Peec AI MCP

The full competitive breakdown matrix: for every brand-perception attribute, the average prominence of each brand (the project's own brand and its competitors) across AI answers. score is 0-100 — higher means the brand tends to be mentioned earlier when AI talks about that attribute; display as-is, never multiply by 1…

Untrusted display-only summary

The recurring arguments AI models make against the project's brand when a buyer is deciding. score is average prominence per AI answer from 0 to 100; display it as-is. members contains the raw phrasings folded into each objection. Data is aggregated across all objection runs and has no date range. Returns columnar JSO…

Untrusted display-only summary

The sources AI models retrieved when asked about one objection. Pass the objection name exactly as returned by get_brand_perception_objections; an unknown name returns an empty result. Data is aggregated across all objection runs and has no date range. citation_rate is an average, not a percentage. Returns columnar JS…

Untrusted display-only summary

Get a report on brand visibility, sentiment, and position across AI search engines. Results are aggregated for the entire date range by default. Use the "date", "week", or "month" dimension for time-bucketed breakdowns (daily, ISO week, or calendar month). When the range spans many days, prefer "week" or "month" over…

Untrusted display-only summary

Get the full content of a single chat (one AI engine's response to one prompt on one date). Returns: - messages: the user prompt and assistant response(s) - brands_mentioned: brands detected in the response with their position - sources: URLs the model retrieved, with citation counts and position - queries: search que…

Untrusted display-only summary

Aggregate counts and rich-answer-feature shares over a project's chats for a date range. Answers questions like "how many chats", "what share rendered a map / shopping / web-search / ad / comparison result", and "how many distinct prompts / engines / countries does tag X span" — use it instead of paging through list_c…

Untrusted display-only summary

Get a report on source domain visibility and citations across AI search engines. Results are aggregated for the entire date range by default. Use the "date", "week", or "month" dimension for time-bucketed breakdowns (daily, ISO week, or calendar month). When the range spans many days, prefer "week" or "month" over "da…

Untrusted display-only summary

Get one product's detailed metrics over a date range — the drill-down companion to list_products, which returns a thin row per product. Returns {data, primary_currency}, where data is null if the product is not in the project. data always includes: - id, name, brand, source (CATALOG or LLM), first_seen_at - visibility…

Untrusted display-only summary

Read a project's brand profile — the description, industry, brand-identity adjectives, target markets, audience distribution, and product/service list that Peec uses to generate prompt suggestions. Returns { profile } where profile may be null if the project hasn't been profiled yet. Call this before set_project_profi…

Untrusted display-only summary

Read the authoritative status of a run returned by generate_prompt_suggestions. QUEUED and RUNNING are non-terminal; SUCCEEDED and FAILED are terminal. A successful run can produce zero suggestions. After success, call list_prompt_suggestions to review the current suggestions.

Untrusted display-only summary

Compare the qualitative characteristics and features that AI engines associate with a product (or the whole catalog) against competitors. These attributes are extracted from shopping answers and are qualitative — for the numeric shopping metrics (visibility, win rate, position) use get_shopping_summary or get_shopping…

Untrusted display-only summary

Return catalog-wide shopping metrics over a date range — avg_visibility, avg_win_rate, and avg_position, each with a period-over-period delta — as a single aggregated row across the filtered scope. Deltas compare against previous_start_date/previous_end_date when given, else the auto-derived previous period. For a per…

Untrusted display-only summary

Return a per-bucket shopping time series (visibility, win_rate, avg_position, sov) for specific products or global brands over a date range. Requires bucket (day/week/month) and exactly one of product_ids or brand_ids. Returns { entity_type, series[] }, one series per entity with a points array; has_data flags buckets…

Untrusted display-only summary

Fetches and returns the content of a URL for downstream analysis — the markdown Peec extracted from the page. Returns the exact content Peec's pipeline indexed, with no extra fetch. Works for any URL Peec has scraped for the project; you do not need to call get_url_report first. If Peec has no record of the URL it ret…

Untrusted display-only summary

Get a report on source URL visibility and citations across AI search engines. Results are aggregated for the entire date range by default. Use the "date", "week", or "month" dimension for time-bucketed breakdowns (daily, ISO week, or calendar month). When the range spans many days, prefer "week" or "month" over "date"…

Untrusted display-only summary

List all known AI crawler/agent bots that visit the site (e.g. GPTBot, ClaudeBot, PerplexityBot). Each bot has an ID, provider, and type. Bot types: - training: crawlers that collect data for model training (e.g. GPTBot, ClaudeBot) - search: bots that retrieve content for AI-powered search (e.g. PerplexityBot) - userQ…

Untrusted display-only summary

The editable attribute taxonomy behind brand perception: every cluster with its id, label and the raw extracted attributes grouped under it. Use this to resolve the cluster_id values edit_brand_perception_attribute_clusters needs, and to see attributes that are grouped wrongly. Prefer get_brand_perception_brand_attrib…

Untrusted display-only summary

List brands tracked in a project — includes the user's own brand and competitors. Use this tool to resolve brand names to IDs before filtering reports (brand_id filter), and to label brand IDs from report output with their human-readable names before presenting results. Returns columnar JSON: {columns, rows, rowCount,…

Untrusted display-only summary

List the social channels configured for a project's own brand and competitors. Optionally filter by brand ID. Returns columnar JSON with id, brand_id, platform, channel_id, and channel_handle.

Untrusted display-only summary

List a project's product categories. Categories are an org-wide tree (e.g. Footwear > Shoes > Running Shoes); each row carries its full `path` and its `parent_id`, so the flat list rebuilds the tree. Use a row's `id` in the `category_ids` of create_products or update_products to categorize products. Returns columnar J…

Untrusted display-only summary

List chats (individual AI responses) for a project over a date range. Each chat is produced by running one prompt against one AI engine on a given date. Filters: - brand_id: only chats that mentioned the given brand - prompt_id: only chats produced by the given prompt - model_id: only chats from the given AI engine (c…

Untrusted display-only summary

List the custom domain classifications defined for a project. These complement the built-in classifications (Corporate, Competitor, Editorial, Institutional, Other, Reference, UGC, You, Related) and can be assigned to domains via assign_domain_classification. Returns columnar JSON: {columns, rows, rowCount, totalCount…

Untrusted display-only summary

Search Peec's global brand catalog — the shared registry of real-world brands (e.g. Nike, Apple) that products attach to. Use it to find the global_brand_id for a brand before creating products with create_products. This is NOT the same as list_brands: list_brands returns the brands you track inside a project (your ow…

Untrusted display-only summary

List the merchants (sellers, e.g. Amazon / eBay) whose product offers surfaced in AI answers, ranked over a date range. Each row carries mention_count, share_of_voice (0–1: this merchant's mentions over all merchants' mentions in the filtered population), win_rate (0–1 buy-box rate: position-1 mentions over all mentio…

Untrusted display-only summary

List the AI engine channels tracked by Peec. A model channel is a stable identifier for an AI engine (e.g. "openai-0" = ChatGPT UI) that persists even as the underlying model is upgraded — use it to filter or break down reports by engine without worrying about model version changes. Use this tool to resolve channel de…

Untrusted display-only summary

Deprecated — prefer list_model_channels, which returns stable channel IDs that survive model upgrades. List AI engines (models) tracked by Peec. Use this tool to resolve model names (e.g., "ChatGPT", "Perplexity", "Gemini") to IDs before filtering reports (model_id filter/dimension), and to label model IDs from report…

Untrusted display-only summary

List a project's products with headline metrics over a date range, filtered by the shopping filter pack. Returns columnar JSON: {columns, rows, rowCount, totalCount}. rowCount is the rows in this page; totalCount is the total matching records ignoring limit/offset. Columns: id, name, brand, source (CATALOG = claimed/u…

Untrusted display-only summary

List active projects the authenticated user has access to. By default, only projects with an active status (CUSTOMER, PITCH, TRIAL, ONBOARDING, API_PARTNER) are returned — this is what you want in almost every case. Only set include_inactive to true if the user asked for a specific project that wasn't in the active li…

Untrusted display-only summary

List prompts (conversational questions tracked daily across AI engines) in a project. Supports filtering by topic_id, tag_id, country_code, and is_archived. Returns only active prompts by default — pass is_archived=true to list archived prompts instead (e.g. when a prompt_id from older report output isn't found among…

Untrusted display-only summary

List a project's prompt suggestions — prompts generated by Prompt discovery and awaiting review, which are not tracked and produce no data until accepted. Accept or reject them with finalize_prompt_suggestions. Their ids are prefixed `pr_`, and a suggestion keeps that id when accepted, so the accepted prompt is findab…

Untrusted display-only summary