Fera MCP server for your AI

Summarize your reviews for any period, clear what is waiting for approval, answer customers in public, see which products rate worst, and look up everything a customer has sent you.

PopMCPFera

Summarize last month's reviews: average rating, stars and the lowest rated

Contact sales Connect

Supported Fera tools

Every route in Fera's API reference is here, private and public, across reviews, photos and videos, ratings, products, customers, orders, store settings and webhooks, with jobs like a review summary for any period and a moderation queue done in one call.

69 tools in the full catalog: 42 read and 27 write. 35 load by default, and the rest are found with tool search.

fera_list_public_reviews

List what shoppers can see on the store: published reviews with private customer details left out, and answers may be cached.

fera_approve_media

Publish a pending photo or video so shoppers see it.

fera_approve_review

Publish a pending review and its photos and videos, so shoppers see it and it counts towards the rating.

fera_create_review

Add a review written by a real customer, such as one moved over from another reviews app.

fera_decline_media

Decline a photo or video so shoppers do not see it.

fera_decline_review

Decline a review and its photos and videos, so shoppers do not see it.

fera_delete_media

Delete a photo or video for good.

fera_delete_review

Delete a review for good, and it leaves the store and the ratings.

fera_get_media

Read one photo or video, with its link, caption, state and product.

fera_get_review

Read one review with its product, customer, photos, videos and store reply.

fera_list_customer_reviews

List the reviews one customer wrote.

fera_list_media

List customer photos and videos.

fera_list_product_reviews

List the reviews of one product.

fera_list_reviews

List reviews about products and the store, with customer details.

fera_update_review

Change a review: heading, body, rating, state, or store_reply.

fera_create_order

Add an order, usually for a store on a custom platform.

fera_get_order

Read one order: line items, total, status, dates, addresses and customer.

fera_list_orders

List orders Fera knows about.

fera_create_webhook

Have Fera send an event to a URL.

fera_delete_webhook

Stop a webhook for good.

fera_list_webhooks

List the store's webhooks.

fera_customer_overview

Everything about one customer in one call: record, latest 10 reviews, latest 10 photos or videos and latest 10 orders.

fera_get_customer

Read one customer: name, email, location, rating and counts.

fera_get_product

Read one product with its rating and counts.

fera_list_customers

List customers.

fera_list_products

List the products Fera knows about, with ratings and counts.

fera_moderation_queue

What waits for a decision, oldest first: reviews and photos or videos pending approval or holding an edit.

fera_product_overview

Everything about one product in one call: details, rating, latest 10 reviews and latest 10 photos or videos.

fera_reply_to_review

Answer a review as the store.

fera_reviews_summary

Totals for a period, which Fera has no report or date filter for: how many reviews, average rating, count per star and per state, how many have no reply, and up to 10 of the lowest rated with ids.

fera_update_customer

Change a customer, such as name, email, display_name or is_anonymous.

fera_get_product_rating

Read one product's average rating and review count.

fera_get_store_rating

Read the store's overall average rating and how many reviews it counts.

fera_list_product_ratings

List average rating and review count per product.

fera_get_store

Read the store's settings: name, platform, url, language, plan, overall rating and counts.

fera_get_public_media

Read one photo or video as shoppers see it.

fera_get_public_product_rating

Read one product's rating as shoppers see it.

fera_get_public_review

Read one review as shoppers see it, with private customer details left out.

fera_get_public_store

Read the store details shoppers can see: name, url and overall rating.

fera_get_public_store_rating

Read the store's overall rating as shoppers see it.

fera_list_public_all_product_media

List photos and videos about any product as shoppers see them.

fera_list_public_all_product_reviews

List reviews about any product as shoppers see them, leaving out reviews about the store.

fera_list_public_media

List photos and videos shoppers can see on the store.

fera_list_public_product_media

List one product's photos and videos as shoppers see them.

fera_list_public_product_ratings

List ratings per product as shoppers see them.

fera_list_public_product_reviews

List one product's reviews as shoppers see them.

fera_list_public_store_media

List photos and videos about the store as shoppers see them.

fera_list_public_store_reviews

List reviews about the store as shoppers see them, leaving out reviews about a single product.

fera_create_media

Add a customer's photo or video from a public link: file is an https URL that Fera downloads.

fera_list_all_product_media

List photos and videos about any product, leaving out those about the store.

fera_list_all_product_reviews

List reviews about any product, leaving out reviews about the store.

fera_list_customer_media

List the photos and videos one customer sent.

fera_list_product_media

List the photos and videos of one product.

fera_list_store_media

List photos and videos about the store or overall experience, leaving out those linked to a single product.

fera_list_store_reviews

List reviews about the store or overall experience, leaving out reviews about a single product.

fera_update_media

Change a photo or video: caption, state, or which review, product or customer it belongs to.

fera_delete_order

Delete an order from Fera.

fera_mark_order_delivered

Mark an order as delivered in Fera.

fera_mark_order_fulfilled

Mark an order as fulfilled in Fera.

fera_mark_order_paid

Mark an order as paid in Fera.

fera_update_order

Change an order, such as total, line_items, addresses or is_cancelled.

fera_get_webhook

Read one webhook, with its status and last response code.

fera_test_webhook

Send a test event to a webhook's URL and refresh its status.

fera_update_webhook

Change a webhook's event_name or url.

fera_create_customer

Add a customer.

fera_create_product

Add a product to Fera, usually for a store on a custom platform.

fera_delete_customer

Delete a customer from Fera, for example when they ask to be forgotten.

fera_delete_product

Remove a product from Fera.

fera_update_product

Change a product's details in Fera, such as name, url, price, sku or tags.

Connect Fera to Claude, ChatGPT and Claude Code

Credentials off one Fera screen, then an endpoint your client signs into. Nothing to deploy, and nothing to install.

Open Fera's API keys page and copy the secret key. Paste it here. That is the only thing to enter: PopMCP finds your store and its public key from it, and there is no app to register.

Secret key••••••••••••3f7a

ConnectionVerified

Drop the PopMCP URL into Claude, ChatGPT, Claude Code, Codex or any other supported client. It signs in through PopMCP with OAuth, so your Fera credential never leaves the server.

app.popmcp.com/mcp

Claude wants to connectApprove

Ask for something harmless before the agent changes anything. Writes run as soon as it calls them, so confirm it reads the right account first.

Summarize last month's reviews: average rating, stars and the lowest rated

fera_reviews_summaryok

Then just ask for the work

“Summarize last month's reviews: average rating, stars and the lowest rated”
- reviews_summary
“What is waiting for approval? Approve the genuine ones and show me the rest”
- moderation_queue
- approve_review
- decline_review
“Draft a reply to this month's one-star reviews for me to check, then post them”
- reviews_summary
- reply_to_review
“Which products have the worst average rating?”
- list_product_ratings
“Show the rating, latest reviews and photos for our best-selling mug”
- product_overview
“Show everything jane@example.com has sent us, with her orders”
- customer_overview

Contact support View docs

Use Fera from the assistant you already open

One hosted endpoint, registered once per client. The same tools and the same permissions, whichever window the request comes from.

Claude DesktopCustom connector

Add the PopMCP URL under Customize → Connectors and the tools appear in every chat.

Claude WebCustom connector

The same endpoint, registered in the browser. Nothing to install on the machine you are working from.

ChatGPTCustom connector

CodexDesktop & CLI

Wire the endpoint into Codex or the Codex CLI when a task needs live business context, not a fixture.

OpenCodeCoding agent

ZCodeDesktop app

Add PopMCP as an MCP server in Z.ai's desktop app and work the account from the same window.

Contact support View docs

FAQ

Fera MCP server questions

What teams ask before putting Fera behind an AI client.

What do I need to connect Fera?

One value: the secret key on Fera's API keys page, at app.fera.ai/integrations/api_keys. PopMCP reads your store's name and public key with it, so there is nothing else to copy and no app to register. Copy the secret key rather than the public one, which starts with pk_.

Can the AI publish and answer reviews?

Yes. It can approve or decline reviews, photos and videos, change them, delete them, and reply as your store. A reply shows in public beside the review. If a review already has a reply, reply_to_review changes nothing unless the AI is told to replace it. Choose read-only access in PopMCP to rule all of this out.

Can it add reviews?

Yes, for reviews real customers wrote, such as ones moved over from another reviews app. The tool says so to the AI, because made-up reviews are illegal in many countries. Set a review's state to approved and it shows on the store at once. Photos and videos are added from a public link, which Fera downloads, as a tool call cannot carry a file from your computer.

How fast can it go?

Fera allows 10 requests a minute on a free account and 100 on a paid one. The summary and overview tools do several steps in one call to stay inside that. If Fera's limit stops a summary partway, it gives the totals counted so far and says it stopped early.

Can it read my reviews by date or star rating?

Fera's list has no date or rating filter, so reviews_summary reads the newest reviews and does that sorting itself, counting up to 800 for one summary. It says so when there were more than that. You can also sort products by rating with list_product_ratings.

What can't it do?

Fera's API does not change your widgets, review request emails or incentives, so you still edit those in Fera. Marking an order paid, fulfilled or delivered changes only Fera's copy: nothing ships, no money moves, and your store platform is not touched. On Shopify, Wix and other linked platforms, Fera syncs products and orders itself, so a change may be overwritten on its next sync.

Do I have to run or host the Fera MCP server myself?

No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.

Which AI clients can use this MCP server?

Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.

How do I connect Fera to Claude Code?

Connect Fera in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Fera on the consent screen. The Fera tools are then available in that session, and no Fera credential is stored on your machine.

Why do only 35 of the 69 tools load by default?

Loading 69 tool definitions into every conversation burns context before the work starts. PopMCP loads a curated 35-tool set covering the everyday workflows and keeps the rest searchable, so your AI pulls a specialist tool only when a task needs it. Every tool stays searchable, and on Scale the owner can load the full catalog for a teammate's connection.

What is the difference between a tool and a trigger?

A tool is something your AI calls, and there are 69 here. A trigger is something PopMCP watches for you: 15 Fera events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Fera.

Connect Fera to your AI in minutes

Launch a hosted MCP endpoint for Fera, keep tool access under control, and start testing real workflow prompts right away.

Connect your first MCP