Connect your AI Agents to Peec AI in minutes
Available tools
list_brands
List tracked brands in a Peec project. Supports offset pagination. Returns brand IDs, names, domains, aliases, and 'is_own' flag for the project owner's brand.
create_brand
Create a new tracked brand. Provide name, domains, aliases, regex pattern, or color. The brand becomes available for tracking immediately.
update_brand
Update a brand's name, domains, aliases, regex, or color. Modifying name, regex, or aliases triggers metric recalculation and blocks further updates until it completes (returns 409). Use list_brands to find valid brand IDs.
delete_brand
Soft-delete a brand. The brand is removed from the project but historical data is retained. Use list_brands to find valid IDs.
list_brand_suggestions
List AI-generated brand suggestions for a project. Each suggestion includes a name, domains, and the count of chats where the brand was mentioned. Use accept_brand_suggestion or reject_brand_suggestion to triage.
accept_brand_suggestion
Accept an AI-generated brand suggestion. The suggestion becomes a tracked brand. Use list_brand_suggestions to find valid IDs.
reject_brand_suggestion
Permanently reject an AI-generated brand suggestion. The suggestion is discarded. Use list_brand_suggestions to find valid IDs.
list_chats
List chats (AI model responses) for a project. Filter by date range, brand_id, prompt_id, or model_channel_id. Returns lightweight refs; use get_chat for full content.
get_chat
Get full content of a chat including the prompt, model channel, all messages (user + assistant), cited source URLs, mentioned brands with positions, and surfaced products. Use list_chats to find valid IDs.
list_model_channels
List available AI model channels (e.g. 'openai-0', 'perplexity-1') and the model each currently points at. Channels are stable references — the underlying model can evolve. Use these IDs as model_channel_id filters when listing chats.
list_projects
List Peec AI projects available to the API key. Requires a company-scoped API key — project-scoped keys will get a 403. Returns project IDs, names, status (CUSTOMER, TRIAL, etc.), and external_id.
get_project_profile
Get the brand profile for a project. Returns occupation, industry, brand presentation, products and services, target markets, and audience distribution. The profile may be null if not yet configured.
set_project_profile
Replace the entire brand profile for a project. WARNING: this is a full replacement — every field is required. Returns 403 during onboarding. Call get_project_profile first to see existing values.
list_prompts
List configured prompts that Peec runs against AI models. Filter by topic_id or tag_id. Each prompt includes its text, tags, topic, user location, and estimated search volume.
create_prompt
Create a new prompt to track. Required: text (1-200 chars) and ISO 3166-1 alpha-2 country_code. Optionally attach tag_ids and a topic_id. Returns the new prompt ID and an optional warning (e.g. credit usage).
update_prompt
Update a prompt's topic_id or tag_ids. Pass null topic_id to detach. Use list_prompts to find valid IDs.
delete_prompt
Soft-delete a prompt. Cascades to delete related chats. Use list_prompts to find valid IDs.
list_prompt_suggestions
List AI-generated prompt suggestions. Optionally filter by topic_id. Use accept_prompt_suggestion or reject_prompt_suggestion to triage.
accept_prompt_suggestion
Accept an AI-generated prompt suggestion. The suggestion becomes a configured prompt. Use list_prompt_suggestions to find valid IDs.
reject_prompt_suggestion
Permanently reject an AI-generated prompt suggestion. Use list_prompt_suggestions to find valid IDs.
list_fanout_search_queries
List fanout search queries — the underlying search-style queries that AI models issued while answering tracked prompts. Filter by date range and additional filters object.
list_fanout_shopping_queries
List fanout shopping queries — the product-style queries that AI models issued while answering tracked prompts. Each query may include surfaced products. Filter by date range and additional filters object.
get_brands_report
Get a brand-level report with metrics (visibility, sentiment, position, mention_count, share_of_voice) over a date range. Group by dimensions and apply filters. Returns paginated rows.
get_domains_report
Get a source-domain report with metrics (citation_rate, retrieval_count, citation_count) over a date range. Identifies which domains AI models cite most often.
get_urls_report
Get a source-URL report with metrics (citation_rate, retrieval_count, citation_count) over a date range. Identifies which specific URLs AI models cite.
get_url_content
Fetch the scraped markdown content of a source URL Peec has indexed. Returns title, domain, content, truncation flag, and last-updated timestamp. Use to inspect what AI models are citing.
list_tags
List tags in a Peec project. Tags are used to group prompts. Returns tag IDs, names, and colors with offset pagination.
create_tag
Create a new tag for grouping prompts. Required: name. Optional color (defaults to 'gray'). Valid colors: gray, red, orange, yellow, lime, green, cyan, blue, purple, fuchsia, pink, emerald, amber, violet, indigo, teal, sky, rose, slate, zinc, neutral, stone.
update_tag
Update a tag's name and/or color. Use list_tags to find valid IDs.
delete_tag
Soft-delete a tag. Use list_tags to find valid IDs.
list_topics
List topics in a Peec project. Topics are used to organize prompts. Returns topic IDs and names with offset pagination.
create_topic
Create a new topic to organize prompts. Required: name (1-64 chars). Optionally provide an ISO 3166-1 alpha-2 country_code.
update_topic
Update a topic's name (1-64 chars). Use list_topics to find valid IDs.
delete_topic
Delete a topic. Use list_topics to find valid IDs.
list_topic_suggestions
List AI-generated topic suggestions. Use accept_topic_suggestion or reject_topic_suggestion to triage.
accept_topic_suggestion
Accept an AI-generated topic suggestion. The suggestion becomes a tracked topic. Use list_topic_suggestions to find valid IDs.
reject_topic_suggestion
Permanently reject an AI-generated topic suggestion. Use list_topic_suggestions to find valid IDs.
validate_credential
Validate the Peec AI API key by making a lightweight list_brands call. Works for both project-scoped and company-scoped keys.
How to set up Merge Agent Handler
In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}FAQs on using Merge's Peec AI MCP server
FAQs on using Merge's Peec AI MCP server
Ready to try it out?
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now
