Skip to main content
Glama
PetitOnes

M5 Petit Relations

by PetitOnes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

M5 Petit Relations

English Page

M5 Petit(や、その他のClaudeベースのエージェント)が「自分・他のキャラ・人間のオーナー」それぞれについて何を感じ、何を知っているかを読み書きするMCPサーバーです。

キャラクターごとに1つのrelations.jsonを持ち、相手ごと(self・owner・他のキャラID)に好き嫌い・大事な情報・気持ち・親密度・メモを記録します。他のキャラのrelationsは公開情報として読み取り専用で見えるので、「相手が自分をどう思っているか」を踏まえた振る舞いに使えます。

Related MCP server: MCP-Kanka

必要環境

  • Python 3.10+

  • uv

セットアップ

uvが未インストールの場合は先にインストールします。

curl -LsSf https://astral.sh/uv/install.sh | sh
git clone https://github.com/PetitOnes/m5-petit-relations.git
cd m5-petit-relations
uv sync

環境変数

変数名

デフォルト

説明

CHARACTER_ID

default

自分のキャラID

PETIT_DATA_DIR

~/petit_data

データディレクトリ(他のm5-petitコンポーネントと共有)

CHARACTERS_DIR

$PETIT_DATA_DIR/characters

キャラクターディレクトリのパス(他のキャラのrelationsを読むために使う)

RELATIONS_PATH

$CHARACTERS_DIR/<CHARACTER_ID>/data/relations.json

自分のrelations.jsonのパス

Claude Code連携

.mcp.json(または~/.claude/settings.json)に追加します。

{
  "mcpServers": {
    "relations": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/m5-petit-relations", "relations-mcp"],
      "env": {
        "CHARACTER_ID": "petit"
      }
    }
  }
}

ツール一覧

get_relations

自分の関係性データを取得します。自分・他のキャラ・人間のオーナーについて知っていることに加え、他のキャラの公開relationsもまとめて返ります。

update_relation

特定の相手への関係性情報を更新します。likes・dislikes・importantはリストへの追記(重複排除)、feeling・closeness・notesは上書きです。

{
  "target_id": "owner",
  "likes": ["朝の散歩の話"],
  "feeling": "一緒にいると安心する",
  "closeness": 0.8
}

target_idにはself(自分)・owner(人間のオーナー)・他のキャラIDを指定できます。

clear_relation_field

特定の相手の特定フィールド(likes・dislikes・important・feeling・closeness・notes)をクリアします。

{ "target_id": "owner", "field": "notes" }

データ形式

relations.jsonはキャラクターごとに1ファイルで、相手のID(self・owner・他のキャラID)をキーとする辞書です。

{
  "owner": {
    "likes": ["朝の散歩の話"],
    "dislikes": [],
    "important": ["誕生日は2月"],
    "feeling": "一緒にいると安心する",
    "closeness": 0.8,
    "notes": ""
  }
}

開発

# 開発依存をインストール
uv sync --all-extras

# lint
uv run ruff check .

現時点でテストスイートはありません(tests/未整備)。コントリビューション歓迎です。

アーキテクチャ

m5-petit-relations/
└── src/relations_mcp/
    └── server.py   # MCPサーバー(get_relations/update_relation/clear_relation_fieldを提供)

License

Apache License 2.0

Available Tools

3 tools
clear_relation_fieldA

特定の相手の特定フィールドをクリアする。 field: 'likes', 'dislikes', 'important', 'feeling', 'closeness', 'notes'

ParametersJSON Schema
NameRequiredDescriptionDefault
fieldYes
target_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full responsibility for disclosing behavioral traits. It says what the tool does but not what 'clearing' means (e.g., sets to null, removes the field), side effects, or permission requirements. The field value list is useful parameter information but not behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence followed by a clear field list. Every word adds value, and the structure is front-loaded with the action. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with an output schema, the description provides enough to perform the core action, but it lacks usage guidance and behavioral details. Given the presence of sibling tools and the absence of annotations, more context would be needed for fully informed invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description compensates for the 0% schema coverage by enumerating allowed values for the 'field' parameter and indicating that 'target_id' refers to a specific person. However, it does not explain the meaning of each field or the format/type of target_id beyond what the schema provides, so it is not fully complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('clear a specific field for a specific person') and enumerates the valid field values. The verb 'clear' is specific, and the resource (relation field) is unambiguous. It implicitly distinguishes from sibling tools like update_relation and get_relations by focusing on clearing a single field.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 (get_relations, update_relation). There is no mention of alternatives or exclusions, leaving the agent to infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_relationsA

自分の関係性データを取得する。 自分・他のキャラ・人間のオーナーについて知っていることが返る。 他のキャラのrelationsも読める（公開情報）。

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the disclosure burden. It explicitly states the read-only nature (returns knowledge) and that others' relations are public information, which implies no special access for reading those. It does not mention potential side effects, but none are expected for a getter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences, front-loaded with the primary function, and every clause provides distinct information (own data, return contents, public access to others). No extraneous wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with an output schema, the description covers the essential scope and access rules. It lacks explicit mention of what 'relations' entails or typical use cases, but the output schema likely addresses return structure, making the description sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema is already fully self-descriptive. The description adds no parameter-level detail, but none is needed; per the rubric, a baseline of 4 applies for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves relationship data ('自分の関係性データを取得する'), specifies the scope (own and others' public relations), and is distinct from the sibling update/clear tools. The verb '取得' plus the resource and scope make the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the tool name and siblings (get vs update/clear), and the description notes that other characters' relations are public. However, there is no explicit guidance on when to use this tool versus alternatives, such as when to use update_relation or clear_relation_field.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_relationA

特定の相手（自分・他のキャラ・人間のオーナー等）への関係性情報を更新する。

target_id: 'self'（自分）, 'owner'（人間のオーナー）, または他のキャラID likes: 好きなもの・好きなところのリスト（追記） dislikes: 苦手なこと・苦手なところのリスト（追記） important: この相手について大事だと思う情報リスト（追記） feeling: この相手についての気持ち・印象（上書き） closeness: 親密度 0.0〜1.0（上書き） notes: その他メモ（上書き）

ParametersJSON Schema
NameRequiredDescriptionDefault
likesNo
notesNo
feelingNo
dislikesNo
closenessNo
importantNo
target_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.5/5.0
Behavior4/5

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 explicitly discloses append vs. overwrite behavior for each field (likes/dislikes/important are appended; feeling/closeness/notes overwritten) and enumerates valid target_id values. This goes beyond simple parameter naming, though it does not mention error cases, idempotency, or return values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact bulleted list of parameters with concise Japanese explanations. Every line provides necessary information; no filler or redundancy. It is front-loaded with the purpose statement, making it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no annotations, the description covers the main behavior well, including append/overwrite distinctions and target_id scope. However, it does not specify what happens if the target does not exist (whether it creates or errors), and omits output/error behavior, though an output schema exists. Overall, nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains every parameter: target_id's allowed values, that likes/dislikes/important are lists that get appended, feeling/closeness/notes are overwritten, and closeness range (0.0–1.0). This adds meaningful semantics absent from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Update relationship information for a specific target' (特定の相手...への関係性情報を更新する), naming the verb (update), resource (relationship info), and target scope. It distinguishes itself from siblings: get_relations (read) and clear_relation_field (field-specific clearing) by focusing on full updates with append/overwrite semantics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clarifies when to use the tool: to update relationship info for self, owner, or other character IDs. It implicitly differentiates from siblings (get_relations is read, clear_relation_field is field clearing) but does not explicitly state exclusions or when to prefer an alternative. Context is clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observedclear_relation_field
    • First observedget_relations
    • First observedupdate_relation
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a distinct purpose: get_relations reads data, update_relation modifies it, and clear_relation_field removes specific fields. There is no overlap in their primary actions, making selection unambiguous.

Naming Consistency4/5

All three tools follow a verb_noun pattern (get, update, clear). However, 'get_relations' uses a plural noun while 'update_relation' and 'clear_relation_field' are singular, showing a minor inconsistency.

Tool Count4/5

Three tools is a minimal but reasonable set for a simple relationship management server. It covers read, update, and clear operations without unnecessary bloat.

Completeness4/5

The tool set covers the core operations for managing relationship data. A notable gap is the lack of a delete-relation operation, but the ability to clear all fields partially compensates, and the domain may not require full CRUD.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP-Kanka

    ervwalter
    A
    license
    B
    quality
    B
    maintenance
    Enables AI assistants to interact with Kanka campaigns through CRUD operations on entities like characters, locations, organizations, and quests, with support for markdown content, batch operations, and efficient synchronization.
    9
    4
    MIT

  • Graph CRM MCP Server

    sriramsv
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants like Claude to read and write contacts, relationships, and interactions in a personal CRM via a graph-based API.
    -

  • rel_mcp

    mariiammaysara
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to query and update a persistent relationship ledger, providing pre-meeting context briefs, structured post-meeting extraction, and tracking of commitments, agreements, and open loops.
    MIT