Farcaster ネットワーク ( farcaster.xyz ) と対話するためのツールを提供する MCP サーバー。AI モデルがキャストを取得したり、チャンネルを検索したり、コンテンツを分析したりできるようになります。
ユーザーキャストの取得: FID で特定の Farcaster ユーザーからのキャストを取得します。
ユーザー名キャストの取得: ユーザー名で特定の Farcaster ユーザーからのキャストを取得します。
チャンネルキャストの取得: 特定の Farcaster チャンネルからキャストを取得します
Related MCP server: Lens Protocol MCP Server
# Clone the repository
git clone https://github.com/manimohans/farcaster-mcp.git
cd farcaster-mcp
# Install dependencies
npm install
# Build the project
npm run buildnpm startnpx @modelcontextprotocol/inspector node ./build/index.jsデスクトップ版Claudeをインストールする
次の場所で Claude for Desktop App の構成を開きます:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
次の構成を追加します。
{
"mcpServers": {
"farcaster": {
"command": "node",
"args": ["/absolute/path/to/farcaster-mcp/build/index.js"]
}
}
}デスクトップ版のClaudeを再起動する
このプロジェクトには、簡単に展開できるように Smithery 構成ファイルが含まれています。
# Install Smithery CLI
npm install -g @smithery/cli
# Deploy to Smithery (specify the client, e.g., claude, cline, windsurf, etc.)
npx @smithery/cli install @manimohans/farcaster-mcp --client claude利用可能なクライアントオプション: claude、cline、windsurf、roo-cline、witsy、enconvo
特定の Farcaster ユーザーからのキャストを FID (Farcaster ID) で取得します。
パラメータ:
fid : Farcaster ユーザー ID (数値)
limit (オプション): 返されるキャストの最大数 (デフォルト: 10)
クエリの例:「FID 6846 からの最新のキャストを表示してください。」
特定の Farcaster ユーザーからのキャストをユーザー名で取得します。
パラメータ:
username : Farcasterのユーザー名（文字列）
limit (オプション): 返されるキャストの最大数 (デフォルト: 10)
クエリの例:「ユーザー名「mani」の最新のキャストを表示してください。」
特定の Farcaster チャネルからキャストを取得します。
パラメータ:
channel : チャンネル名またはURL（文字列）
limit (オプション): 返されるキャストの最大数 (デフォルト: 10)
クエリの例: 「「aichannel」チャンネルの最新のキャストを表示してください。」
このリポジトリには、Smithery に必要な構成ファイルが含まれています。
smithery.yaml : Smithery デプロイメント用の YAML 構成
smithery.json : Smithery 機能の JSON 設定
Dockerfile : Smithery デプロイメント用のコンテナ構成
この実装では、Farcaster Hubble API を使用してデータを取得します。
# Run in development mode
npm run devマサチューセッツ工科大学
Get casts from a specific Farcaster channel
| Name | Required | Description | Default |
|---|---|---|---|
| channel | Yes | Channel name (e.g., 'aichannel') or URL | |
| limit | No | Maximum number of casts to return (default: 10) |
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 what the tool does but doesn't describe behavioral traits such as whether it's read-only, has rate limits, authentication needs, pagination behavior, or what the return format looks like. This leaves significant gaps for a tool that presumably fetches data.
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 directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with every part contributing to understanding the core function.
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 a data-fetching tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects like safety, response format, or error handling, which are crucial for an agent to use the tool effectively in 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 description doesn't add any parameter-specific information beyond what's already in the input schema, which has 100% schema description coverage. It mentions 'specific Farcaster channel' but doesn't elaborate on the 'channel' parameter's semantics or the 'limit' parameter's implications. Baseline 3 is appropriate since 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 casts') and target resource ('from a specific Farcaster channel'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'get-user-casts' or 'get-username-casts', which would require mentioning channel-specific versus user-specific retrieval.
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 the sibling tools 'get-user-casts' or 'get-username-casts'. It lacks any context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based on 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 casts from a specific Farcaster user by FID
| Name | Required | Description | Default |
|---|---|---|---|
| fid | Yes | Farcaster user ID (FID) | |
| limit | No | Maximum number of casts to return (default: 10) |
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 what the tool does but lacks details on permissions, rate limits, error handling, or return format. For a read operation with no annotations, this leaves significant gaps in understanding how the tool behaves.
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 with zero waste. It is front-loaded with the core purpose and efficiently conveys the essential information without unnecessary elaboration.
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 low complexity (2 parameters, no output schema, no annotations), the description is minimally adequate but incomplete. It lacks details on behavioral aspects like pagination, error cases, or output structure, which are important for a read operation without annotations to guide the agent.
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 both parameters (fid and limit) adequately. The description adds no additional meaning beyond what the schema provides, such as parameter interactions or usage examples, which aligns with the baseline score when schema coverage is high.
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 casts') and specifies the resource ('from a specific Farcaster user by FID'), making the purpose explicit. It distinguishes from sibling tools like 'get-channel-casts' and 'get-username-casts' by focusing on user ID rather than channel or username.
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 'get-username-casts' or 'get-channel-casts'. It does not mention prerequisites, exclusions, or contextual factors that would help an agent choose between these sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get casts from a specific Farcaster username
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | Farcaster username | |
| limit | No | Maximum number of casts to return (default: 10) |
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 what the tool does but lacks details on traits like whether it's read-only, requires authentication, has rate limits, returns paginated results, or handles errors. For a retrieval tool with zero annotation coverage, this is a significant gap in transparency.
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 directly states the tool's purpose without unnecessary words. It's front-loaded with the core action and resource, making it easy to parse. Every word earns its place, achieving optimal 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 complexity (data retrieval with parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'casts' entail (e.g., content, metadata), return format, error handling, or behavioral constraints. For a tool with these contextual gaps, the description should provide more completeness to aid the agent.
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%, with clear descriptions for both parameters ('username' as Farcaster username and 'limit' with default). The description adds no additional parameter semantics beyond what the schema provides, such as format examples for usernames or constraints on limit values. Baseline 3 is appropriate since 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 resource 'casts from a specific Farcaster username', making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get-channel-casts' and 'get-user-casts', which likely retrieve casts by different criteria. The description is specific but lacks sibling distinction.
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. With sibling tools like 'get-channel-casts' and 'get-user-casts' available, there's no indication of when this username-based retrieval is preferred, such as for public profiles or specific user identification. 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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get-channel-castsget-user-castsget-username-castsScored across 3 tools
The three tools all retrieve casts but from different sources (channel, user by FID, username), which provides some distinction. However, the overlap in purpose (getting casts) and the potential confusion between user-based tools (FID vs. username) create moderate ambiguity, as an agent might struggle to choose the right one without clear context about the available identifier.
All tool names follow a consistent verb-noun pattern with hyphens (get-channel-casts, get-user-casts, get-username-casts). This uniformity makes the set predictable and easy to understand, with no deviations in naming style or structure.
With only 3 tools, the server feels thin for a Farcaster domain, which likely involves more operations like posting casts, interacting with content, or accessing user profiles. This limited set may hinder agents from performing comprehensive tasks, indicating an under-scoped tool surface.
The tool set is severely incomplete for a Farcaster server, covering only read operations for casts from specific sources. It lacks essential CRUD operations such as creating or deleting casts, user management, channel interactions, or broader API features, leaving significant gaps that will cause agent failures in typical workflows.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Discover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs. 17 tools.
X (Twitter) data for AI agents: tweets, profiles, followers, search, trends + social listening.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
