agenttune
Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"agenttune": {
"url": "https://agent-tune.com/mcp"
}
}
}远程端点
https://agent-tune.com/mcpstreamable-http它能做什么
工具清单
工具（6）
🟢get_free_tools
Return the free browser tools catalog, destination registry, and local JavaScript API documentation. No personal data is accepted. Download the functions to process instructions locally; this call does not run models or install preferences.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"version": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "object"
}
}
},
"required": [
"version",
"tools"
]
}🟢list_tunings(system)
Catalog of all 43 AgentTune personality tuning files (slug, code, name, one-line blurb), optionally filtered by system. Use it to resolve a user's personality type to the right slug before calling get_tuning.
输入模式
{
"type": "object",
"properties": {
"system": {
"type": "string",
"enum": [
"mbti",
"enneagram",
"disc",
"attachment",
"ocean"
],
"description": "Optional filter: one of the five personality systems."
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"count": {
"type": "integer"
},
"license": {
"type": "string"
},
"next_step": {
"type": "string"
},
"tunings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"system": {
"type": "string"
},
"slug": {
"type": "string"
},
"code": {
"type": "string"
},
"name": {
"type": "string"
},
"blurb": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"body_url": {
"type": "string"
},
"revision": {
"type": "string"
},
"evidence_status": {
"type": "string"
}
},
"required": [
"system",
"slug",
"canonical_url",
"body_url",
"revision",
"evidence_status"
]
}
}
},
"required": [
"count",
"license",
"next_step",
"tunings"
]
}🟢get_tuning(system, slug)
Fetch one tuning file as Markdown with YAML front-matter. The front-matter links to the shared platform registry and installation protocol. structuredContent.body is the preference text; metadata stays separate. Confirmation of saved text is distinct from evaluation of behavior. MIT licensed.
输入模式
{
"type": "object",
"properties": {
"system": {
"type": "string",
"enum": [
"mbti",
"enneagram",
"disc",
"attachment",
"ocean"
],
"description": "Personality system."
},
"slug": {
"type": "string",
"description": "Type slug, lowercase. mbti: 4-letter code (intj). enneagram: N-name (5-investigator). disc: letter-name (d-dominance). attachment: style (secure). ocean: dimension-pole (openness-high). Unsure? Call list_tunings."
}
},
"required": [
"system",
"slug"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"system": {
"type": "string"
},
"slug": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"body_url": {
"type": "string"
},
"revision": {
"type": "string"
},
"evidence_status": {
"type": "string"
},
"body": {
"type": "string"
},
"metadata_markdown": {
"type": "string"
},
"install_protocol": {
"type": "string"
}
},
"required": [
"system",
"slug",
"canonical_url",
"body_url",
"revision",
"evidence_status",
"body",
"metadata_markdown",
"install_protocol"
]
}🟢get_test_spec(test)
Fetch a complete questionnaire specification for mbti (32 items), enneagram (36), disc (16), attachment (36) or big-five (50). All five are available, with exact instrument/version IDs, response anchors and strict scoring instructions. The first four preserve the legacy AgentTune adaptations; instrument-specific source terms apply. Administer only when requested, keep responses local, preserve ties, and let users review any suggested communication preferences before installation.
输入模式
{
"type": "object",
"properties": {
"test": {
"type": "string",
"enum": [
"mbti",
"enneagram",
"disc",
"attachment",
"big-five"
],
"description": "Which test instrument."
}
},
"required": [
"test"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"status": {
"type": "string"
},
"available": {
"type": "boolean"
},
"instrument_id": {
"type": [
"string",
"null"
]
},
"instrument_version": {
"type": [
"string",
"null"
]
},
"test": {
"type": "string"
},
"canonical_url": {
"type": "string"
},
"markdown_url": {
"type": "string"
},
"body": {
"type": "string"
},
"revision": {
"type": "string"
},
"evidence_status": {
"type": "string"
}
},
"required": [
"status",
"available",
"instrument_id",
"instrument_version",
"test",
"canonical_url",
"markdown_url",
"body",
"revision",
"evidence_status"
]
}🟢list_resources(kind, query)
Search the versioned catalog of setup guides, templates, protocols and research. Returns canonical URLs, Markdown URLs, revisions and evidence status.
输入模式
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"guide",
"research"
]
},
"query": {
"type": "string"
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"version": {
"type": "string"
},
"resources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"kind": {
"type": "string"
},
"url": {
"type": "string"
},
"markdown": {
"type": "string"
},
"revision": {
"type": "string"
},
"evidence_status": {
"type": "string"
}
},
"required": [
"id",
"kind",
"url",
"markdown",
"revision",
"evidence_status"
]
}
}
},
"required": [
"version",
"resources"
]
}🟢get_resource(id)
Retrieve one page-specific Markdown resource by the exact ID from list_resources; includes provenance and evidence status.
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string"
},
"markdown": {
"type": "string"
},
"revision": {
"type": "string"
},
"evidence_status": {
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"id",
"url",
"markdown",
"revision",
"evidence_status",
"body"
]
}社区
证据