Ghosthand

by kumard3

Overview Schema Related Servers Score Discussions

TypeScript

Local

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.2.9
Disambiguation5/5
Each tool has a clearly distinct purpose: clicking methods separate from finding, typing from pressing keys, scrolling from navigation, etc. Even similar tools like click and click_text are differentiated by whether a ref or text is used.
Naming Consistency3/5
Naming conventions are mixed: single verbs (click, drag, hover) coexist with underscore-separated verb_noun (click_text, press_key) and verb_preposition (move_to, wait_for). While all lowercase, the lack of a uniform pattern may cause slight confusion.
Tool Count5/5
15 tools is well-scoped for browser automation, covering navigation, interaction, page reading, waiting, and screenshots without being bloated or sparse.
Completeness4/5
Core browser automation features are present (click, type, navigate, scroll, read page, wait). Minor gaps like tab management, cookies, or back/forward navigation are absent, but the set handles common workflows effectively.
Average 3.8/5 across 15 of 15 tools scored. Lowest: 2.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 33 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
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 only mentions 'Human-like' movement and events, but omits details on stealth behavior, coordinate vs element precedence, or any 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose. It is efficient but could be slightly more compact. The examples add value without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not detail parameter usage, return values, or error conditions, leaving significant gaps for an agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description should explain all 4 parameters. It only vaguely refers to 'element or coordinates', leaving x, y, ref, and stealth completely unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('move the cursor') and the target ('element or coordinates'), and mentions the hover events fired. This distinguishes it from sibling tools like 'move_to' which may not fire events, though not explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lists typical use cases (dropdowns, tooltips, menus) but does not specify when not to use this tool or compare it to alternatives like 'move_to' or 'click'. Usage context is implied but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description mentions 'eased human steps' suggesting smooth scrolling, but fails to explain the effect of the 'stealth' parameter or behavior when scrolling exceeds page bounds. Without annotations, the description carries the full burden and is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no superfluous words. Every part adds value, making it highly efficient for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a basic scroll tool with three parameters and no output schema, the description is adequate but has gaps: it does not explain the 'stealth' parameter or boundary behavior. Sibling tools like drag or click might be alternatives, but no comparison is given.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description should document parameters. It only partially explains dx and dy (pixels) but omits the 'stealth' parameter entirely. Units are implied but no details on sign conventions or limits.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool scrolls the page by dy and optional dx pixels, with eased human steps. This distinguishes it from siblings like navigate (page navigation) or drag (scrolling by dragging). However, it does not explicitly mention that it scrolls within the current viewport.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use scroll versus alternatives like drag or clicking on a scrollbar. The description does not mention any prerequisites or context for effective use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 action without disclosing behavior like page load waiting, error handling, or URL scheme support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words, perfectly front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the description is incomplete. It lacks information about expected behavior, return values, and side effects, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description merely restates 'a URL' without adding meaning beyond the schema's type string. No format, example, or constraint is given.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses verb 'navigate' and resource 'active tab' clearly. It distinguishes from siblings like get_url (which retrieves URL) and click (which interacts with elements).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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, nor any prerequisites or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses human key timing and stealth driver usage, but omits details like exact timing behavior, error handling, return values, or side effects, leaving significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no extra words. Main purpose is front-loaded, and all key points are covered without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 3-param tool with no annotations, no output schema, and no param descriptions in schema, the description is too brief. Missing details on input constraints, stealth behavior nuances, error conditions, and return values make it incomplete for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must explain parameters. It explains ref (focus/click first), text (implied as content to type), and stealth (debugger driver). This adds meaning beyond the bare schema, though more detail would help.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Type text with human key timing,' clearly indicating the verb (type) and resource (text). It distinguishes from sibling tools like press_key and click by mentioning human-like timing and focus behavior.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs. alternatives like press_key or click_text. The note about ref and stealth provides context but no comparative direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description adds value by mentioning 'human-like move' and 'stealth (trusted-event) mode', but lacks details on default behavior, error handling, or interaction between x/y and ref.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence packs key information (action, target options, variations) without fluff; slightly dense but effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Moderate complexity (6 params, no output schema) not fully addressed; missing prerequisites, order of operations, and result description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description explains most parameters (button, double, stealth, ref, x/y) but is vague on how x/y and ref relate and lacks detail on all parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a human-like move and click on an element or coordinates, and distinguishes from sibling tools like hover, move_to, and click_text by mentioning button options, double-click, and stealth mode.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like click_text or hover; no context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries the burden. It discloses it returns refs, roles, names, rectangles, and text, and implies a read-only operation. However, it does not mention response format, size limits, or rate limits, leaving gaps in behavioral understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that front-loads the main action and key outputs. Every word adds value, no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description must compensate. It lists returned data (ref, role, name, rectangle, text) but omits structure, ordering, or parameter effects. Adequate but not comprehensive for a tool with no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description does not explain either parameter (includeText, maxElements). The hint 'plus visible text' vaguely relates to includeText but is insufficient. The description adds no value beyond the schema's type definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it reads the current page and lists specific outputs (interactive elements with ref handles, roles/names, rectangles, visible text). It also implies its role as a prerequisite for actions like clicking/typing, distinguishing it from sibling tools that perform actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Call before clicking or typing by ref', providing clear when-to-use guidance. It lacks explicit when-not-to-use or comparison with other read tools like find or status, but the context is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It simply states the return value does not disclose side effects, permissions needed, or any edge cases. However, as a read-only operation with no parameters, the transparency 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, precise sentence that front-loads the key purpose. Every word earns its place with no redundancy or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
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 is nearly complete. It could optionally specify whether the URL includes protocol, query strings, or fragment, but this is minor. Overall, it sufficiently informs the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100% by default. The description does not add anything beyond the schema, but the baseline score of 3 is elevated to 4 because there are no parameters to document.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the active tab's current URL, using a specific verb and resource. It distinguishes itself from sibling tools like click, navigate, and read_page, which 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.
Usage Guidelines2/5
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 read_page or navigate. The description does not mention prerequisites, limitations, or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It discloses supported conditions and default timeout, but does not explain behavior on timeout (e.g., error or return value), whether the function blocks, or its return type. This leaves some uncertainty for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the purpose and conditions. Every sentence adds value without redundancy. It is 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.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 4 parameters, no output schema, and no annotations, the description is somewhat complete: it covers the main conditions and use case. However, missing details on return value, error handling, and parameter interactions leave gaps for accurate usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, and the description explains 'ref' (element), 'condition', and 'timeoutMs' but not 'text' explicitly. It does not clarify the relationship between 'ref' and 'text' (mutually exclusive or combinable), nor what happens if both are provided. This ambiguity hinders correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool waits for an element or text condition, with specific verb 'Wait' and resources (element, text). It distinguishes from sibling tools like click, find, etc., by focusing on waiting for conditions rather than performing actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states 'Use in testing and automation flows for resilience on dynamic sites,' providing clear context for when to use it. However, it does not explicitly exclude scenarios or mention alternatives among the listed sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries full burden. Discloses 'human-like drag', 'realistic path engine', and 'holding mouse button', giving insight into behavior. Could mention whether it waits for completion or supports cancellation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with main purpose, then behavioral detail. No redundant or unnecessary words. Efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, 0% schema coverage, no output schema, and no annotations, the description is too brief. Does not cover parameter roles or output format. Needs more detail for a complex interaction tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and description does not explain any of the 8 parameters. Parameter names (toX, fromY, button, stealth, etc.) are somewhat self-explanatory, but lack of clarity on 'stealth' and 'toRef' vs coordinates reduces utility.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'drag' with specific resources (elements/refs/coords) and provides examples (sliders, reordering, canvas drawing). Distinguishes from sibling tools like click, move_to, hover.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context with examples (e.g. sliders, reordering, canvas drawing) implicitly guiding when to use. Lacks explicit when-not-to-use or alternatives, but context is sufficient for typical choices.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses 'human-like path' and stealth mode behavior via debugger driver, but lacks details on implications like triggering hover effects or cursor path specifics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences front-load the core purpose and add a key behavioral detail. No redundant information; every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description covers main use cases and common parameters. Missing details on coordinate system origin and path behavior, but sufficient for basic operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, the description adds meaning for all parameters: ref from read_page, x/y as absolute viewport, and stealth as trusted events. However, it does not specify coordinate origin or ref format.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool moves the cursor to either an element reference or absolute viewport coordinates, and explicitly states it does not click. This distinguishes it from sibling tools like click and hover.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates when to use the tool (move cursor without clicking) but does not provide explicit guidance on when not to use it or mention alternatives beyond stating it does not click.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behaviors: re-reads page if element missing, nth picks later match, stealth delivers trusted events, double double-clicks. Lacks info on failure handling but overall transparent given no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with front-loaded purpose, each sentence adding value with no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 4 parameters and no output schema, description covers re-reading, event trust, and matching variants. Lacks details on edge cases but sufficient for typical usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds meaning for nth, stealth, and double parameters, but text parameter is obvious and parameter types not described. With 0% schema coverage, description partially compensates but could be more comprehensive.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it combines identification and interaction in one step by finding an element matching text/label and clicking it, distinguishing it from siblings like click or find.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implicitly clear that it is for text-based identification and clicking, but lacks explicit when-to-use vs. alternatives like click or hover.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations present, so description carries full burden. It describes what is returned but does not explicitly state it is read-only or non-destructive. Behavioral traits are implied but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first defines output, second gives usage context. No fluff, every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description covers return fields and use cases thoroughly. Minor gap: exact data types not specified, but sufficient for the task.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so baseline is 3. Description adds context about return values but not strictly about parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it returns MCP server status, driver, bridge connection, and active tab URL. It clearly distinguishes from sibling tools like click or navigate which are action-oriented.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit use cases: health checks, long-running tests, CI workflows, agent monitoring. No ambiguity about when to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses shadow-DOM awareness, return data (ranked matches with ref, role, rect). It implies a read-only operation by its nature. However, it does not explicitly state it has no side effects, which would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: first describes functionality and output, second provides usage guidance and alternatives. It is front-loaded, concise, and every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description covers return value well. Parameters are partially explained. Sibling tool context is provided via click_text. The description could be more complete by mentioning maxResults, but overall it is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains that the 'text' parameter matches visible text or accessible name, adding meaning. However, it does not explain 'maxResults' at all, leaving a gap for that parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool locates on-screen elements by visible text or accessible name, is shadow-DOM aware, and returns ranked matches with ref, role, and rect. It distinguishes from siblings like click_text by noting that click_text does the find and click in one step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly tells when to use: 'when you don't already have a ref.' It provides alternatives: 'use click_text to do it in one step.' It also suggests subsequent actions: 'click/move_to/hover by [ref].' This gives 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.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the stealth parameter's effect (trusted key event via debugger driver) and lists supported keys. It does not detail side effects, but for a key press action this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no redundant information. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple action with 2 parameters and no output schema, the description is fairly complete. It covers key, stealth, and use cases. Minor omissions like behavior for unsupported keys or return value do not significantly hinder an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, so the description must compensate. It adds significant meaning by listing allowed values for key and explaining stealth's effect. However, it does not specify exact format (e.g., case sensitivity) or all possible values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it presses a single key on the focused element and lists supported keys (Enter, Escape, Tab, etc.) and common use cases. This distinguishes it from sibling tools like click and type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly mentions when to use it (submit, dismiss dialogs, tab between fields). It does not list alternatives, but the context from sibling tool names implies other tools for other actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description fully discloses key behavior: 1:1 pixel-to-coordinate scaling and independence from DOM, enabling informed agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with critical information (scaling, usage context), every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, description covers all essential aspects for a simple tool with one optional parameter. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Single parameter (format) has enum in schema; description does not elaborate on it. Schema coverage is 0%, but enum values are self-explanatory. Minimal added value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description explicitly states the tool captures the visible tab as an image with coordinate scaling, clearly distinguishing it from DOM-based sibling tools like click, read_page, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes the vision loop pattern (screenshot -> decide coords -> click) and explicitly states it needs no DOM refs, guiding when to use vs alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![agentcursor MCP server](https://glama.ai/mcp/servers/kumard3/agentcursor/badges/card.svg)](https://glama.ai/mcp/servers/kumard3/agentcursor)

Score Badge

Copy to your README.md:

[![agentcursor MCP server](https://glama.ai/mcp/servers/kumard3/agentcursor/badges/score.svg)](https://glama.ai/mcp/servers/kumard3/agentcursor)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/kumard3/agentcursor'

If you have feedback or need assistance with the MCP directory API, please join our Discord server