HyperXosist-Agent Remote MCP
X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs.
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": {
"hyperxosist-agent": {
"url": "https://mcp.kgninja.dev/mcp"
}
}
}遠端端點
https://mcp.kgninja.dev/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢hyperxosist_search_plan(intent)
Use only for specialized X (Twitter) research planning: complaints, bug reports, feature requests, product feedback, or community signals. Builds multiple noise-reduced official x.com/search URLs and quality scores. It is not general web search and does not scrape X or collect posts.
輸入結構描述
{
"type": "object",
"properties": {
"intent": {
"type": "string",
"minLength": 1,
"description": "An X-specific research goal, for example: Find user complaints and bug reports on X about Acme."
}
},
"required": [
"intent"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"type": {
"const": "hyperxosist.search_plan.v1"
},
"missionId": {
"type": "string"
},
"mission": {
"type": "object"
},
"queries": {
"type": "array",
"items": {
"type": "string"
}
},
"searchUrls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
}
},
"qualityScores": {
"type": "array",
"items": {
"type": "number"
}
},
"estimatedCostUsd": {
"type": "number"
},
"requiresPaymentForAutomatedProductionUse": {
"type": "boolean"
},
"paymentPolicy": {
"type": "object"
}
},
"required": [
"type",
"missionId",
"mission",
"queries",
"searchUrls",
"qualityScores",
"estimatedCostUsd",
"requiresPaymentForAutomatedProductionUse",
"paymentPolicy"
]
}🟢hyperxosist_filter_signals(feedback)
Use after X posts or tweet text have already been collected. Separates actionable bugs, feature requests, and UX friction from empty praise, engagement bait, and spam. It does not fetch, scrape, or search X.
輸入結構描述
{
"type": "object",
"properties": {
"feedback": {
"type": "array",
"minItems": 1,
"items": {
"type": "string",
"minLength": 1
},
"description": "Previously collected X post text to classify in memory."
}
},
"required": [
"feedback"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"type": {
"const": "hyperxosist.signal_filter.v1"
},
"keep": {
"type": "array"
},
"discard": {
"type": "array"
},
"summary": {
"type": "object"
},
"keepCount": {
"type": "integer"
},
"discardCount": {
"type": "integer"
}
},
"required": [
"type",
"keep",
"discard",
"summary",
"keepCount",
"discardCount"
]
}🟢hyperxosist_build_handoff(productName, feedback)
Use to turn previously collected X feedback into a structured Signal-to-Fix package and coding-agent prompt. It does not perform general summarization, search the web, scrape X, or modify source code.
輸入結構描述
{
"type": "object",
"properties": {
"productName": {
"type": "string",
"minLength": 1
},
"feedback": {
"type": "array",
"minItems": 1,
"items": {
"type": "string",
"minLength": 1
},
"description": "Previously collected X feedback text."
}
},
"required": [
"productName",
"feedback"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"type": {
"const": "hyperxosist.handoff.v1"
},
"handoff": {
"type": "object"
},
"signalToFixInput": {
"type": "object"
},
"agentPrompt": {
"type": "object"
}
},
"required": [
"type",
"handoff",
"signalToFixInput",
"agentPrompt"
]
}社群
證據