Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Xyla AI is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
20
tools declared
remote
at its publisher
—
calls last 7d
What it does
Social posts for Shopify and WooCommerce stores: approve posts, see results, change settings.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http xyla-ai-mcp https://app.xyla.ai/mcp
# 2 — ask your agent for something these tools do
# whoami, shop_overview, upcoming_posts and 17 more
Xyla AI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
XYAll 1 server
xyla1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http xyla-ai-mcp https://app.xyla.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Shows which Xyla shop this connection acts for and whether it can only read or can also make changes.
No parameter schema on file.
Summarises this Xyla shop: its plan, AI credits left, whether autopilot is on, how many posts wait for approval, the next 3 posts due, and any social account that needs fixing.
No parameter schema on file.
Lists the posts this Xyla shop will publish, day by day, for up to 7 days from a start date (the shop's today if left out). Each post has its platforms, send time in the shop's time zone, type, caption and media links. Posts waiting for approval are not here: use pending_approvals.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start_date | string | no | First day to show, as YYYY-MM-DD in the shop's time zone. Defaults to today. |
| days | integer | no | How many days to show, 1 to 7. Defaults to 7. |
Lists the posts in this Xyla shop that wait for the merchant's approval before they are scheduled, 12 per page, with captions and media links. When the shop is still on its first batch, returns that batch as one draft: it is approved as a whole, not post by post.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | Page number, starting at 1. Defaults to 1. |
Shows how this Xyla shop's published posts performed over the last 7, 14, 30 or 90 days: reach, views, engagement, followers per account, and the top posts. Same data as the Insights page in Xyla.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| window_days | integer | no | How many days back to look. Defaults to 30. |
Shows each social account connected to this Xyla shop: connected, expiring soon, expired, needs reconnecting, restricted or disconnected, and how many upcoming posts a broken account is blocking.
No parameter schema on file.
Shows the shop's current Xyla settings for one setting group, with the ids change_settings needs and how each field works. Call it without tool to list the setting groups. Read a group before changing it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool | string | no | The setting group to read. Leave out to list them. |
Changes the shop's Xyla settings in one setting group (or a few related ones) and returns each value before and after plus an undo id. Every change in a call applies, or none does. Read the group with get_settings first, and confirm the change with the merchant before calling this. Changes affect posts made from now on, not posts already scheduled or published.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool | string | yes | The setting group to change. logo, outro, post_type_on_off, billing cannot be changed from chat; naming one returns the web page to change it on. |
| actions | array | yes | The changes, applied together: all of them or none. |
Puts back the settings a change set replaced, using the undo id from change_settings or change_history. The whole set is undone, or nothing is. It is refused when a setting has changed again since, so a newer choice is never overwritten.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| undo_id | string | yes | The undo id, exactly as change_settings or change_history gave it. |
Lists recent changes to the shop's Xyla settings, newest first: what changed, before and after, who made it (the merchant, Xyla or the assistant), and the undo id to pass to undo_change.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many changes to list. Defaults to 10. |
Makes a one-use link that connects a social account to this Xyla shop, or reconnects a broken one. Give the merchant the link to open in their browser; it works once and expires in 10 minutes, and asks for the store's email. To reconnect an account from connection_status, pass its social_media_account_id. Instagram has two ways in: instagram_direct (Instagram Login, the usual choice) and instagram
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | yes | The platform to connect. |
| social_media_account_id | integer | no | The account to reconnect, from connection_status. Leave out to connect a new account. |
Approves posts in this Xyla shop that are waiting for approval, by their IDs from pending_approvals. Each approved post takes the next free slot in the schedule; nothing publishes straight away. Posts in the shop's first batch cannot be approved one by one: use approve_first_batch for those.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_ids | array | yes | The IDs of the posts to approve, from pending_approvals. |
Rejects one post in this Xyla shop that is waiting for approval, by its ID from pending_approvals. The post is cancelled and will not be published.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_id | integer | yes | The ID of the post to reject, from pending_approvals. |
Approves this Xyla shop's first batch of posts as a whole. When the shop can publish, this also turns autopilot on in include mode (the posts already made are scheduled and nothing is deleted), and releases posts held for review into the schedule. Posts go out at their scheduled times, not straight away.
No parameter schema on file.
Starts a fix for one post's image or video in this Xyla shop. Xyla first checks the media for a problem on its side, which makes the fix free; otherwise the fix costs credits. Nothing is changed or charged yet. Then call post_fix_status with the audit_id to learn the cost, tell the merchant, and call confirm_post_fix only once they agree.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_id | integer | yes | The ID of the post to fix. |
| what_to_change | string | yes | What the merchant wants changed, in their words. |
Reports where a post fix from request_post_fix stands in this Xyla shop: still being checked, free (Xyla found a problem on its side), or how many credits it costs. After confirm_post_fix, reports whether the fix is running, done or failed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | integer | yes | The audit_id from request_post_fix. |
Runs a post fix that request_post_fix started in this Xyla shop, with the change the merchant asked for. Call post_fix_status first and tell the merchant whether it is free or what it costs; a fix that is not free uses the shop's credits. The new image or video replaces the post's media when it is ready.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| audit_id | integer | yes | The audit_id from request_post_fix. |
Turns Xyla autopilot on or off for this shop. With autopilot on, Xyla makes and schedules posts by itself. mode include (the default) keeps posts already made and adds them to the schedule. mode fresh DELETES every post not yet scheduled, including posts the merchant made by hand, then builds a new schedule: call it first without confirm_delete_count to get the number of posts it deletes, tell the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| on | boolean | yes | true turns autopilot on, false turns it off. |
| mode | string | no | Only when turning on. include keeps existing posts; fresh deletes unscheduled posts first. |
| confirm_delete_count | integer | no | Fresh mode only: the number of posts to delete, from the previous set_autopilot reply, after the merchant agreed. |
Shows what Xyla would post for an online store, with no Xyla account. Give it the store's web address (Shopify or WooCommerce). Xyla reads the store's brand (logo, colours, niche) and makes 3 sample social media posts from the store's own product photos, with captions. Returns a preview token at once; the posts take about 3 minutes and the card shows them as they finish. A store previewed in the l
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The store's web address, such as yourstore.com or yourstore.myshopify.com. |
Checks a store preview started with preview_store: the brand Xyla found and the sample posts finished so far. done is true once the preview is ready or has stopped. While the preview card is showing it updates itself, so only call this when no card is shown, every few seconds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | The preview token preview_store returned. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Xyla AI or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 23 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest6df0380715de81f774ce91cdd9cd69c7b5a16140d13b46c2115fd332c0fe8f9b
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| whoami | no tags | |
| shop_overview | no tags | |
| upcoming_posts | no tags | |
| pending_approvals | no tags | |
| insights | no tags | |
| connection_status | no tags | |
| get_settings | no tags | |
| change_settings | state-write | state-write: declares readOnlyHint: false |
| undo_change | state-write | state-write: declares readOnlyHint: false |
| change_history | no tags | |
| connect_account | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| approve_posts | state-write | state-write: declares readOnlyHint: false |
| reject_post | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| approve_first_batch | state-write | state-write: declares readOnlyHint: false |
| request_post_fix | state-write | state-write: declares readOnlyHint: false |
| post_fix_status | no tags | |
| confirm_post_fix | state-write | state-write: declares readOnlyHint: false |
| set_autopilot | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| preview_store | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| preview_status | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest6df0380715de81f7
Scanned2026-10-23
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Xyla AI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.