simple-qqdocs-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@simple-qqdocs-mcpinput cell B2 with 'Revenue 2025'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
simple-qqdocs-mcp
配合 Playwright MCP 操作腾讯文档表格(.excel-container>canvas)的简易 MCP 服务。
前置条件
用 Playwright MCP 打开
docs.qq.com/sheet表格页浏览器开启 CDP,默认
http://127.0.0.1:9222若遇代理报错,在 MCP 配置中设置
ALL_PROXY=""
Related MCP server: ExcelMCPAdvanced
安装与配置
pnpm install在 Cursor / MCP 配置中注册(路径按实际修改):
{
"mcpServers": {
"simple-qqdocs": {
"command": "node",
"args": ["d:/1024/llm/simple-qqdocs-mcp/src/index.js"],
"env": {
"CDP_ENDPOINT": "http://127.0.0.1:9222",
"ALL_PROXY": ""
}
}
}
}使用流程
Playwright 打开腾讯文档表格
调用
refresh_grid_boundaries或直接使用默认工具(会自动重新识别网格)页面滚动/缩放后,优先用非
quick_*工具,或先refresh_grid_boundaries
工具选用
场景 | 推荐 |
常规操作 |
|
用户明确要求 quick/快速/缓存 |
|
Tools
坐标与操作
Tool | 说明 |
| 识别并刷新列标 ABCD、行标 1234 的边界缓存 |
| 默认 获取单元格边界(每次重新识别) |
| 用缓存快速获取边界 |
| 默认 识别并点击单元格 |
| 用缓存快速点击 |
| 默认 点击单元格并输入文本 |
| 用缓存快速输入 |
单元格引用:A1(单格)、A1:C2 或 A1C2(范围)
返回格式:
单格
A1→bounds: [[x1, x2], [y1, y2]]范围
A1:C2→bounds: [[x1, x2, x3, x4], [y1, y2, y3]]
基础 / 调试
Tool | 说明 |
| 获取 canvas 截图(base64 PNG) |
| 识别行标/列标区域与边界 |
| 识别单元格文字,返回 |
环境变量
变量 | 默认 | 说明 |
|
| 浏览器 CDP 地址 |
Available Tools
10 toolsclick_cellA
【默认】识别单元格位置并点击(每次重新识别网格)
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. It discloses the re-identification behavior but omits details like error handling, prerequisite grid state, or click side effects. Minimal but adequate for a simple click action.
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?
A single short sentence that contains all essential information—action and key behavioral trait. No filler, front-loaded, and efficient.
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 simple one-parameter tool and no output schema, the description covers the core behavior but lacks context about prerequisites, error scenarios, or comparison with click alternatives. Adequate but not full.
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 parameter 'ref' has a minimal schema description ('cell reference'), and the tool description adds no additional meaning about its format or allowed values. Schema coverage is 100% but the description does not enhance understanding.
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 identifies a cell position and clicks it, and specifies it re-identifies the grid each time, distinguishing it from siblings like quick_click_cell. This is a specific verb-resource pair with a behavioral nuance.
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 when grid re-identification is needed (vs. siblings like quick_click_cell), but it does not explicitly state when to use or avoid this tool. No direct when/when-not guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
detect_gridB
基础:识别行标/列标区域与 ABCD、1234 边界
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose all behavioral traits. It lacks details on side effects (likely none), output format, idempotency, or performance considerations. The description merely states what it detects, not much about how it 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?
Extremely concise at one short phrase, but it lacks sentence structure. While efficient, it may be under-specified for an agent; a bit more context could improve usability without adding much length.
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?
The tool has no parameters, no output schema, and no annotations. The description only says it identifies boundaries but doesn't explain the return value (e.g., coordinates, boolean, or structured data). For a detection tool, this missing output info leaves the agent guessing about how to use the result.
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?
No parameters exist, so baseline is 4. The description clarifies the tool's purpose beyond the empty schema, adding meaning by specifying detection targets (boundaries and headers).
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 explicitly states it identifies row/column header areas and boundaries (ABCD, 1234). The verb 'detect' and resource 'grid boundaries' are specific. It distinguishes from sibling tools like click_cell or input_cell, which operate on cells rather than detecting the grid structure.
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 on when to use this tool versus alternatives. The term '基础' (basic) hints it's a prerequisite step, but there is no explicit context, exclusions, or references to related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_canvas_snapshotA
获取 .excel-container>canvas 截图(base64 PNG)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the output format but does not disclose whether the tool is read-only, has side effects, or requires prior conditions.
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?
One concise sentence front-loads the core purpose and output format with zero waste.
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 zero parameters and no output schema, the description adequately defines the tool's purpose. It could briefly mention the canvas context or that it captures the current grid state, but it's sufficient for a simple read operation.
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 zero parameters and 100% coverage trivially. The description adds no parameter info (none needed), and the baseline for 0 params 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 action (get a screenshot of .excel-container>canvas) and the output format (base64 PNG). It uniquely identifies the resource and differs from sibling tools that interact with cells.
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 over siblings or any prerequisites. The context of use (after grid rendering, etc.) is implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_cell_boundsA
【默认】获取单元格边界(每次重新识别网格)。单格 A1 返回 [[x1,x2],[y1,y2]];范围 A1C2 或 A1:C2 返回 [[x1,x2,...],[y1,y2,...]]
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用,如 A1、A1:C2 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly states that the grid is re-identified each call, and gives exact return formats for different input types, which is valuable for the agent.
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 short, front-loaded with key behavior, and every sentence provides essential information. No waste.
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 simple tool with one parameter and no output schema, the description is complete. It explains input format and output format with examples, covering all necessary 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?
Schema coverage is 100% with a clear description of the 'ref' parameter. The tool description adds no additional meaning beyond the schema, so baseline score of 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?
The description uses specific verb '获取' (get) and resource '单元格边界' (cell bounds), and distinguishes return formats for single cell vs range. It is clear and distinct from siblings like quick_get_cell_bounds.
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 mentions '每次重新识别网格' (re-identify grid each time), implying a trade-off between accuracy and performance. This hints at when to use this vs quick versions, but does not explicitly state when not to use or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
input_cellA
【默认】点击单元格并输入文本(每次重新识别网格)
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用 | |
| text | Yes | 要输入的文本 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the burden of behavioral disclosure. It explicitly states the key trait of re-identifying the grid each time, which is a critical behavioral detail for an AI agent. It does not mention other behaviors like return value or error handling, but for a simple input action, this is adequate.
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 concise sentence that front-loads the action and key behavioral detail. Every word earns its place, with zero waste.
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 has 2 parameters, no output schema, no annotations, and sibling tools exist, the description is mostly complete. It covers the action and a critical behavioral trait, though it could briefly mention what the tool does not return (e.g., no cell content).
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 descriptions for both 'ref' and 'text' parameters, so the baseline is 3. The description adds no additional semantic context beyond what the schema already provides.
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 it clicks a cell and inputs text, with the specific behavioral trait of re-identifying the grid each time. This distinguishes it from sibling tools like 'click_cell' (clicks only) and 'quick_input_cell' (likely skips re-identification). The verb 'input' matches the tool 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?
Usage context is implied through the re-identification behavior, suggesting this tool is appropriate when grid re-detection is needed. However, there is no explicit guidance on when to use this versus alternatives like 'quick_input_cell' or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
quick_click_cellA
【仅用户明确要求 quick/快速时】使用缓存坐标点击单元格,不重新识别网格
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the tool uses cached coordinates and does not re-identify the grid, indicating it may use stale data. However, it fails to mention what happens if the cache is invalid or outdated, or any potential errors.
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 very concise with one sentence and no fluff. It front-loads the usage condition in brackets. It is appropriately sized for the tool's 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?
The description is fairly complete for a quick variant tool with one parameter. It explains when to use and what it does differently. However, it lacks details on failure modes (e.g., cache miss) and does not describe return values, which are absent from output schema.
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% (one parameter with description). The description adds context that the ref refers to a cell previously identified, but does not provide additional format or constraints beyond 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?
The description clearly states the tool clicks a cell using cached coordinates and is intended for when the user explicitly requests quick/快速. It distinguishes from the sibling 'click_cell' by noting it does not re-identify the grid. However, it is brief and could elaborate on what 'cached coordinates' implies.
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 explicitly specifies when to use this tool: only when the user explicitly requests quick/快速. It does not explicitly mention when not to use it or name alternatives, but the sibling tool 'click_cell' is implied as the alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
quick_get_cell_boundsA
【仅用户明确要求 quick/快速时】使用缓存坐标获取单元格边界,不重新识别网格
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用,如 A1、A1:C2 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It states the core behavioral trait: uses cached coordinates and does not re-identify grid. However, it could mention potential staleness or error conditions if cache is missing.
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 very short and to the point, but written in mixed Chinese/English without structured formatting. Every word earns its place, yet it could be slightly more structured.
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 simple tool with one parameter and no output schema, the description covers the purpose, usage condition, and behavior. It does not mention return format or error cases, but given tool simplicity, it is largely 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% with parameter 'ref' already described as cell reference. The description does not add additional meaning beyond the schema, meeting baseline but not exceeding.
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 it uses cached coordinates to get cell bounds without re-identifying the grid, and the condition for use (only when user requests quick) distinguishes it from the sibling get_cell_bounds.
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 explicitly provides a usage condition: '【仅用户明确要求 quick/快速时】' (only when user explicitly requests quick/fast), telling when to use this tool over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
quick_input_cellA
【仅用户明确要求 quick/快速时】使用缓存坐标点击并输入,不重新识别网格
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用 | |
| text | Yes | 要输入的文本 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It discloses key behaviors: using cached coordinates (implying potential staleness) and not re-identifying the grid. This informs the user of trade-offs (speed vs. accuracy). However, it does not mention what happens if cached coordinates are invalid or other mutation 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 extremely concise: a single sentence that includes a precondition, the core action, and a clarifying negative condition. Every word serves a purpose, with no 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?
For a tool with no output schema and two simple parameters, the description is adequate but not fully complete. It does not mention return values or error conditions (e.g., what happens if coordinates are stale). It could be slightly more informative about the tool's boundaries.
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 both parameters having descriptions ('单元格引用' and '要输入的文本'). The description adds no extra detail beyond the schema, so it meets the baseline. No additional context on format or constraints is provided.
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: using cached coordinates to click and input without re-identifying the grid. It specifies the exact scenario (when user explicitly requests quick/fast) and distinguishes itself from siblings like 'input_cell' (which presumably re-identifies the grid) and 'quick_click_cell' (which only clicks).
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 explicitly states when to use the tool: only when the user requests 'quick' or 'fast'. This is strong guidance. However, it does not explicitly name the alternative tool (e.g., 'input_cell') for normal usage, though the context of siblings implies it. The guidance is clear but could be more explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
recognize_cell_textB
基础:识别单元格文字,返回 {text,bcolor,fcolor}(背景/反色不敏感)
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes | 单元格引用,如 A1 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that background/reverse color is insensitive, a useful behavioral trait. But no annotations exist, and description does not cover empty cell behavior, error cases, or performance.
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?
Single sentence with essential info, front-loaded. Could be slightly improved with structured format but efficient overall.
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?
Adequate for a basic recognition tool with one parameter. Lacks details on return behavior for different cell types or error states, but output schema is absent so description is somewhat 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 ref description. Description adds return format but no additional parameter meaning beyond schema. Baseline 3 applies.
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 recognizes cell text and returns text, bcolor, fcolor. It distinguishes itself from sibling tools like click_cell and input_cell that perform different actions.
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 on when to use this tool versus alternatives like get_canvas_snapshot or quick_get_cell_bounds. Lacks explicit context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
refresh_grid_boundariesB
识别并刷新表格 canvas 坐标边界缓存(列标 ABCD、行标 1234)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states that it refreshes a cache, but omits side effects, whether it is destructive, or any required permissions. The behavioral disclosure is minimal.
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 sentence, concise and front-loaded. However, it could include additional context without becoming verbose, so it is not maximally efficient.
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 parameters, no output schema, and no annotations, the description is incomplete. It lacks information about when to call the tool (e.g., after grid changes), preconditions, or expected outcomes. The agent may not know the proper usage 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 tool has zero parameters, and schema description coverage is 100%. According to guidance, baseline is 4. The description adds context about what the tool does, which is sufficient since no parameter details are needed.
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 uses specific verbs ('识别并刷新' meaning 'identify and refresh') and clearly states the resource ('表格 canvas 坐标边界缓存' meaning 'grid canvas coordinate boundary cache') with details about column and row labels. This clearly distinguishes it from sibling tools that operate on cells.
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 does not mention context, prerequisites, or when it is appropriate to refresh the cache.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Each tool has a clearly distinct purpose, with base tools and quick variants explicitly conditioned on user request. The descriptions precisely differentiate when to use each, eliminating ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case, with a uniform 'quick_' prefix for cached variants. No mixing of conventions.
10 tools is well-scoped for interacting with a spreadsheet grid, covering detection, clicking, input, bounds, text recognition, and snapshot. Not too few nor too many.
Covers core cell operations (click, input, read text, grid detection) but lacks tools for range selection, formatting, or formula editing. Minor gap, but the set is functional for basic tasks.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Live data grids for AI agents. Push structured data; humans review, agents read back via MCP.
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
An agent-first office suite Claude & ChatGPT read and write over one MCP URL.
Headless browser primitives for AI agents when sites need real JS rendering.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to interact with Google Sheets for reading, writing, and managing spreadsheets through a set of MCP tools.MIT
- FlicenseNot gradedqualityDmaintenanceFast, multi-sheet Excel retrieval and writing via MCP, supporting efficient data access with patch-based navigation and formula support.
- AlicenseNot gradedqualityDmaintenanceMCP server enabling AI agents to read, write, and manage Google Sheets, including sheet manipulation, row/column operations, dropdowns, checkboxes, and conditional formatting.14MIT
- AlicenseAqualityDmaintenanceEnables to read, write, format cells, create charts, use formulas, and manage Google Sheets spreadsheets directly from Claude, Cursor, or any MCP-compatible client.2717MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thetime50/simple-qqdocs-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server