site
CSV Convert: the site's own MCP server — checker, enquiry (enquiry = a human handoff, not a...
我該用這個嗎
品質與安全性
發現項目(1)
- LOW在 checker_tree 中
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": {
"site": {
"url": "https://csvconvert.uk/mcp"
}
}
}遠端端點
https://csvconvert.uk/mcpstreamable-http它能做什麼
工具清單
工具(6)
⚪checker_start
The first question of the Which PDF to CSV route? decision guide.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪checker_answer(question, choice)
Given a question id and the chosen option (its `choice` index), return the next question or the final verdict.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1
},
"choice": {
"type": "integer",
"minimum": 0
}
},
"required": [
"question",
"choice"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪checker_tree
Every question, option and verdict of the Which PDF to CSV route? guide, for reasoning end to end.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡enquiry_describe
Read first. States plainly what submit_enquiry does on CSV Convert: it starts an enquiry with human providers who quote directly. Nothing is bought, ordered or paid; no quote is guaranteed; it is free. Also returns who receives the details, the consent wording, and how the person confirms.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡enquiry_fields
Every field of the CSV Convert enquiry: key, label, type, whether required, help text and the allowed options where there are any. Pass answers to submit_enquiry keyed by field key.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡submit_enquiry(answers, consent, confirmation)
Submits an enquiry to CSV Convert — NOT a purchase, NOT a guaranteed quote. Step 1: call with the answers (keyed by field key from enquiry_fields) and consent=true; it validates and returns a summary, the consent line and a confirmation token — show the person the summary and the consent line. Step 2: only if the person agrees, call again with the same answers, consent=true and the confirmation token; the enquiry is then submitted, and the person receives an email with a link they must click before any provider sees it. Consent means the person has read and agreed to: "Happy for my details to go to data extraction suppliers, who'll contact me directly."
輸入結構描述
{
"type": "object",
"properties": {
"answers": {
"type": "object",
"additionalProperties": {
"type": [
"string",
"number",
"boolean"
]
},
"description": "the person's answers, keyed by field key"
},
"consent": {
"type": "boolean",
"description": "true only when the person has agreed to: Happy for my details to go to data extraction suppliers, who'll contact me directly."
},
"confirmation": {
"type": "string",
"description": "the confirmation token from step 1, after the person has approved the summary"
}
},
"required": [
"answers",
"consent"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據