PERSONAIZER
Free MCP API to create AI chat personas for websites — upload knowledge, search, and chat
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"mcp": {
"url": "https://sessions.personaizer.com/mcp"
}
}
}遠端端點
https://sessions.personaizer.com/mcpstreamable-http它能做什麼
工具清單
工具(5)
🟡upload_knowledge_text(content, title, source, id, url)
Add a piece of text — an FAQ, policy, guide, article or notes — to a knowledge source as a plain-text document. Uploading again with the same id replaces that document's text. For products (price, stock, attributes, variants) use upload_knowledge_docs. Requires your account API key and the source to write to; every persona speaking for that source's brand answers from it.
輸入結構描述
{
"type": "object",
"properties": {
"content": {
"description": "The full text of the document.",
"type": "string"
},
"title": {
"description": "Document title.",
"type": "string"
},
"source": {
"description": "The knowledge source this belongs to — its name, e.g. my-shop.ge.",
"type": "string"
},
"id": {
"description": "Optional stable identifier. Uploading again with the same id replaces that document's text; omit it to create a new document.",
"type": [
"string",
"null"
],
"default": null
},
"url": {
"description": "Optional URL where this content lives — shown as the document's link when the persona cites it.",
"type": [
"string",
"null"
],
"default": null
}
},
"required": [
"content",
"title",
"source"
]
}🟡create_persona(websiteUrl, harvestContent)
Start building a new PersonAIzer persona from a website URL — reads the site's brand facts, makes the brand, synthesizes the persona's identity and avatar, and (by default) crawls the site into the brand's knowledge; the persona and the crawl run in parallel. Asynchronous (~1 minute for the persona) — returns jobId, brandId and personaId; poll check_persona_status. Requires an account-level API key.
輸入結構描述
{
"type": "object",
"properties": {
"websiteUrl": {
"description": "The website URL to build the persona from.",
"type": "string"
},
"harvestContent": {
"description": "Whether to crawl the site into the brand's knowledge alongside the persona build (default true).",
"type": "boolean",
"default": true
}
},
"required": [
"websiteUrl"
]
}🟡chat(message, personaId, sessionId)
Send a message to a PersonAIzer persona and get its reply, including any knowledge-base cards it surfaces. Requires your account API key and the persona_id to speak as.
輸入結構描述
{
"type": "object",
"properties": {
"message": {
"description": "The message to send.",
"type": "string"
},
"personaId": {
"description": "Which persona to chat with (its Persona ID).",
"type": "string"
},
"sessionId": {
"description": "Continue an existing conversation by passing back the session_id from a previous chat call. Omit to start a new conversation.",
"type": [
"string",
"null"
],
"default": null
}
},
"required": [
"message",
"personaId"
]
}🟡upload_knowledge_docs(source, items)
Upsert up to 100 PRODUCTS (including services and unpriced catalog entries) into a knowledge source. For plain text (FAQs, policies, guides, articles, notes) use upload_knowledge_text instead. Requires your account API key; the source must exist (POST /v1/knowledge/sources).
輸入結構描述
{
"type": "object",
"properties": {
"source": {
"description": "The knowledge source the products belong to — its name, e.g. my-shop.ge.",
"type": "string"
},
"items": {
"description": "The products to upsert. Each needs title and categories (e.g. [[\"phones\"]]); id, description, price, in_stock, attributes, variants, images and links are optional — see PersonAIzer's /v1/knowledge API reference for the full shape.",
"type": "array"
}
},
"required": [
"source",
"items"
]
}🟡check_persona_status(jobId)
Poll the status of a persona build started by create_persona. Requires an account-level API key.
輸入結構描述
{
"type": "object",
"properties": {
"jobId": {
"description": "The job_id returned by create_persona.",
"type": "string"
}
},
"required": [
"jobId"
]
}社群
證據