a personal account (novalo-dev)
- Repository
- github.com/novalo-dev/Prestashop-MCP-Server
- Stars
- 2
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-11-06; security policy read from GitHub · 2026-11-04.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating5 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 2 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-06 (security policy 2026-11-04). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about io.github.novalo-dev/prestashop-mcp-server
Answered from the data aboveWho publishes io.github.novalo-dev/prestashop-mcp-server?
The registry ties the namespace io.github.novalo-dev to the GitHub account novalo-dev; only its owner can publish under it. Its linked repository, github.com/novalo-dev/Prestashop-MCP-Server, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.
Is io.github.novalo-dev/prestashop-mcp-server safe to install?
We do not rate servers as safe or unsafe. 5 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Has io.github.novalo-dev/prestashop-mcp-server been security tested?
No. It requires a setting the publisher marks as required (for example a URL part or a configuration value) that has no default, so we did not start it.
Does io.github.novalo-dev/prestashop-mcp-server publish a security policy?
Yes: its repository has a public security policy (github.com/novalo-dev/prestashop-mcp-server/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Where is the source code of io.github.novalo-dev/prestashop-mcp-server?
In github.com/novalo-dev/Prestashop-MCP-Server, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
Has it been tested?
Feature #1It requires a setting the publisher marks as required (for example a URL part or a configuration value) that has no default, so we did not start it. — the server's own choice
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.novalo-dev/prestashop-mcp-server: MCP server record.” Data checked 2026-11-06. https://protocolprobe.com/mcp/servers/io.github.novalo-dev/prestashop-mcp-server
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.novalo-dev/prestashop-mcp-server)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology