Git 統合を通じて Overleaf プロジェクトへのアクセスを提供する MCP (Model Context Protocol) サーバーです。これにより、Claude やその他の MCP クライアントは、LaTeX ファイルの読み取り、ドキュメント構造の分析、コンテンツの抽出、および Overleaf プロジェクトへのファイルの書き込みが可能になります。
📄 ファイル管理: Overleaf プロジェクトとの間でファイルのリスト表示、読み取り、書き込みを行います
📋 ドキュメント構造: LaTeX のセクションおよびサブセクションを解析します
🔍 コンテンツ抽出: タイトルを指定して特定のセクションを抽出します
📊 プロジェクト概要: プロジェクトのステータスと構造の概要を取得します
🏗️ マルチプロジェクト対応: 複数の Overleaf プロジェクトを管理します
Related MCP server: overleaf-mcp
クローンや npm install は不要です。以下のブロックを Claude Desktop の設定に追加し、Claude Desktop を再起動してください。
設定ファイルの場所
OS | パス |
Windows |
|
macOS |
|
Linux |
|
macOS / Linux
{
"mcpServers": {
"overleaf": {
"command": "npx",
"args": ["-y", "@mjyoo2/overleaf-mcp"],
"env": {
"OVERLEAF_PROJECT_ID": "YOUR_OVERLEAF_PROJECT_ID",
"OVERLEAF_GIT_TOKEN": "YOUR_OVERLEAF_GIT_TOKEN"
}
}
}
}Windows — Windows 上の Claude Desktop では npx を見つけるために cmd /c が必要です：
{
"mcpServers": {
"overleaf": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@mjyoo2/overleaf-mcp"],
"env": {
"OVERLEAF_PROJECT_ID": "YOUR_OVERLEAF_PROJECT_ID",
"OVERLEAF_GIT_TOKEN": "YOUR_OVERLEAF_GIT_TOKEN"
}
}
}
}Claude Desktop を再起動します。🔧 メニューに overleaf ツールが表示されるはずです。
環境変数によるクイックスタートは単一プロジェクトのみを扱います。複数のプロジェクトを扱う場合は、projects.json ファイルをユーザー設定ディレクトリに配置し、Claude Desktop 設定の env ブロックを省略してください。
ファイルの場所
OS | パス |
Windows |
|
macOS / Linux |
|
ファイルの内容
{
"projects": {
"default": {
"name": "Main Paper",
"projectId": "...",
"gitToken": "olp_..."
},
"thesis": {
"name": "PhD Thesis",
"projectId": "...",
"gitToken": "olp_..."
}
}
}Claude Desktop 設定 — クイックスタートと同じですが、env ブロックはありません：
{
"mcpServers": {
"overleaf": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@mjyoo2/overleaf-mcp"]
}
}
}(macOS / Linux では cmd /c を削除してください。)
ツール呼び出しで projectName を指定して特定のプロジェクトを参照します：
Use read_file with filePath: "main.tex", projectName: "thesis"projectName を省略した場合は、default エントリが使用されます。projects.json を標準以外の場所に配置したい場合は、env ブロックから OVERLEAF_PROJECTS_CONFIG=/absolute/path/projects.json を指定してください。
プロジェクト ID — Overleaf プロジェクトを開きます。ID は URL に含まれています：https://www.overleaf.com/project/[PROJECT_ID]
Git トークン — Overleaf → Account Settings → Git Integration → "Create Token"
サーバーは最初に見つかった設定ソースを採用します：
環境変数 (単一プロジェクト) — OVERLEAF_PROJECT_ID + OVERLEAF_GIT_TOKEN。オプション: 表示名用の OVERLEAF_PROJECT_NAME。
ファイルからのトークン — OVERLEAF_PROJECT_ID と共に OVERLEAF_GIT_TOKEN_FILE=/path/to/token.txt を設定します (OVERLEAF_GIT_TOKEN の代わり)。Claude Desktop の JSON にトークンを含めたくない場合に便利です。ファイルは起動時に一度読み込まれ、末尾の空白や改行は削除されます。
マルチプロジェクトファイル — OVERLEAF_PROJECTS_CONFIG=/absolute/path/projects.json。
ユーザー設定ディレクトリ — 以下の場所にある projects.json:
Windows: %APPDATA%\overleaf-mcp\projects.json
macOS / Linux: $XDG_CONFIG_HOME/overleaf-mcp/projects.json (デフォルトは ~/.config/overleaf-mcp/projects.json)
作業ディレクトリ — ./projects.json
パッケージディレクトリ — サーバースクリプトの隣にある projects.json (レガシー、クローンベースのインストール用)。
環境変数が設定されており、かつファイルも存在する場合は、環境変数が優先され、上書きされていることがわかるように stderr に通知が記録されます。
projects.json スキーマ (マルチプロジェクト){
"projects": {
"default": {
"name": "Main Paper",
"projectId": "...",
"gitToken": "olp_..."
},
"paper2": {
"name": "Second Paper",
"projectId": "...",
"gitToken": "olp_..."
}
}
}その後、ツール呼び出しでプロジェクトを指定します：projectName: "paper2"。
サーバーのハック、公開前の変更テスト、または npm パッケージを利用せずに使用したい場合は、3 つのローカルインストールオプションがあります。
git clone https://github.com/mjyoo2/OverleafMCP.git
cd OverleafMCP
npm install次に、Claude Desktop でスクリプトを指定し、環境変数経由で認証情報を渡します (npm パッケージが使用するのと同じローダーパス)：
{
"mcpServers": {
"overleaf": {
"command": "node",
"args": ["/absolute/path/to/OverleafMCP/overleaf-mcp-server.js"],
"env": {
"OVERLEAF_PROJECT_ID": "...",
"OVERLEAF_GIT_TOKEN": "olp_..."
}
}
}
}Windows では、args に "C:\\Users\\you\\OverleafMCP\\overleaf-mcp-server.js" を使用する必要があります。
マルチプロジェクトファイルを使用したい場合：
cp projects.example.json projects.json # then edit itスクリプトの隣にある projects.json は最も優先順位の低いフォールバックであるため、環境変数なしでも動作します。
ユーザーがパブリックレジストリを通じて利用するものとほぼ同じコードパスを検証します。リリースをプッシュする前に便利です：
npm pack
# → mjyoo2-overleaf-mcp-<version>.tgzClaude Desktop で tarball を指定します。明示的な --package= と bin 名に注意してください。npx -y <tarball-path> は npm 10+ では動作しません (パスが実行ファイルとして誤検出されるため)：
{
"mcpServers": {
"overleaf": {
"command": "cmd",
"args": [
"/c", "npx", "-y",
"--package=C:\\absolute\\path\\to\\mjyoo2-overleaf-mcp-<version>.tgz",
"overleaf-mcp"
],
"env": {
"OVERLEAF_PROJECT_ID": "...",
"OVERLEAF_GIT_TOKEN": "olp_..."
}
}
}
}macOS / Linux では cmd /c ラッパーを削除します："command": "npx", "args": ["-y", "--package=/abs/path/to/...tgz", "overleaf-mcp"]。
Claude Desktop は不要です：
OVERLEAF_PROJECT_ID=... OVERLEAF_GIT_TOKEN=... node overleaf-mcp-server.jsstderr に Overleaf MCP server running on stdio と表示されるはずです。プロセスは stdin で JSON-RPC を待機したまま開いた状態になります。Ctrl+C で終了します。
list_projects設定されたすべてのプロジェクトをリスト表示します。
list_filesプロジェクト内のファイルをリスト表示します (デフォルト: .tex ファイル)。
extension: ファイル拡張子のフィルタ (オプション)
projectName: プロジェクト識別子 (オプション、デフォルトは "default")
read_fileプロジェクトから特定のファイルを読み取ります。
filePath: ファイルへのパス (必須)
projectName: プロジェクト識別子 (オプション)
get_sectionsLaTeX ファイルからすべてのセクションを取得します。
filePath: LaTeX ファイルへのパス (必須)
projectName: プロジェクト識別子 (オプション)
get_section_content特定のセクションのコンテンツを取得します。
filePath: LaTeX ファイルへのパス (必須)
sectionTitle: セクションのタイトル (必須)
projectName: プロジェクト識別子 (オプション)
status_summary包括的なプロジェクトステータスの概要を取得します。
projectName: プロジェクト識別子 (オプション)
write_fileファイルの全コンテンツをプロジェクトに書き込みます。
filePath: ファイルへのパス (必須)
content: ファイルに書き込むコンテンツ (必須)
commitMessage: コミットメッセージ (必須)
projectName: プロジェクト識別子 (オプション)
write_section特定のセクションのコンテンツをプロジェクトに書き込みます。
filePath: LaTeX ファイルへのパス (必須)
sectionTitle: セクションのタイトル (必須)
newContent: セクションの見出しを含む、セクションの置換コンテンツ (必須)
commitMessage: コミットメッセージ (必須)
projectName: プロジェクト識別子 (オプション)
# List all projects
Use the list_projects tool
# Get project overview
Use status_summary tool
# Read main.tex file
Use read_file with filePath: "main.tex"
# Get Introduction section
Use get_section_content with filePath: "main.tex" and sectionTitle: "Introduction"
# List all sections in a file
Use get_sections with filePath: "main.tex"
# Write the full content of a file to the project
Use write_file with filePath: "main.tex", content: "...", commitMessage: "..."
# Write the content of a specific section to the project
Use write_section with filePath: "main.tex", sectionTitle: "Introduction", newContent: "\\section{Introduction}\n...", commitMessage: "..."Overleaf Git トークンはプロジェクトへの完全な読み取り/書き込みアクセス権を付与します。パスワードのように扱ってください。
設定ファイルがバックアップや同期される場合は、Claude Desktop の JSON にトークンを直接記述するよりも OVERLEAF_GIT_TOKEN_FILE を優先してください。
projects.json はこのリポジトリで .gitignore されています。実際のプロジェクト ID や Git トークンをコミットしないでください。
MCP ツール呼び出しを通じて提供されるファイルパスは、クローンされたプロジェクトディレクトリ内に制限されています。.. によるトラバーサルや絶対パスは拒否されます。
MIT ライセンス
Get content of a specific section
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the LaTeX file | |
| gitToken | No | Git token (optional, uses env var) | |
| projectId | No | Project ID (optional, uses env var) | |
| projectName | No | Project name (default, project2, etc.) | |
| sectionTitle | Yes | Title of the section |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('Get content') without detailing how it works (e.g., whether it fetches from a repository, handles errors, or returns structured data). This leaves critical behavioral traits like permissions, rate limits, or output format unspecified.
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 with no wasted words. It's front-loaded with the core purpose, making it easy to parse quickly, though this conciseness comes at the cost of detail.
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 complexity (5 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what 'content' means (e.g., text, metadata), how it relates to LaTeX files or Git, or what the output looks like. This leaves significant gaps for an agent to understand the tool's full context.
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 all parameters documented in the input schema. The description adds no additional meaning beyond what the schema provides (e.g., it doesn't explain the relationship between parameters like 'filePath' and 'sectionTitle'). Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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 the tool's purpose as 'Get content of a specific section', which is clear but vague. It specifies the verb 'Get' and resource 'content of a specific section', but doesn't distinguish it from sibling tools like 'read_file' or 'get_sections', leaving ambiguity about what makes this tool unique.
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 alternatives. The description doesn't mention sibling tools like 'read_file' (which might read entire files) or 'get_sections' (which might list sections), nor does it specify prerequisites or contexts for usage, leaving the agent without direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all sections from a LaTeX file
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the LaTeX file | |
| gitToken | No | Git token (optional, uses env var) | |
| projectId | No | Project ID (optional, uses env var) | |
| projectName | No | Project name (default, project2, etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Get all sections' but doesn't explain what 'sections' means (e.g., LaTeX section commands like \section), how they are returned (e.g., list of strings, structured data), or any limitations (e.g., file size, parsing errors). This leaves significant gaps in understanding the tool's behavior.
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 with no wasted words, making it easy to parse and understand quickly. It's appropriately sized for a simple tool and front-loads the core action.
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 complexity (4 parameters, no output schema, no annotations), the description is incomplete. It doesn't address what the tool returns (e.g., format of sections), error handling, or dependencies between parameters. For a tool that parses LaTeX files, more context is needed to use it effectively.
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%, so the input schema already documents all parameters thoroughly. The description adds no additional meaning beyond the schema, such as explaining interactions between parameters (e.g., how gitToken and projectId relate to filePath). Baseline 3 is appropriate when the schema does the heavy lifting.
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 verb 'Get' and the resource 'sections from a LaTeX file', making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_section_content' or 'read_file', which might have overlapping functionality, so it doesn't reach the highest score.
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 such as 'get_section_content' or 'read_file'. It lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all files in an Overleaf project
| Name | Required | Description | Default |
|---|---|---|---|
| extension | No | File extension filter (e.g., .tex) | .tex |
| gitToken | No | Git token (optional, uses env var) | |
| projectId | No | Project ID (optional, uses env var) | |
| projectName | No | Project name (default, project2, etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states the basic action without disclosing behavioral traits. It doesn't mention whether this is a read-only operation, what permissions are needed, how results are formatted, or any rate limits, which is insufficient for a tool with 4 parameters.
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 states the core purpose without any wasted words. It's appropriately sized and front-loaded, making it easy to parse quickly.
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 4 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain return values, error conditions, or behavioral context needed for effective use, leaving significant gaps despite the concise statement of purpose.
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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning about parameters beyond implying a listing operation, meeting the baseline score when schema does the heavy lifting.
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 verb 'List' and resource 'files in an Overleaf project', making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'list_projects' or 'get_sections', which would require explicit comparison to achieve a score of 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 provides no guidance on when to use this tool versus alternatives like 'list_projects' or 'get_sections'. There's no mention of prerequisites, context, or exclusions, leaving the agent without usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available projects
| 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 carries the full burden of behavioral disclosure. 'List all available projects' implies a read-only operation, but it doesn't specify behavioral traits such as pagination, sorting, filtering, rate limits, authentication needs, or what 'available' means (e.g., active vs. archived). This leaves significant gaps for an agent to understand how to interact with the tool effectively.
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 with zero waste: 'List all available projects'. It is front-loaded and directly conveys the core purpose without unnecessary elaboration, making it highly concise and well-structured for its simplicity.
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 lack of annotations and output schema, the description is incomplete for contextual understanding. It doesn't explain what 'projects' entail, the format of the returned list, or any constraints like visibility or access controls. For a tool with no structured support, more context is needed to guide the agent fully, especially regarding behavioral aspects.
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 0 parameters with 100% coverage, meaning no parameters are documented in the schema. The description doesn't add parameter details, which is appropriate since there are none to describe. This meets the baseline for tools with zero parameters, as there's no need to compensate for missing schema information.
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 'List all available projects' clearly states the verb ('List') and resource ('projects') with scope ('all available'). It distinguishes from siblings like 'list_files' (different resource) and 'get_sections' (different operation), though it doesn't explicitly differentiate from them. The purpose is unambiguous but lacks explicit sibling comparison.
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 doesn't mention prerequisites, context for usage, or comparisons to siblings like 'get_sections' or 'list_files'. The agent must infer usage based solely on the tool name and description without explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a file from an Overleaf project
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the file | |
| gitToken | No | Git token (optional, uses env var) | |
| projectId | No | Project ID (optional, uses env var) | |
| projectName | No | Project name (default, project2, etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool reads a file but doesn't mention permissions required, rate limits, error handling, or what the output looks like (e.g., file content format). This is a significant gap for a tool that interacts with external resources.
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, direct sentence that efficiently conveys the core purpose without any fluff. It is appropriately sized and front-loaded, making it easy to parse quickly.
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 complexity of reading files from a project management system, no annotations, and no output schema, the description is incomplete. It doesn't address behavioral aspects like authentication needs, error cases, or output format, which are crucial for effective tool use.
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 description coverage is 100%, so the schema already documents all parameters well. The description adds no additional meaning beyond the schema, such as explaining how 'filePath' relates to Overleaf's structure or when to use 'gitToken' versus environment variables. Baseline 3 is appropriate as the schema does the heavy lifting.
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 ('Read') and resource ('a file from an Overleaf project'), making the tool's purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_section_content' or 'list_files', which might have overlapping functionality in reading file content, so it misses the highest score.
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 alternatives such as 'get_section_content' or 'list_files'. The description lacks context about scenarios where this tool is preferred, prerequisites, or exclusions, leaving usage ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a summary of the project status using default credentials
| Name | Required | Description | Default |
|---|---|---|---|
| projectName | No | Project name (default, project2, etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'using default credentials', which adds some context about authentication, but fails to describe critical traits like whether this is a read-only operation, what the output format is, or any rate limits or side effects. For a tool with zero annotation coverage, this leaves significant gaps.
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 with no wasted words. It is appropriately sized for a simple tool and front-loaded with the core purpose, making it easy to parse quickly.
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 no annotations and no output schema, the description is incomplete for a tool that presumably returns a status summary. It lacks details on what the summary includes, format, or any behavioral context beyond credentials. For a tool with 1 parameter and no structured output documentation, more information is needed to guide effective use.
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 100% description coverage, with the parameter 'projectName' documented as 'Project name (default, project2, etc.)'. The description adds no additional meaning beyond this, such as explaining what 'default' refers to or how the parameter influences the summary. Baseline 3 is appropriate when the schema does the heavy lifting.
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 ('Get a summary') and resource ('project status'), making the purpose understandable. It doesn't differentiate from siblings like 'list_projects' or 'get_sections', which would require more specificity about what distinguishes a status summary from other project-related operations.
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 like 'list_projects'. It mentions 'using default credentials', which hints at authentication context but doesn't clarify prerequisites or exclusions for usage relative to other tools.
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.
v1.0.0get_section_contentget_sectionslist_fileslist_projectsread_filestatus_summaryScored across 6 tools
Each tool has a clearly distinct purpose targeting different resources or actions: list_projects (projects), list_files (files within a project), read_file (content of a file), get_sections (sections within a file), get_section_content (content of a specific section), and status_summary (project overview). There is no overlap or ambiguity in their functions.
All tool names follow a consistent verb_noun pattern with snake_case: list_projects, list_files, read_file, get_sections, get_section_content, and status_summary. The verbs (list, read, get) are appropriate and predictable, making the set easy to navigate.
With 6 tools, this server is well-scoped for managing Overleaf projects, covering core operations like listing projects/files, reading content, and getting summaries. The count is appropriate—neither too sparse nor bloated—for the domain of LaTeX project management.
The tool set provides good coverage for reading and listing operations in Overleaf projects, but there are minor gaps in write/update capabilities (e.g., no tools for creating or editing files/sections). Agents can work around this for read-only tasks, but full lifecycle management is incomplete.
Edit your Overleaf LaTeX projects from Claude and ChatGPT; every change is a real Git commit.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Read and write KukGit repositories, files, issues and pull requests from an AI assistant.
Persistent AI LaTeX workspace: edit and compile multi-file projects, export publication-ready PDFs.
