Skip to main content
Glama
enesjakozh
TakumiY235

UniProt MCP Server

by TakumiY235
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

UniProt MCP サーバー

UniProtタンパク質情報へのアクセスを提供するモデルコンテキストプロトコル（MCP）サーバー。このサーバーにより、AIアシスタントはUniProtからタンパク質の機能と配列情報を直接取得できます。

特徴

  • UniProtアクセッション番号でタンパク質情報を取得する

  • 複数のタンパク質のバッチ検索

  • パフォーマンス向上のためのキャッシュ（24時間TTL）

  • エラー処理とログ記録

  • 情報には以下が含まれます:

    • タンパク質名

    • 機能の説明

    • フルシーケンス

    • シーケンスの長さ

    • 生物

Related MCP server: UniProt MCP Server

クイックスタート

  1. Python 3.10以降がインストールされていることを確認してください

  2. このリポジトリをクローンします:

    git clone https://github.com/TakumiY235/uniprot-mcp-server.git
cd uniprot-mcp-server

  3. 依存関係をインストールします:

    # Using uv (recommended)
uv pip install -r requirements.txt

# Or using pip
pip install -r requirements.txt

構成

Claude Desktop 構成ファイルに以下を追加します:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "uniprot": {
      "command": "uv",
      "args": ["--directory", "path/to/uniprot-mcp-server", "run", "uniprot-mcp-server"]
    }
  }
}

使用例

Claude Desktop でサーバーを構成した後、次のような質問をすることができます。

Can you get the protein information for UniProt accession number P98160?

バッチクエリの場合:

Can you get and compare the protein information for both P04637 and P02747?

APIリファレンス

ツール

  1. get_protein_info

    • 単一のタンパク質の情報を取得する

    • 必須パラメータ: accession (UniProt アクセッション番号)

    • 応答例:

      {
  "accession": "P12345",
  "protein_name": "Example protein",
  "function": ["Description of protein function"],
  "sequence": "MLTVX...",
  "length": 123,
  "organism": "Homo sapiens"
}

  2. get_batch_protein_info

    • 複数のタンパク質の情報を取得する

    • 必須パラメータ: accessions (UniProt アクセッション番号の配列)

    • タンパク質情報オブジェクトの配列を返します

発達

開発環境の設定

  1. リポジトリをクローンする

  2. 仮想環境を作成します。

    python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

  3. 開発依存関係をインストールします。

    pip install -e ".[dev]"

テストの実行

pytest

コードスタイル

このプロジェクトでは以下を使用します:

  • コードフォーマット用の黒

  • インポートソート用のisort

  • 糸くず除去用flake8

  • 型チェックのためのmypy

  • セキュリティチェックの盗賊

  • 依存関係の脆弱性チェックの安全性

すべてのチェックを実行します:

black .
isort .
flake8 .
mypy .
bandit -r src/
safety check

技術的な詳細

  • MCP Python SDKを使用して構築

  • 非同期HTTPリクエストにhttpxを使用する

  • OrderedDictベースのキャッシュを使用して24時間TTLのキャッシュを実装します

  • レート制限と再試行を処理する

  • 詳細なエラーメッセージを提供する

エラー処理

サーバーはさまざまなエラー シナリオを処理します。

  • 無効なアクセス番号（404 応答）

  • API接続の問題（ネットワークエラー）

  • レート制限（429件の回答）

  • 不正な応答（JSON 解析エラー）

  • キャッシュ管理（TTLとサイズ制限）

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。貢献方法は以下の通りです。

  1. リポジトリをフォークする

  2. 機能ブランチを作成します（ git checkout -b feature/amazing-feature ）

  3. 変更をコミットします ( git commit -m 'Add some amazing feature' )

  4. ブランチにプッシュする ( git push origin feature/amazing-feature )

  5. プルリクエストを開く

必要に応じてテストを更新し、既存のコーディング スタイルに準拠するようにしてください。

ライセンス

このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細についてはLICENSEファイルを参照してください。

謝辞

  • タンパク質データAPIを提供するUniProt

  • モデルコンテキストプロトコル仕様のAnthropic

  • このプロジェクトの改善に協力してくれた貢献者

Available Tools

2 tools
get_batch_protein_infoB

Get protein information for multiple accession No.

ParametersJSON Schema
NameRequiredDescriptionDefault
accessionsYesList of UniProt accession No.

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't disclose whether this is a read-only operation, potential rate limits, authentication needs, or what 'protein information' includes (e.g., format, fields). The description is minimal and adds little beyond the basic action.

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, efficient sentence with no wasted words, clearly front-loading the purpose. It is appropriately sized for a simple tool with one parameter.

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

Completeness2/5

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

Given no annotations and no output schema, the description is incomplete. It doesn't explain what 'protein information' entails, potential errors, or behavioral traits, leaving significant gaps for a tool that presumably returns complex data.

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

Parameters3/5

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

Schema description coverage is 100%, with the parameter 'accessions' documented as 'List of UniProt accession No.' in the schema. The description adds no additional meaning beyond this, such as format examples, constraints, or usage tips, so it meets the baseline for high schema coverage.

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

Purpose4/5

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

The description clearly states the action ('Get protein information') and the resource ('multiple accession No.'), making the purpose understandable. It distinguishes from the sibling tool 'get_protein_info' by specifying 'multiple' vs. presumably single, though not explicitly naming the alternative.

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?

The description implies usage when multiple accession numbers are needed, but provides no explicit guidance on when to use this vs. the sibling tool 'get_protein_info' (e.g., for bulk vs. single queries). No exclusions or prerequisites are mentioned.

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

get_protein_infoB

Get protein function and sequence information from UniProt using an accession No.

ParametersJSON Schema
NameRequiredDescriptionDefault
accessionYesUniProt Accession No. (e.g., P12345)

TDQS

B3.2/5.0
Behavior2/5

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 mentions the data source (UniProt) and type of information, but lacks details on behavioral traits like rate limits, error handling, authentication needs, or response format. This is a significant gap for a tool with no annotation coverage.

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, efficient sentence that front-loads the purpose without unnecessary words. Every part of the sentence contributes to understanding the tool's function.

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

Completeness2/5

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

Given no annotations and no output schema, the description is incomplete. It does not explain what the return values look like (e.g., format of function and sequence information), error cases, or other contextual details needed for effective use.

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

Parameters3/5

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

The schema description coverage is 100%, with the parameter 'accession' well-documented in the schema. The description adds minimal value by mentioning 'UniProt Accession No.' and providing an example, but does not elaborate beyond what the schema already specifies.

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

Purpose4/5

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

The description clearly states the action ('Get') and resource ('protein function and sequence information from UniProt'), specifying the data source and type of information retrieved. It distinguishes from the sibling tool 'get_batch_protein_info' by implying this is for single proteins, though not explicitly contrasting them.

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?

The description implies usage when you have a UniProt accession number and need protein details, but does not explicitly state when to use this versus the sibling batch tool or other alternatives. No exclusions or prerequisites are mentioned.

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. 2 tool updates
    • First observedget_batch_protein_info
    • First observedget_protein_info
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: get_protein_info retrieves detailed function and sequence information for a single protein accession, while get_batch_protein_info handles multiple accessions in batch. There is no overlap or ambiguity in their functions.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with 'get_' prefix and snake_case naming. The naming clearly indicates the action (get) and target (protein_info), with batch differentiation for the multi-accession tool.

Tool Count2/5

With only two tools, the server feels severely under-scoped for a UniProt domain. While the tools cover basic retrieval, there are obvious gaps for operations like searching, filtering, or accessing related data (e.g., taxonomy, structures), making the surface too thin for comprehensive protein information workflows.

Completeness2/5

The server is severely incomplete for UniProt functionality. It only provides protein information retrieval (single and batch), missing essential operations like search_by_keyword, get_taxonomy, get_structure, or update tracking. This will cause agent failures when trying to perform typical bioinformatics tasks beyond simple lookups.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • UniProt MCP Server

    vitamin3615
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables language models to fetch protein information from the UniProt database, including protein details, sequences, functions, and structures.
    MIT

  • UniProt MCP Server

    josefdc
    A
    license
    B
    quality
    D
    maintenance
    Provides seamless access to UniProtKB protein database, enabling queries for protein entries, sequences, Gene Ontology annotations, full-text search, and ID mapping across 200+ database types.
    5
    2
    MIT

  • mcp-uniprot

    pipeworx-io
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides access to UniProt protein sequence and function knowledge base, enabling search and retrieval of protein entries, proteomes, taxonomy, and feature annotations.
    190 npm
    MIT

  • mcp-alphafold

    zeinab-sheikhi
    F
    license
    B
    quality
    D
    maintenance
    Provides programmatic access to AlphaFold protein structure predictions and UniProt data, enabling users to retrieve protein structures, summaries, and annotations through natural language.
    3
    -

Appeared in Searches