stagenth · 文档解析
Server Details
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4/5 across 4 of 4 tools scored.
Each tool targets a distinct aspect of document processing: parsing to Markdown, chunking for RAG, extracting images, and extracting tables. No overlap is evident.
All tools share a 'doc_' prefix and use snake_case, but the second part mixes verbs and nouns (chunk, images, parse, tables). Mostly consistent with a minor deviation.
Four tools provide a focused and complete set for document parsing without being excessive or insufficient.
Covers core document operations: parsing, chunking, image extraction, and table extraction. Missing OCR for scanned documents and metadata extraction, but these are minor gaps.
Available Tools
4 toolsdoc_chunkAInspect
把文档切成适合 RAG / 向量嵌入的语义块（按标题层级切，超长块按段落细分）。
返回 [{index, heading, text, chars}]，喂检索/嵌入无需再自己写切块逻辑。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 已上传到文件中转站的文档 ID（与 data_base64 二选一） | |
| filename | No | 文件名带扩展名；base64 输入时必填以判类型 | |
| max_chars | No | 每块最大字符数（200-8000） | |
| page_range | No | 页码范围，如 3-10，空=全部（PDF/PPT 有效） | |
| data_base64 | No | 文档内容 base64（与 file_id 二选一） |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must bear the load. It discloses the return format (list of objects with index, heading, text, chars) and splitting strategy. It does not mention destructive actions, auth, or rate limits, but the tool is read-only and non-destructive, so no contradiction.
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 extremely concise with two sentences plus a bullet point. It front-loads the purpose and provides essential details without redundancy.
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 output schema, the description explicitly states the return format, which is critical. It covers splitting logic and edges (超长块按段落细分). A brief mention of the splitting algorithm's limitations or prerequisites would improve 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% with each parameter explained. The tool description adds overall context (splitting logic, return format) but does not significantly enhance parameter semantics beyond what is in the 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: chunk documents into semantic blocks for RAG/vector embedding, using heading hierarchy and paragraph splitting. It distinguishes itself from sibling tools like doc_images, doc_parse, and doc_tables.
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 implies usage for preparing documents for retrieval/embedding (避免了自行编写切块逻辑). It does not explicitly state when not to use or compare with siblings, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
doc_imagesAInspect
抽取文档内嵌的图片（PDF / .docx / .pptx），打包 ZIP 落文件中转站并返下载 URL。
过滤 <1KB 的图标噪声；多模态 AI 可配合 doc_parse 的文本一起理解图文文档。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 已上传到文件中转站的文档 ID（与 data_base64 二选一） | |
| filename | No | 文件名带扩展名；base64 输入时必填以判类型 | |
| max_images | No | 最多抽取图片数（1-100） | |
| data_base64 | No | 文档内容 base64（与 file_id 二选一） |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It mentions filtering images <1KB as noise and packaging as ZIP, but does not address potential destructive actions, permissions, or side effects.
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 concise with two sentences, front-loading the main purpose. It could be slightly more structured, but it is efficient and contains no unnecessary 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?
Given no output schema, the description adequately covers output (ZIP URL) and usage context with doc_parse. It is complete enough for a straightforward extraction tool.
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 coverage is 100%, so parameters are already documented. The description adds limited value beyond schema, mainly mentioning noise filtering and multimodal use, but does not provide detailed parameter-specific guidance.
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 extracts embedded images from documents (PDF, .docx, .pptx), packages them as ZIP, and returns a download URL. It distinguishes itself from siblings like doc_tables and doc_parse by focusing on images.
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 suggests using this tool with doc_parse for multimodal AI understanding, providing context. However, it lacks explicit instructions on when not to use it or alternatives for other tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
doc_parseAInspect
把 PDF / Word(.docx) / PPT(.pptx) / HTML / 纯文本 解析成干净 Markdown + 结构化（按实际解析页数计费，每页 1 credit）。
纯解析 + 格式转换、不生成任何 AI 内容；扫描件 OCR 暂未支持。
支持 page_range 只解析指定页码段（只按解析的页数扣费）。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 已上传到文件中转站的文档 ID（与 data_base64 二选一） | |
| filename | No | 文件名带扩展名；base64 输入时必填以判类型（.pdf/.docx/.pptx） | |
| max_pages | No | 最多解析页数，0=全部 | |
| page_range | No | 页码范围，如 3-10 或 5，空=全部（PDF/PPT 有效） | |
| data_base64 | No | 文档内容 base64（与 file_id 二选一） |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description partially covers behavior: pricing per page, no OCR, no AI generation, and page range support. It does not mention authorization needs, rate limits, or whether the operation is destructive, but the core behavior is clear.
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 concise with two paragraphs. Key information is front-loaded: purpose, pricing, supported formats. No superfluous text; every sentence provides value.
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 5 parameters with full schema coverage and no output schema, the description covers inputs, pricing, limitations, and page range. Could be improved with more detail on output format, but overall adequate.
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 coverage is 100%, so baseline is 3. The description adds context beyond schema: explains mutual exclusivity of file_id and data_base64, necessity of filename for base64, and format for page_range, adding value for correct parameter usage.
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 function: parsing PDF, Word, PPT, HTML, and plain text into clean Markdown and structured output. It differentiates from siblings (doc_chunk, doc_images, doc_tables) by focusing on full document conversion.
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 specifies it is for pure parsing and format conversion without AI content generation, and notes that OCR for scanned documents is not supported. However, it does not explicitly state when to use alternative sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
doc_tablesAInspect
抽取文档中的表格（PDF / .docx / .pptx），转成 headers+rows 的 JSON 可直接计算。
与 doc_parse 的区别：表格不再压平成 markdown 竖线文本，而是结构化行列，
AI 可直接算合计/对比；PDF 用版面识别找表格。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 已上传到文件中转站的文档 ID（与 data_base64 二选一） | |
| filename | No | 文件名带扩展名；base64 输入时必填以判类型 | |
| max_pages | No | PDF 最多扫描页数（1-100） | |
| data_base64 | No | 文档内容 base64（与 file_id 二选一） |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that PDF uses layout recognition for tables, but does not mention error handling, performance limits, or what happens when no tables are found. Adds some value beyond schema but not comprehensive.
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?
Description is extremely concise: two sentences that front-load the main purpose and key differentiator. No filler or redundant 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?
For a table extraction tool with no output schema, the description adequately explains the output format (headers+rows JSON) and the distinguishing feature from doc_parse. It could mention fallback behavior for non-table content but is largely complete.
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 coverage is 100% with all four parameters described. The description does not add significant new information about parameters; it only restates the mutual exclusivity of file_id and data_base64, which is already in the schema. Baseline 3 is appropriate.
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?
Description clearly states the tool extracts tables from documents (PDF, .docx, .pptx) and converts them into structured JSON with headers and rows. It explicitly distinguishes from sibling doc_parse by noting that tables are not flattened into markdown.
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?
Description provides explicit comparison with doc_parse, explaining when to use this tool (for structured table extraction) versus doc_parse (which flattens tables). However, it does not mention exclusions for other siblings like doc_chunk or doc_images.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!