Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@emotion-mcp analyze message: 'I missed you' for character Alice"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
弗洛伊德双驱情绪管理 MCP 服务器 —— astrbot_plugin_affection 的独立 MCP 实现。
NPM: https://www.npmjs.com/package/emotion-mcp GitHub: https://github.com/yaoxiaolinglong/emotion-mcp
为 AI 角色扮演/伴侣场景提供动态情绪模拟系统。基于弗洛伊德心理动力学（力比多/攻击性），通过潜意识 LLM 分析对话内容实时调整情绪数值，具备时间衰减能力。
npx -y emotion-mcpRelated MCP server: five-mcp
mcpServers:
emotion:
type: stdio
command: npx
args:
- -y
- emotion-mcp
timeout: 60000无需任何环境变量！ Agent 通过两步模式完成情绪分析：
用户发言
→ emotion_get_analysis_prompt(user_id, message) # 获取分析任务
→ Agent 自己分析 → 输出 JSON
→ emotion_apply_deltas(user_id, deltas) # 提交结果，数值更新
→ emotion_get_emotion_prompt(user_id) # 获取情绪文本
→ 注入 system prompt → 生成回复如果配置了 EMOTION_LLM_API_KEY，可用 emotion_analyze 一步完成：
mcpServers:
emotion:
type: stdio
command: npx
args:
- -y
- emotion-mcp
env:
EMOTION_LLM_API_KEY: sk-your-key-here
timeout: 60000变量 | 默认值 | 说明 |
| (必填) | 潜意识 LLM API Key |
|
| API 地址 |
|
| 模型名（建议轻量模型） |
|
| 情绪敏感度 (0-100) |
|
| 初始好感度 (0-100) |
emotion_analyze ★ 核心分析用户消息 → 调用潜意识 LLM → 更新情绪数值。每次用户发言后调用。
输入: user_id, message, history(可选)
输出: 更新后的完整情绪面板 + 增量详情
emotion_get_emotion_prompt生成可追加到 system prompt 的情绪文本。
输入: user_id
输出: 情绪数值面板文本
emotion_get_panel获取当前情绪数值面板（JSON 格式）。
输入: user_id
emotion_get_status完整情绪档案，含参考表。
emotion_reset / emotion_set / emotion_reset_all管理工具。
将以下规则加入角色设定的 system prompt 末尾：
【情绪驱动规则】
你的回复风格和情感倾向由系统实时计算的「力比多/攻击性/好感」数值决定。每次对话前，你会收到【当前情绪数值】面板，包含：
- 他力比多（0-50）：想亲近对方的欲望。高→主动撒娇黏人，低→冷淡回避疏远。
- 他攻击性（0-50）：想伤害对方的冲动。高→敌意烦躁刻薄，低→温顺容忍顺从。
- 好感度（0-100）：长期累积的喜欢和依恋。≥70 时攻击性表现为"吃醋""占有欲"；≤30 时表现为"厌恶""敌意"。
- 自力比多（0-50）：自爱程度。高→自信自爱，低→自卑空虚。
- 自攻击性（0-50）：自责/自我毁灭冲动。高→崩溃自我贬低。
重要约束：不要提及任何具体数值，根据数值强度自然演绎。数值的微小变化也应体现在语气强度上。基于 astrbot_plugin_affection (AGPL-3.0) 改造。同样采用 AGPL-3.0。
【一键模式】分析用户消息 + 更新情绪。如果配置了 EMOTION_LLM_API_KEY 则由后台 LLM 分析，否则由调用方（Agent）分析。推荐使用 emotion_get_analysis_prompt + emotion_apply_deltas 两步模式以获得更好的控制
| Name | Required | Description | Default |
|---|---|---|---|
| history | No | 最近对话历史（可选，最多2000字符） | |
| message | Yes | 用户最新消息内容 | |
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the conditional analysis mode (backend LLM vs caller) and the side effect of updating emotion. While it doesn't detail the exact update mechanism or potential side effects beyond this, it provides useful behavioral context that goes beyond a minimal statement.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, dense sentence that front-loads the core purpose, then provides configuration context and a recommendation. Every clause adds value and there is no redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers usage context and configuration clearly, but since there is no output schema, it should describe what the tool returns. It does not mention any return value or response format, which is a significant gap for a tool that both analyzes and updates emotion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for all three parameters, so the baseline is 3. The description does not add parameter-specific details beyond what the input schema already states; it only mentions 'user message' and 'history' generically.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '分析用户消息 + 更新情绪' with a specific verb and resource, and distinguishes itself from the two-step alternative by labeling it '一键模式' (one-click mode). This makes the tool's purpose unambiguous and distinct from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly recommends using emotion_get_analysis_prompt + emotion_apply_deltas for better control, implying this one-click mode is for simpler use cases. It also explains the configuration-dependent behavior (EMOTION_LLM_API_KEY), giving clear when-to-use guidance and naming alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
手动触发时间衰减（通常自动执行）
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only mentions the triggering action and automaticity, but does not describe side effects, reversibility, or the impact on emotion state. This is a significant gap for a mutation-like tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence that front-loads the action and provides a useful qualifier. It contains no filler or redundant information, earning a perfect score for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity—zero parameters, no output schema, and no annotations—the description is minimally viable. However, it lacks crucial context about what time decay does to emotions or whether the operation is safe, which would be needed for confident invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the schema is empty, so there are no parameter semantics to explain. The description appropriately avoids inventing parameter details, and the baseline for no-param tools is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action—manually triggering time decay—and notes it is usually automatic, which gives a distinct purpose. However, it does not explicitly differentiate from sibling tools like emotion_apply_deltas, though the term 'decay' is distinct enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase '通常自动执行' (usually automatic execution) implies this tool is for manual override when automatic decay has not occurred. It provides some context for when to use it but lacks explicit exclusions or references to alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
提交情绪增量 JSON 以更新数值。配合 emotion_get_analysis_prompt 使用：分析完成后将 JSON 结果提交于此
| Name | Required | Description | Default |
|---|---|---|---|
| deltas | Yes | 情绪增量 JSON，格式：{libido_other_delta, aggression_other_delta, libido_self_delta, aggression_self_delta, affection_delta, base_libido_other_delta, base_aggression_other_delta, base_libido_self_delta, base_aggression_self_delta, intensity} | |
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only says 'update values' without explaining whether deltas are additive, if values are clamped, or what the return/effects are. This lacks the disclosure expected for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one short sentence plus a usage pointer, with no filler words. It front-loads the action and is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex nested object and no output schema. The description gives workflow context with emotion_get_analysis_prompt but omits return value expectations and behavioral details, making it incomplete for a state-changing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage, including the delta object format and user_id description. The tool description adds no extra parameter meaning, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('submit emotion delta JSON to update values') and names the paired tool (emotion_get_analysis_prompt). This clearly distinguishes it from siblings like emotion_set or emotion_apply_decay.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says to use with emotion_get_analysis_prompt after analysis completes, providing a clear usage context. It does not name when-not-to-use scenarios or alternatives, but the pairing instruction is specific.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
获取情绪分析任务 — 返回当前数值 + 分析指南 + 消息和对话历史。调用后你会得到一个分析任务，请根据指南判断情绪变化并输出 JSON，然后调用 emotion_apply_deltas 提交结果。这样就由你（主 LLM）来做潜意识分析，无需额外配置 API Key
| Name | Required | Description | Default |
|---|---|---|---|
| history | No | 最近对话历史（可选，最多2000字符） | |
| message | Yes | 用户最新消息内容 | |
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the disclosure burden. It communicates that this is a retrieval step in a larger workflow (the tool returns data and the agent later submits changes), and that no external API Key is required. It does not explicitly state side effects or permissions, though the '获取' wording strongly implies a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the purpose and return contents, then adds workflow and rationale. Each sentence adds value, but the explanation of why to use the tool could be tightened, so it falls just short of 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description appropriately summarizes the return payload (current values, guide, message, history) and instructs the agent to produce JSON and call emotion_apply_deltas. It also addresses the environment (no API Key). It does not describe exact output shapes, but the returned guide presumably covers that, making it sufficiently complete for this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all three parameters, so the description adds only modest value by mentioning '消息和对话历史' in the context of returned data rather than parameter semantics. It does not clarify user_id or provide formatting details beyond the schema, meriting the baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as retrieving an emotion analysis task, with a specific verb '获取' and resource '情绪分析任务'. It lists the return contents (current values, guide, message/history) and the follow-up workflow, but it does not explicitly differentiate itself from the sibling tool emotion_get_emotion_prompt, so it misses the full 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool by stating that after calling, the main LLM should analyze and then call emotion_apply_deltas; it also explains the no-API-key rationale. However, it does not explicitly compare alternatives or state when not to use it, so usage guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
生成可注入 system prompt 的情绪数值文本，让 AI 根据当前情绪数值演绎角色
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It clearly indicates a read/generate operation ('generate', 'based on current emotion values'), implying no mutation. However, it does not disclose potential side effects, required permissions, or output format details, which is a notable gap but acceptable for a simple getter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the action and includes the key purpose. Every word adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (one parameter, no output schema), the description adequately explains what the tool returns (emotion value text for system prompt) and its use case. It could specify format details or edge cases, but it is complete enough for an agent to understand and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already fully documents the only parameter, user_id, as '用户唯一标识' (user unique identifier). The description adds no additional parameter context, so it neither enhances nor detracts from schema coverage. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states a specific action: 'Generate emotion value text that can be injected into system prompt, enabling the AI to role-play based on current emotion values.' It clearly identifies the resource (emotion values) and the output (injectable prompt text), and the explicit mention of 'system prompt' distinguishes it from sibling tools like emotion_get_status and emotion_get_analysis_prompt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use: when a system prompt with current emotion values is needed for role-play. It implicitly differentiates from sibling tools by focusing on prompt generation, but it does not explicitly name alternatives or state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
获取用户当前情绪数值面板，返回所有情绪维度的当前值和基线值
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must bear the burden of behavioral disclosure. It indicates a read operation ('获取') and explains the return content, but does not explicitly state side effects (or lack thereof), permissions, or edge cases. The main behavior is clear but not deeply transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the action and return value. It is concise, front-loaded, and contains no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter and no output schema. The description explains what it does and what it returns. However, it does not clarify how this tool relates to sibling tools like emotion_get_status, which could be a minor completeness gap for a simple read operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has full coverage (100%) for the only parameter 'user_id' with a description. The tool description does not add any additional parameter semantics, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the user's current emotion numerical panel and returns current and baseline values for all emotion dimensions. It uses a specific verb (获取) and resource (panel), but does not explicitly differentiate from siblings like emotion_get_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention any context, exclusions, or alternative tools, leaving the agent without usage criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
获取用户完整情绪档案：好感度、力比多/攻击性、情感标签、对话轮次、完整参考表
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | 用户唯一标识 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden of behavioral disclosure. It transparently lists the data categories returned, including favorability, libido/aggression, emotional tags, conversation turns, and full reference table. The verb '获取' implies read-only behavior, but it does not address possible errors or auth requirements; still, for a simple getter, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently communicates the tool's purpose and the key output components. Every element contributes informational value with no filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter getter with no output schema, the description provides sufficient context by naming the major return categories. The phrase '完整参考表' is somewhat vague, but overall the description is complete enough for an agent to understand what the tool returns and when to consider it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema fully covers the only parameter (user_id) with the Chinese description '用户唯一标识'. Since schema description coverage is 100%, the baseline applies; the tool description adds no extra parameter context, but none is needed for a single self-explanatory identifier.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('获取') and resource ('用户完整情绪档案') and enumerates the exact contents: favorability, libido/aggression, emotion tags, conversation turns, and a full reference table. This clearly differentiates it from sibling tools like emotion_get_panel or emotion_get_emotion_prompt by focusing on the complete status profile.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the sibling tools. The description implies retrieval of the full emotional status, but it does not state contexts where alternatives (e.g., emotion_get_panel) would be more appropriate, nor does it mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
重置指定用户的情绪数值至初始状态
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | 要重置的用户 uid |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the action ('reset to initial state') but does not disclose side effects, whether the operation is destructive, required permissions, irreversibility, or what 'initial state' specifically means. For a mutation tool, this is a significant lack of behavioral detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that is front-loaded with the action. Every word contributes meaning without redundancy, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one required parameter and no output schema, so the description is minimally adequate. However, it lacks contextual information about what 'initial state' constitutes, when to invoke this tool, and what side effects to expect, which would help the agent use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with user_id documented as '要重置的用户 uid'. The tool description adds no additional meaning about the parameter beyond what the schema already provides. Baseline of 3 is appropriate when the schema fully documents parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action (reset) on a specific resource (specified user's emotion values) with a clear target state (initial). It distinguishes from sibling emotion_reset_all by emphasizing 'specified user', and from emotion_set by focusing on resetting rather than setting arbitrary values.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: it is for resetting a single user's emotions. However, it does not explicitly state when to use this tool versus alternatives like emotion_reset_all (reset all users) or emotion_set (set specific values), nor does it mention any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
⚠️ 清除所有用户情绪档案，重置机器人自身情绪
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies destructive behavior ('clear', 'reset') but does not explicitly state whether the action is irreversible, affects all users globally, or requires special permissions. With no annotations provided, the description carries the full burden and falls short by omitting these critical consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with a warning symbol, efficiently conveying the core action. Every word adds value without redundancy, making it appropriately concise for a zero-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool, the description is minimally viable but leaves gaps: it does not define what 'reset' returns to (default state?), whether the action is reversible, or how it differs from emotion_reset. While the essential behavior is clear, the absence of these contextual details prevents a higher score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the input schema is empty. Per baseline rules, 0 params warrant a score of 4. The description adds no parameter-specific information because none exist, but it clearly conveys the tool's global scope.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action: clearing all user emotion profiles and resetting the robot's own emotion. It uses specific verbs (清除/重置) and names the exact resources affected, distinguishing it from sibling tools like emotion_reset through the scope 'all'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs. alternatives such as emotion_reset. The warning emoji hints at caution but does not explicitly state conditions or exclusions. There is no mention of prerequisites or scenarios where this tool should be avoided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
手动设置用户情绪数值。未指定的字段保持不变
| Name | Required | Description | Default |
|---|---|---|---|
| user_id | Yes | ||
| affection | No | 好感度 0-100 | |
| libido_self | No | 自力比多 0-50 | |
| libido_other | No | 他力比多 0-50 | |
| aggression_self | No | 自攻击性 0-50 | |
| aggression_other | No | 他攻击性 0-50 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the critical partial-update behavior ('unspecified fields remain unchanged') and that it is a set operation, which is sufficient for this simple setter. It could mention persistence or side effects, but these are not essential here.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the action and immediately adds the key preservation behavior. Every word earns its place, with no redundant content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple setter nature and 6 parameters, the schema thoroughly documents ranges, and the description covers partial updates. No output schema is present, so return values are not needed. The description is complete for typical usage without being verbose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema descriptions cover ranges for 5 of 6 parameters (83%), and the description adds crucial semantics: omitting an optional field preserves its value. This goes beyond the schema's per-field descriptions and is essential for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('manually set') and the resource ('user emotion values'), and the note about unspecified fields remaining unchanged distinguishes it from other modifying tools like emotion_apply_deltas or emotion_reset. It is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'manually set' implies direct assignment versus incremental changes from emotion_apply_deltas, but there is no explicit when-to-use or mention of alternatives. It provides enough context for basic use but lacks explicit exclusionary guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.2emotion_analyzeemotion_apply_decayemotion_apply_deltasemotion_get_analysis_promptemotion_get_emotion_promptemotion_get_panelemotion_get_statusemotion_resetemotion_reset_allemotion_setScored across 10 tools
Several get tools overlap in the data they return. get_panel and get_status both provide current emotion values, and get_analysis_prompt also includes current values, which could confuse agents. However, descriptions clearly differentiate their broader purposes (UI panel, full profile, analysis task), so overlaps are manageable.
All tools use the emotion_ prefix with snake_case, and verbs like get, apply, set, reset are consistent and predictable. The pattern is verb_noun or verb, with only minor exceptions like emotion_analyze and emotion_reset_all, but these are still clear and uniform.
10 tools is well within the typical 3-15 range and each tool serves a distinct function in managing emotion state. The number feels appropriate for a focused emotion management server, covering read, update, reset, and analysis operations without unnecessary bloat.
The server covers the full emotion lifecycle: reading (get_panel, get_status, get_analysis_prompt), updating (set, apply_deltas, analyze, apply_decay), and resetting (reset, reset_all). Minor gaps like listing all users are not essential for typical role-play scenarios, so the surface is almost complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Persistent AI entity framework with causal memory, emotional state, and identity.
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Psychological text analysis: tone, emotions, communication style, multilingual replies.
Bilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yaoxiaolinglong/emotion-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server