Peec AI MCP for AI agents

Agents read Peec AI MCP at once. Changes and sends are held for a person's approval by default.

About Peec AI MCP

Peec AI MCP lets agents analyze authorized AI-search visibility, competitors, citations, sources, sentiment, topics, and trends, and manage supported project configuration with confirmation.

What an agent can do in Peec AI MCP

Every Peec AI MCP action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.

Runs at once (reads)

Looks things up in Peec AI MCP without asking first. 44 actions.

  • Get actionsGet Peec's opportunity-scored action recommendations for improving brand visibility in AI search engines. **Always call with `scope=overview` first** to see which slices have the biggest opportunity,
  • Get agent visitsAggregate AI agent visit counts from access logs over a date range. Without group_by: returns total visit count as a single {visits: N} row. With group_by: returns one row per distinct value of the ch
  • Get brand perception attribute rankingsHow the project's own brand ranks against competitors for each brand-perception attribute. ranking is the own brand's position among every brand scored for the attribute, ordered by average prominence
  • Get brand perception attribute sourcesThe sources feeding one brand-perception attribute: the URLs AI answers cited when describing the brand with this attribute. Pass the attribute name exactly as returned by get_brand_perception_brand_a
  • Get brand perception brand attributesHow AI models describe the project's own brand: attribute clusters (e.g. "Luxury", "Racing Heritage") with a prominence score. score is 0-100 — the attribute's average prominence per AI answer; higher
  • Get brand perception competitive breakdownThe 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 — high
  • Get brand perception objectionsThe 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 phrasin
  • Get brand perception objection sourcesThe 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 aggrega
  • Get brand reportGet 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-b
  • Get chatGet 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 re
  • Get chats reportAggregate 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 r
  • Get domain reportGet 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-buck
Show all 44
  • Get productGet 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 prod
  • Get project profileRead 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. Re
  • Get prompt suggestion generationRead 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. A
  • Get shopping attributesCompare 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 q
  • Get shopping summaryReturn 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. De
  • Get shopping trendReturn 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
  • Get url contentFetches 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
  • Get url reportGet 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-buckete
  • List botsList 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 tr
  • List brand perception attribute clustersThe 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_percep
  • List brandsList 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 re
  • List brand social channelsList 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.
  • List categoriesList 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.
  • List chatsList 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
  • List domain classificationsList the custom domain classifications defined for a project. These complement the built-in classifications (Corporate, Competitor, Editorial, Institutional, Other, Reference, UGC, You, Related) and c
  • List global brandsSearch 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 c
  • List merchantsList 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 ov
  • List productsList 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
  • List projectsList 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 alm
  • List promptsList 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 — pa
  • List prompt suggestionsList 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_su
  • List referral sourcesEvery AI assistant Peec can attribute referral traffic to, whether or not a project has seen traffic from it. Use it to resolve the exact display name for the `assistants` filter on get_ai_referrals,
  • List search queriesList the general web-search queries an AI engine fanned out to while answering prompts in a project over a date range — the text sub-queries it sent to a search index, NOT product/shopping lookups (us
  • List shopping demandRank the query terms that drive shopping demand by how many distinct chats they appear in, with a trend vs a comparison window. Returns an aggregated ranking, not per-chat rows — for the individual qu
  • List shopping performanceList products or categories (via entity_type) ranked by shopping performance over a date range. Performance columns are visibility, win_rate, avg_position, and appearances, each with a period-over-per
  • List shopping queriesList the product/shopping queries an AI engine fanned out to while answering prompts in a project over a date range. Each row represents one shopping sub-query and the distinct products returned for i
  • List tag groupsList the user-defined tag groups in a project, each with its shared color and tag count. Use this to discover group names before filtering list_tags by group or before renaming/deleting a group. Syste
  • List tagsList tags in a project. Tags are cross-cutting labels that can be assigned to any prompt. Use this tool to resolve tag names to IDs before filtering (tag_id filter/dimension, list_prompts), and to lab
  • List topicsList topics in a project. Topics are folder-like groupings — each prompt belongs to exactly one topic. Use this tool to resolve topic names to IDs before filtering (topic_id filter/dimension, list_pro
  • List url classificationsList the custom URL classifications defined for a project. These complement the built-in classifications (Homepage, Category Page, Product Page, Listicle, Comparison, Profile, Alternative, Discussion,
  • Read docRead the full markdown content of a single Peec documentation page. Pass the path returned by search_docs (e.g. 'metrics/brand-metrics/visibility'). Answer strictly from the returned content — never i
  • Search docsSearch the Peec docs (https://docs.peec.ai) and return the most relevant pages. The docs carry two kinds of content: product documentation (what a metric means, how a feature behaves, setup steps, pla

Held for approval by default (changes and sends)

Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 38 actions.

  • Archive promptsArchive up to 50 prompts (sets is_archived = true) so they stop running while keeping their chats and history intact. Prefer this over delete_prompts when the data should be retained. Returns a count
  • Assign domain classificationAssign a built-in classification (Corporate, Competitor, Editorial, Institutional, Other, Reference, UGC, You, Related) or the name of a custom domain classification to a domain. Overrides any heurist
  • Assign url classificationAssign a built-in classification (Homepage, Category Page, Product Page, Listicle, Comparison, Profile, Alternative, Discussion, How-To Guide, Article, Other) or the name of a custom URL classificatio
  • Create brandsCreate up to 50 brands (competitors or own) in a project in one call. Returns the created brands with their new ids, plus any skipped items. After creation, call list_brands to confirm the requested b
  • Create categoriesCreate product categories. Each item needs a name and an optional parent_id — omit it for a top-level category, or pass another category's id (use list_categories to find it) to nest it underneath. A
  • Create domain classificationDefine a new custom domain classification on a project. This creates the classification entity — it does not assign it to any domain (use assign_domain_classification for that). Confirm with the user
  • Create global brandCreate a brand and return its global_brand_id. Use this when list_global_brands finds no match for a brand you need, or when create_products rejects an item with brand_not_found. Returns { id, name }.
  • Create productsCreate catalog products (source=CATALOG) in a project — the brand's own claimed/uploaded products, as opposed to LLM products that Peec auto-detects in shopping answers. Each item needs a global_brand
  • Create promptsCreate up to 50 prompts in a project in one call. Returns the created prompts with their new ids, plus any skipped/rejected items. Every prompt needs a topic: pick the best-fitting existing topic, or
  • Create tagsCreate up to 50 tags in a project in one call. Each tag may specify a group (grouped tags share the group's color, so their color field is ignored). Returns the created tags with their new ids, plus a
  • Create topicsCreate up to 50 topics in a project in one call. Topics group related prompts. Returns the created topics with their new ids, plus any skipped/rejected items. Duplicates are matched case-insensitively
  • Create url classificationDefine a new custom URL classification on a project. This creates the classification entity — it does not assign it to any URL (use assign_url_classification for that). Returns the created classificat
Show all 38
  • Delete brandsDelete up to 50 brands in a project. Returns a count of deleted brands plus any skipped items (successful items are not echoed back). This is destructive — always confirm with the user before calling.
  • Delete categoriesDelete categories by id (use list_categories to resolve ids). A deleted category's child categories and products move up to its parent (a top-level delete sends children to the top level and its produ
  • Delete domain classificationPermanently delete a custom domain classification entity. Cascades through the override table — any domains currently assigned this classification fall back to their heuristic classification. To only
  • Delete productsDelete products by id (use list_products to resolve ids). Returns per-item results { deleted, skipped } — ids not present in the project are skipped (not_found). Only delete source=CATALOG products. D
  • Delete promptsDelete up to 50 prompts in a project. Deletions run asynchronously — returns a count of queued deletions plus any skipped (not found / already deleted) or rejected items (queued items are not echoed b
  • Delete tag groupsDelete up to 50 user-defined tag groups. By default each group's tags are kept and simply ungrouped; set delete_tags=true on a group to delete its tags and remove them from every prompt. Returns each
  • Delete tagsDelete up to 50 tags in a project. Removes tag associations from prompts. Returns a count of deleted tags plus any skipped items (successful items are not echoed back). This is destructive — always co
  • Delete topicsDelete up to 50 topics in a project. Detaches associated prompts (prompts are kept) and deletes any prompt suggestions linked to the topics. Returns a count of deleted topics plus any skipped items (s
  • Delete url classificationPermanently delete a custom URL classification entity. Any URLs currently assigned this classification fall back to their heuristic (default) classification. To only clear a single URL's assignment, u
  • Edit brand perception attribute clustersRename, delete and reassign brand-perception attribute clusters — the same edits the Manage attributes screen makes. Resolve every cluster_id and attribute with list_brand_perception_attribute_cluster
  • Finalize prompt suggestionsResolve prompt suggestions listed by list_prompt_suggestions, in one pass over a reviewed set: ids in accepted_ids become tracked prompts and promote their topics into the project, ids in rejected_ids
  • Generate prompt suggestionsGenerate prompt suggestions for a project — the same generation Prompt discovery runs in the app. Generation runs in the background: the call returns {queued: true, generation_id}, which get_prompt_su
  • Generate topicsCompose candidate topics for the project from its brand profile — the same composition Prompt discovery runs in the app. Nothing is saved: review the returned names with the user and create the chosen
  • Set brand social channelsReplace the complete social-channel list for up to 50 brands. Each channel is supplied as its platform and full profile or community URL. Existing channels omitted for a brand are removed; an empty ch
  • Set project profileSet the project's own brand-identity profile — its industry, target audience, tone, and similar descriptive fields. This is the project's own identity, not the competitor/monitored brand entities mana
  • Unarchive promptsUnarchive up to 50 prompts (sets is_archived = false), reactivating them so they resume running. Subject to the project's active-prompt plan limit — prompts that would exceed it are rejected. Returns
  • Unassign domain classificationClear the classification override on a whole domain (operates on a domain, e.g. "example.com" — for a single URL use unassign_url_classification), restoring the heuristic classification. Does NOT dele
  • Unassign url classificationClear the classification override on a single URL (operates on one full URL — for a whole domain use unassign_domain_classification), restoring the heuristic classification. Does NOT delete the custom
  • Update brandsUpdate up to 50 brands in one call (name, regex, aliases, domains, color per item). Before changing aliases, read the brand's regex and aliases with list_brands. A nonempty regex is the active Advance
  • Update categoriesRename and/or move categories by id (use list_categories to resolve ids). Each item sets name (rename it), parent_id (move it under that category, or null to promote it to the top level), or both. Ret
  • Update productsUpdate up to 1000 products by id in one call (use list_products to resolve ids). Per item, set any of: name (unique within the brand), description, image_url, price_override (per-currency; replaces al
  • Update promptsUpdate the topic, tags, location and/or fact-checking selection of up to 50 prompts in one call. Per item, pass tag_ids to fully replace the prompt's tag set, topic_id = null to detach its topic, coun
  • Update prompt suggestionsEdit up to 50 pending prompt suggestions from list_prompt_suggestions before finalizing: rewrite the text and/or replace the tag set per item. Prefer this over rejecting and regenerating when a sugges
  • Update tag groupsRename and/or recolor up to 50 user-defined tag groups in one call. The change applies to every tag in each group. Per group, provide a new name, a new color, or both (a group with neither is rejected
  • Update tagsUpdate up to 50 tags in one call (name, color, and/or group per item). Set a tag's group to move it into a group (inherits the group's color), `null` to ungroup, or omit to leave unchanged. Returns a
  • Update topicsRename up to 50 topics in one call. Returns a count of updated topics plus any skipped/rejected items (successful items are not echoed back).

Changes wait in Needs you

Changes and sends in Peec AI MCP are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

How approvals work

Peec AI MCP questions

Can an agent change data in Peec AI MCP on its own?

Not by default. Changes and sends in Peec AI MCP are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

What can an agent read in Peec AI MCP?

This connector lists 44 read actions. Reads run at once, without waiting for approval.

How does Peec AI MCP connect?

It connects with dcr oauth. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.

Bring Peec AI MCP to your agents.