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., "@SlimSnap MCP look at my last capture"
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.
Your recent screen captures, as structured data your AI can actually read.
Take a capture in SlimSnap, mark what you mean, then in Claude or Cursor say "look at my last capture". No pasting, no file paths, no clipboard.
Not a screenshot. A JSON document: every piece of text on screen with its position and colour, plus the arrows, boxes and callouts you drew, and which element each one points at.
That matters for three reasons.
A screenshot pasted into an agent gets downscaled before the model reads it, and nobody tells you. Anthropic's own docs say to pre-resize and crop your images because resizing "might make text less legible". A tall page loses its text entirely.
Images returned over MCP are worse still. In Claude Code they are passed through as text rather than native image blocks, costing roughly 15-25k tokens against about 1.6k for the same image pasted directly, and the model cannot read them at all (claude-code#31208, closed as not planned). A big enough result blows the per-result token ceiling outright (#9152).
And an oversized screenshot can poison a session permanently. It stays in context, gets re-sent every turn, and there is no way to remove it (#55040).
This connector sidesteps all three by never sending the picture. An ordinary screen costs roughly a third less than the same screen as an image, and on a tall page the comparison stops being about cost at all: shrinking an 18,410 pixel page to fit the model's 1568 pixel limit leaves body text 1.4 pixels tall, so the cheap image is cheap because it is unreadable. Either way the agent gets exact coordinates rather than a guess about which button you meant.
When you genuinely need pixels (visual style, spacing, colour balance) there is a separate tool for that, and the image is already downscaled to a size the model can read.
Related MCP server: Desktop MCP
Claude Code
claude mcp add slimsnap -- npx -y @slimsnap/mcpThen check it: /mcp should list slimsnap with 4 tools.
Claude Desktop
Download slimsnap-mcp.mcpb from Releases and open it. Claude shows an install dialog. The connector then appears under Settings.
Cursor
Or add it by hand to .cursor/mcp.json in your project, or ~/.cursor/mcp.json for every project:
{
"mcpServers": {
"slimsnap": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@slimsnap/mcp"]
}
}
}Project config wins over global when both exist. Then ask Cursor about your last capture the same way you would ask Claude.
As a Claude Code plugin (same connector, installed and updated as a plugin)
/plugin marketplace add bickov/slimsnap-mcp
/plugin install slimsnap@slimsnapYou need SlimSnap 0.5.0 or newer, because that is the version that started keeping recent captures on disk.
The first time Claude Code uses each tool it asks for permission, and the approval is scoped to the folder you were in. Four tools means four prompts, and they come back in the next project. Nothing is wrong; that is how Claude Code gates MCP tools.
To approve them once, everywhere, add this to ~/.claude/settings.json:
{
"permissions": {
"allow": [
"mcp__slimsnap__get_latest_capture",
"mcp__slimsnap__list_captures",
"mcp__slimsnap__get_capture",
"mcp__slimsnap__get_capture_image"
]
}
}If the file already exists, merge the allow entries into it rather than replacing it. Restart Claude Code afterwards.
Tool | What it does |
| The newest capture as structured JSON. This is the one that gets used most. |
| Recent captures newest first, with a text preview. Use it to find an older one, or to work through several marked screens at once. |
| One capture by id. |
| One frame as a downscaled image, for when the JSON cannot answer the question. |
Four tools on purpose. Tool descriptions are charged against your context window on every turn, so the surface stays small.
Two sample captures live in samples/ — one single screen, one
three-frame scroll capture, both with an arrow resolved to the element it points
at. Copy either into ~/.slimsnap/recent/ and the connector will read it, so you
can try all four tools before installing SlimSnap.
mkdir -p ~/.slimsnap/recent
cp -R samples/single-frame ~/.slimsnap/recent/2026-07-30T09-00-00-000000-00-00Then ask your agent what did I mark in my last capture? — it should come back with the Save changes button and the note attached to it.
SlimSnap keeps your recent captures in ~/.slimsnap/recent/, newest 20 by default. Each capture is a folder with capture.json, a small meta.json index, and one PNG per frame capped at 1568px on the long edge.
The connector finds that folder by reading ~/.slimsnap/config.json, which SlimSnap rewrites whenever your settings change. Move your save folder and the connector follows, with nothing to reconfigure.
Change how many are kept, or turn the cache off entirely, in SlimSnap under Settings, Export, Recent captures. There is a Clear button in the same place.
The server reads files under your home directory and talks to nobody. There is no network code in it. It cannot capture your screen and it cannot ask SlimSnap to capture your screen. It only reads captures you already took and chose to keep.
Nothing is uploaded, there is no account, and no telemetry.
No personal data is collected, stored, transmitted or shared. The server has no network code and no analytics. Full policy: https://slimsnap.ai/privacy.
SlimSnap 0.5.0 or newer, macOS or Windows. Works with Claude Code, Claude Desktop and Cursor.
Codex is not supported yet. It caps a single tool result at about 10 KB, which a real capture goes past, and it drops image content when structured output is present (codex#7906, #10334). Both are open upstream.
The Claude Desktop route needs nothing else: Desktop ships its own Node and the .mcpb bundle uses it. The Claude Code route runs node from your PATH, so it needs Node 18 or newer installed. That catches people out on a fresh Windows machine, where Node usually isn't there.
MIT
Returns one specific capture as structured JSON, same shape as get_latest_capture. Get ids from list_captures.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Capture id from list_captures. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already marking readOnlyHint=true, the description adds useful context about the return shape ('same shape as get_latest_capture') and the data source for ids. It does not disclose potential error behavior (e.g., not found) but is acceptable for a simple read operation.
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?
Two concise sentences with no redundant information. Each clause serves a purpose: what it returns, how the output relates to other tools, and where to find ids.
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 single-parameter retrieval tool with readOnly annotation and no output schema, the description is complete. It covers the input source, output shape, and relationship to sibling tools, leaving no critical gaps for an agent to invoke it correctly.
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 for the only parameter. The tool description adds 'Get ids from list_captures' which reinforces schema info, but does not add meaningful new semantics beyond what the schema already provides, matching the baseline for high coverage.
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 states a specific verb ('Returns') and resource ('one specific capture'), with scope also indicated ('by id'). It explicitly differentiates from siblings by mentioning get_latest_capture and list_captures, making its unique purpose clear.
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?
Provides clear usage context by referencing list_captures for obtaining ids and comparing its output shape to get_latest_capture. It implies when to use this tool (to fetch a known capture) but does not explicitly state when not to use alternatives, so a point off for lacking explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the actual pixels of one frame, already downscaled to a size the model can read. Useful for visual questions that the text and coordinates cannot settle, such as spacing, visual style, colour balance, or imagery with no text in it. Costs substantially more tokens than the structured form of the same capture.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Capture id. Omit to use the newest capture. | |
| frame | No | 1-based frame number. Scroll captures have several, top to bottom. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint true, so the description adds extra context: the image is downscaled and costs substantially more tokens than the structured form. This goes beyond the annotation's safety signal, though it doesn't mention potential errors or output format specifics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three focused sentences: one for function, one for usage context, one for cost warning. Each sentence adds distinct value with no redundancy or filler.
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 two-parameter tool with no output schema, the description fully covers purpose, when to use it, and an important cost caveat. Annotations cover the read-only nature, making this complete in context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage for both parameters (id and frame) with detailed descriptions. The tool description adds no additional parameter-level semantics, so the 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 clearly states the tool returns actual pixels of one frame as an image, distinguishing it from sibling tools like get_capture which returns structured data. It also specifies that the image is downscaled for model readability, making the purpose unambiguous.
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?
Provides explicit use cases: visual questions that text and coordinates cannot settle, such as spacing, style, colour balance, or imagery without text. It also contrasts with the structured form of the same capture, implicitly indicating when not 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.
Returns the newest SlimSnap capture as structured JSON: every OCR'd text element with its normalised bounding box and colour, plus any annotations the user drew (arrows, boxes, highlights, callouts) and which element each one points at. Use this whenever the user refers to their screen, their last screenshot, 'this', 'here', or something they just marked. Returns no image. The text and coordinates answer most questions about a capture on their own; the pixels are available separately when a question is genuinely visual.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description adds substantial behavioral context by detailing the return structure (OCR elements, bounding boxes, colors, annotations, pointer associations) and explicitly stating that no image is returned. This goes well beyond the annotation and clarifies what consumers can expect.
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 yet information-dense, with the primary action and return type front-loaded in the first sentence. The second sentence adds usage context and exclusions 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 it has no output schema, the description enumerates the returned data elements in enough detail to set expectations, and it explicitly states what is not returned (no image) and where to find pixel data. This makes the tool's behavior complete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and schema coverage is 100%, so the baseline is 4. No parameter semantics need clarification, and the description correctly focuses on output and usage rather than inventing parameter details.
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 returns the newest SlimSnap capture as structured JSON with specific contents, and distinguishes itself from siblings by explicitly noting 'Returns no image' and emphasizing 'newest' versus a generic get_capture.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use guidance: 'Use this whenever the user refers to their screen, their last screenshot, "this", "here", or something they just marked.' It also explains when not to use it, directing users to the pixel tool for genuinely visual questions, and implicitly differentiates from list_captures and get_capture.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists the user's recent captures newest first, with a short text preview of each. This is the cheap summary view; get_capture returns a single capture in full. Useful for finding an earlier capture when the user does not mean the newest one, or for working through several marked screens.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many captures to return. Default 10. |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| captures | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses ordering ('newest first'), preview behavior, and a performance trait ('cheap summary view'). It does not detail the exact content of previews or pagination behavior, but the added context goes beyond annotations.
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?
Two sentences, zero waste. The first sentence delivers the core purpose; the second adds context and differentiation. Information is front-loaded and every sentence earns its place.
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 list tool with one parameter, an output schema, and a read-only annotation, the description covers the essential behavior, ordering, preview, and usage scenarios. There are no significant gaps.
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 schema fully documents the only parameter ('limit') with description, default, and range. The description does not need to add parameter semantics; 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 action ('Lists'), the resource ('captures'), and the scope ('user's recent'), plus ordering ('newest first') and content ('short text preview'). It also distinguishes itself from the sibling get_capture by framing it as 'the cheap summary view'.
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?
Provides clear usage context: 'Useful for finding an earlier capture when the user does not mean the newest one, or for working through several marked screens.' It explicitly names get_capture as an alternative but does not explicitly address get_latest_capture, leaving that distinction implied by context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.2get_captureget_capture_imageget_latest_capturelist_capturesEach tool has a clearly distinct role: list_captures gives an overview, get_latest_capture and get_capture return structured data for different selections, and get_capture_image provides the raw pixels. The descriptions reinforce these boundaries, so an agent should not confuse them.
All tool names follow a consistent verb_noun pattern: list_captures, get_capture, get_latest_capture, and get_capture_image. The variation in pluralization and the additional 'latest' qualifier are natural and predictable.
Four tools is a well-scoped set for a capture retrieval server. There are no redundant tools and each one contributes a distinct function, covering both listing and accessing individual captures.
The tool surface fully covers the core lifecycle of reading captures: listing available captures, retrieving the latest capture, retrieving a specific capture by ID, and fetching the raw image when needed. There are no obvious missing operations for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
Cross-device AI memory with encrypted activity capture and context handoff between AI tools
Capture screenshots, detect visual regressions between page versions, and analyze with AI.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bickov/slimsnap-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
