MCP 服务器实现提供了通过矢量搜索检索和处理文档的工具，使 AI 助手能够通过相关文档上下文增强他们的响应。
基于矢量的文档搜索和检索
支持多种文档来源
语义搜索功能
自动化文档处理
法学硕士 (LLM) 的实时上下文增强
Related MCP server: RAG Documentation MCP Server
使用自然语言查询搜索存储的文档。返回符合上下文的摘录，并按相关性排序。
输入：
query （字符串）：要在文档中搜索的文本。可以是自然语言查询、特定术语或代码片段。
limit （数字，可选）：返回结果的最大数量（1-20，默认值：5）。限制值越高，返回结果越全面，但处理时间也越长。
列出系统中当前存储的所有文档来源。返回所有已索引文档的完整列表，包括来源 URL、标题和最后更新时间。使用此列表可以了解哪些文档可供搜索，或验证特定来源是否已被索引。
提取并分析给定网页的所有 URL。此工具会抓取指定网页，识别所有超链接，并选择性地将其添加到处理队列中。
输入：
url （字符串）：待分析网页的完整 URL（必须包含协议，例如 https://）。该页面必须可公开访问。
add_to_queue （布尔值，可选）：如果设置为 true，则自动将提取的 URL 添加到处理队列中，以便稍后进行索引。在大型网站上请谨慎使用，以避免队列过长。
根据 URL 从系统中移除特定文档来源。移除操作是永久性的，并将影响未来的搜索结果。
输入：
urls (string[])：要从数据库中移除的 URL 数组。每个 URL 必须与添加文档时使用的 URL 完全匹配。
列出当前在文档处理队列中等待的所有 URL。显示调用 run_queue 时将处理的待处理文档源。使用此方法可以监控队列状态、验证 URL 是否已正确添加，或检查处理积压情况。
处理并索引当前文档队列中的所有 URL。每个 URL 均按顺序处理，并采用适当的错误处理和重试逻辑。处理过程中会提供进度更新。长时间运行的操作将一直处理，直到队列为空或发生不可恢复的错误。
从文档处理队列中移除所有待处理的 URL。当您想重新开始、移除不需要的 URL 或取消待处理处理时，可以使用此功能重置队列。此操作是即时且永久的 - 如果您希望稍后处理 URL，则需要重新添加。
RAG 文档工具旨在用于：
利用相关文档增强人工智能响应
构建具有文档意识的人工智能助手
为开发人员创建上下文感知工具
实现语义文档搜索
扩充现有知识库
将其添加到您的claude_desktop_config.json中：
{
"mcpServers": {
"rag-docs": {
"command": "npx",
"args": [
"-y",
"@hannesrudolph/mcp-ragdocs"
],
"env": {
"OPENAI_API_KEY": "",
"QDRANT_URL": "",
"QDRANT_API_KEY": ""
}
}
}
}您需要为以下环境变量提供值：
OPENAI_API_KEY ：用于生成嵌入的 OpenAI API 密钥
QDRANT_URL ：您的 Qdrant 矢量数据库实例的 URL
QDRANT_API_KEY ：用于使用 Qdrant 进行身份验证的 API 密钥
使嵌入可配置，以允许在 OpenAI 嵌入或本地 Ollama 之间进行选择以生成向量
此 MCP 服务器采用 MIT 许可证。这意味着您可以自由使用、修改和分发该软件，但须遵守 MIT 许可证的条款和条件。更多详情，请参阅项目仓库中的 LICENSE 文件。
该项目是qpd-v/mcp-ragdocs的一个分支，最初由 qpd-v 开发。原始项目为本实现提供了基础。
Remove all pending URLs from the documentation processing queue. Use this to reset the queue when you want to start fresh, remove unwanted URLs, or cancel pending processing. This operation is immediate and permanent - URLs will need to be re-added if you want to process them later. Returns the number of URLs that were cleared from the queue.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does so effectively. It discloses critical behavioral traits: the operation is 'immediate and permanent', URLs 'will need to be re-added', and it 'Returns the number of URLs that were cleared'. This covers mutability, permanence, and output format without contradictions.
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?
Perfectly front-loaded with the core action in the first sentence, followed by usage guidance and behavioral details. Every sentence adds value: purpose, when-to-use, permanence warning, and return information. Zero wasted words.
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 0-parameter tool with no annotations or output schema, the description is complete. It explains what the tool does, when to use it, behavioral consequences (permanent, immediate), and what it returns. No additional context is needed given the tool's simplicity.
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, so no parameter documentation is needed. The description appropriately focuses on behavior rather than parameters, maintaining a baseline of 4 since it doesn't need to compensate for any parameter gaps.
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 specific action ('Remove all pending URLs') and resource ('documentation processing queue'), distinguishing it from sibling tools like list_queue (which lists) or run_queue (which processes). It uses precise verbs and identifies the exact scope of operation.
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?
Explicitly states when to use this tool ('to reset the queue when you want to start fresh, remove unwanted URLs, or cancel pending processing') and provides clear alternatives by naming sibling tools like list_queue and run_queue. It gives practical scenarios for application.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extract and analyze all URLs from a given web page. This tool crawls the specified webpage, identifies all hyperlinks, and optionally adds them to the processing queue. Useful for discovering related documentation pages, API references, or building a documentation graph. Handles various URL formats and validates links before extraction.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The complete URL of the webpage to analyze (must include protocol, e.g., https://). The page must be publicly accessible. | |
| add_to_queue | No | If true, automatically add extracted URLs to the processing queue for later indexing. This enables recursive documentation discovery. Use with caution on large sites to avoid excessive queuing. |
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 effectively describes key behaviors: crawling webpages, identifying hyperlinks, optional queue addition with a caution note for large sites, handling various URL formats, and link validation. This covers mutation aspects (queue addition) and operational constraints, though it could mention performance or rate limits more explicitly.
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 appropriately sized and front-loaded, with the core purpose stated first. Each sentence adds value: the first defines the action, the second explains optional queue behavior, the third gives usage context, and the fourth covers technical handling. There is no wasted text, and the structure flows logically from general to specific details.
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 moderate complexity (2 parameters, no output schema, no annotations), the description is largely complete. It covers purpose, usage, behaviors, and parameters adequately. However, it could be more explicit about output (e.g., what the analysis returns) since there is no output schema, and it lacks details on error handling or authentication needs, leaving minor gaps in full contextual understanding.
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 thoroughly. The description adds marginal value by implying the 'url' parameter is for webpage analysis and hinting at the 'add_to_queue' parameter's purpose ('optionally adds them to the processing queue'), but it does not provide additional syntax or format details beyond what the schema specifies. 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 specific action ('extract and analyze all URLs') and resource ('from a given web page'), distinguishing it from sibling tools like clear_queue or search_documentation. It explicitly mentions the tool's scope (crawling, identifying hyperlinks, handling URL formats, validating links), which goes beyond a simple tautology of the name.
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 clear context for when to use this tool ('useful for discovering related documentation pages, API references, or building a documentation graph'), but it does not explicitly state when not to use it or name specific alternatives among sibling tools. The guidance is helpful but lacks explicit exclusions or comparisons to tools like list_sources or run_queue.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all URLs currently waiting in the documentation processing queue. Shows pending documentation sources that will be processed when run_queue is called. Use this to monitor queue status, verify URLs were added correctly, or check processing backlog. Returns URLs in the order they will be processed.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 effectively describes key behaviors: it's a read-only operation (implied by 'list'), returns URLs in processing order, and relates to queue monitoring. However, it doesn't mention potential limitations like rate limits, error conditions, or whether the list is real-time vs. cached.
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 core purpose in the first sentence, followed by usage guidelines and output details. Every sentence adds value without redundancy, making it efficiently structured and appropriately sized for the tool's complexity.
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 (0 parameters, no annotations, no output schema), the description is largely complete. It covers purpose, usage, and output behavior well. A minor gap is the lack of explicit mention of read-only safety or error handling, but for this simple tool, it's sufficient.
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, so no parameter documentation is needed. The description adds value by explaining the output semantics ('Returns URLs in the order they will be processed'), which compensates for the lack of an output schema. Baseline is 4 for 0 parameters, and it exceeds this by providing output context.
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 specific action ('List all URLs') and resource ('documentation processing queue'), distinguishing it from siblings like 'list_sources' (which likely lists different resources) and 'run_queue' (which processes rather than lists). It explicitly defines what the tool does without being tautological.
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 explicit guidance on when to use this tool: 'to monitor queue status, verify URLs were added correctly, or check processing backlog.' It also distinguishes it from 'run_queue' by noting it shows pending sources 'that will be processed when run_queue is called,' offering clear context and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all documentation sources currently stored in the system. Returns a comprehensive list of all indexed documentation including source URLs, titles, and last update times. Use this to understand what documentation is available for searching or to verify if specific sources have been indexed.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 describes the return format (list with URLs, titles, update times) and implies a read-only operation, but lacks details on potential limitations like pagination, rate limits, or error conditions. No contradiction with annotations exists.
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 efficiently structured in two sentences: the first states the action and return value, the second provides usage context. Every sentence adds value without redundancy, and it is appropriately sized for a simple listing 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?
Given the tool's low complexity (0 parameters, no annotations, no output schema), the description is reasonably complete—it explains what the tool does, what it returns, and when to use it. However, it could be more comprehensive by addressing potential behavioral aspects like performance or data freshness.
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 0 parameters with 100% schema description coverage, so the schema already fully documents the inputs. The description appropriately does not add parameter details, maintaining focus on the tool's purpose and output. Baseline for 0 parameters 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 the specific verb ('List') and resource ('all documentation sources currently stored in the system'), distinguishing it from siblings like 'search_documentation' (searching) and 'remove_documentation' (deleting). It explicitly mentions what information is returned (source URLs, titles, last update times).
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 clear context on when to use this tool ('to understand what documentation is available for searching or to verify if specific sources have been indexed'), but does not explicitly state when not to use it or name specific alternatives among siblings (e.g., 'search_documentation' for querying content).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove specific documentation sources from the system by their URLs. Use this tool to clean up outdated documentation, remove incorrect sources, or manage the documentation collection. The removal is permanent and will affect future search results. Supports removing multiple URLs in a single operation.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | Array of URLs to remove from the database |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well: it discloses permanence ('removal is permanent'), impact ('will affect future search results'), and batch capability ('supports removing multiple URLs'). However, it lacks details on error handling or permission requirements.
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?
Three sentences with zero waste: first states purpose, second gives usage context, third covers behavioral traits. Each sentence earns its place, and key information is front-loaded.
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 destructive tool with no annotations or output schema, the description is reasonably complete—covering purpose, usage, and key behavioral warnings. However, it could mention response format or error cases for full completeness.
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 the 'urls' parameter fully. The description adds minimal value beyond implying batch operations, matching the baseline score when schema does 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 ('Remove') and resource ('specific documentation sources by their URLs'), distinguishing it from siblings like 'list_sources' (read-only) or 'search_documentation' (query-focused). It specifies the action is targeted removal rather than bulk clearing.
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 clear context for when to use this tool ('clean up outdated documentation, remove incorrect sources, or manage the documentation collection'), but does not explicitly mention when NOT to use it or name specific alternatives among siblings (e.g., 'clear_queue' might be for different cleanup).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Process and index all URLs currently in the documentation queue. Each URL is processed sequentially, with proper error handling and retry logic. Progress updates are provided as processing occurs. Use this after adding new URLs to ensure all documentation is indexed and searchable. Long-running operations will process until the queue is empty or an unrecoverable error occurs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 effectively describes key behavioral traits: sequential processing, error handling with retry logic, progress updates, and long-running nature until queue empty or unrecoverable error. It doesn't mention side effects like resource consumption or rate limits, but covers core operational behavior well.
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 efficiently structured with three sentences that each serve a distinct purpose: stating the core operation, describing behavioral characteristics, and providing usage guidelines. It's front-loaded with the main action and contains no redundant or unnecessary information.
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 (long-running queue processing with error handling) and lack of annotations/output schema, the description provides good coverage of what the tool does and when to use it. It could benefit from mentioning what 'indexed and searchable' means or potential side effects, but it's sufficiently complete for an agent to understand the tool's role.
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, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, and instead focuses on the tool's operational context and behavior, which adds value beyond the empty schema.
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's purpose with specific verbs ('process and index') and resources ('URLs currently in the documentation queue'), distinguishing it from siblings like clear_queue, extract_urls, and list_queue. It explicitly mentions the target resource (URLs in queue) and the outcome (making documentation indexed and searchable).
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 explicit guidance on when to use this tool ('Use this after adding new URLs to ensure all documentation is indexed and searchable'), distinguishing it from alternatives like list_queue (for viewing) or clear_queue (for removal). It clearly states the intended context and timing for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search through stored documentation using natural language queries. Use this tool to find relevant information across all stored documentation sources. Returns matching excerpts with context, ranked by relevance. Useful for finding specific information, code examples, or related documentation.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The text to search for in the documentation. Can be a natural language query, specific terms, or code snippets. | |
| limit | No | Maximum number of results to return (1-20). Higher limits provide more comprehensive results but may take longer to process. Default is 5. |
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 describes key behaviors like returning 'matching excerpts with context, ranked by relevance' and mentions performance implications ('higher limits may take longer'), but lacks details on permissions, rate limits, or error handling that would be important for a search 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 efficiently structured in three sentences: purpose statement, usage guidance, and behavioral details. Every sentence adds value without redundancy, and it's appropriately front-loaded with the core functionality.
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 search tool with 2 parameters, 100% schema coverage, and no output schema, the description provides adequate context about what the tool does and returns, but could be more complete by explaining the format of returned excerpts or clarifying what 'stored documentation sources' encompasses relative to sibling tools.
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 thoroughly. The description adds marginal value by reinforcing that queries can be 'natural language' and mentioning the relevance ranking, but doesn't provide additional semantic context beyond what's in the parameter descriptions.
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's purpose with specific verbs ('search through stored documentation') and resources ('documentation sources'), distinguishing it from siblings like 'remove_documentation' or 'list_sources' by focusing on search functionality rather than management 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 clear context for when to use this tool ('to find relevant information across all stored documentation sources') and mentions specific use cases ('finding specific information, code examples, or related documentation'), but does not explicitly state when not to use it or name alternatives among sibling 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.
clear_queueextract_urlslist_queuelist_sourcesremove_documentationrun_queuesearch_documentationScored across 7 tools
Each tool has a clearly distinct purpose with no overlap: clear_queue manages queue state, extract_urls discovers links, list_queue and list_sources provide status views, remove_documentation deletes sources, run_queue processes the queue, and search_documentation queries content. The descriptions reinforce these boundaries, making misselection unlikely.
All tool names follow a consistent verb_noun pattern using snake_case, such as clear_queue, extract_urls, list_queue, list_sources, remove_documentation, run_queue, and search_documentation. This uniformity makes the set predictable and easy for agents to navigate.
With 7 tools, the server is well-scoped for its RAG documentation purpose, covering queue management, source discovery, processing, and search. Each tool earns its place without bloat, aligning with typical server sizes of 3-15 tools for focused functionality.
The tool set covers core RAG documentation workflows including queue management, source extraction, indexing, and search, with no dead ends. A minor gap exists in lacking tools for updating or modifying existing documentation sources, but agents can work around this by re-adding URLs.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Versioned documentation registry and semantic search for AI tools and coding assistants.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Tailor Platform for AI assistants: search, list and read the platform documentation.