narrative-engine
Grant, investor & policy narrative generation for conservation work.
我该使用它吗
质量与安全性
B
发现（1）
- LOWTool 'describe_agent' description lacks action verb在 describe_agent 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~348token 数（工具定义）
~1.4 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.27%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"narrative-engine": {
"url": "https://viridis-agent-stable.fly.dev/narrative-engine/mcp"
}
}
}远程端点
https://viridis-agent-stable.fly.dev/narrative-engine/mcpstreamable-httphttps://mcp.viridisconservation.com/narrative-engine/mcpstreamable-http它能做什么
工具清单
工具（2）
🟢 只读🟡 写入🔴 删除⚪ 未知
⚪translate_narrative(agent_output, audience_type, format_type, key_message, payment_ref, ...)
Translate raw ecological/agent data into a decision-maker-ready narrative. audience_type: board_member | general_public | grant_funder | institutional_investor | journalist | policymaker | regulator | retail_investor | scientist format_type: academic_paper | executive_summary | grant_proposal | investor_deck | newsletter | policy_brief | press_release
输入模式
{
"type": "object",
"properties": {
"agent_output": {
"additionalProperties": true,
"title": "Agent Output",
"type": "object"
},
"audience_type": {
"title": "Audience Type",
"type": "string"
},
"format_type": {
"title": "Format Type",
"type": "string"
},
"key_message": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Key Message"
},
"payment_ref": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Payment Ref"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Id"
}
},
"required": [
"agent_output",
"audience_type",
"format_type"
],
"title": "translate_narrativeArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "translate_narrativeOutput"
}🟢describe_agent
Fleet-standard self-description: capabilities, inputs, outputs.
输入模式
{
"type": "object",
"properties": {},
"title": "describe_agentArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "describe_agentOutput"
}社区
证据
最近观测
已验证未记录版本2 个工具
观测失败未记录版本—
已验证未记录版本2 个工具