Skip to main content
Glama
pixelvault-dev

@pixelvault-dev/local-mcp

by pixelvault-dev
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

@pixelvault-dev/local-mcp

A local (stdio) MCP server for PixelVault — agent-first image hosting.

The difference from the hosted MCP server (mcp.pixelvault.dev): this one runs on your machine, so it can upload a local file by path. It reads the bytes off disk and streams them to the API as multipart/form-data — the file is never base64-encoded into the model's context. That keeps large images (and slow, token-hungry base64 round-trips) out of the conversation.

Use the hosted server when your client is remote (ChatGPT, etc.); use this one for local coding agents that have files on disk.

Install

Runs with npx — no global install needed:

npx @pixelvault-dev/local-mcp

Related MCP server: image-vision-mcp

Configure

Set your PixelVault API key (a pv_live_… secret key for private uploads):

export PIXELVAULT_API_KEY=pv_live_xxx
# optional: point at a different API
export PIXELVAULT_API_URL=https://api.pixelvault.dev

The server also reads ~/.pixelvault/config.json if you've authenticated with the PixelVault CLI (pixelvault login).

Claude Desktop / MCP client config

{
  "mcpServers": {
    "pixelvault": {
      "command": "npx",
      "args": ["-y", "@pixelvault-dev/local-mcp"],
      "env": { "PIXELVAULT_API_KEY": "pv_live_xxx" }
    }
  }
}

Tools

Tool

What it does

upload_image

Upload by local path (streamed, no base64), or source_url, or data. Optional folder, visibility, expires_in.

list_images

List images in your project (paginated).

get_image

Metadata for one image by id.

delete_image

Permanently delete an image by id.

sign_url

Mint a time-limited signed URL for a private image.

transform_image

Build an on-the-fly transform URL (resize, crop, format, AI background removal, effects).

Every returned CDN URL supports on-the-fly transforms via query params — see the transforms docs.

License

MIT

Available Tools

6 tools
delete_imageDelete imageA

Permanently delete one PixelVault image by id (DELETE /v1/images/:id).

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesImage id to delete, e.g. img_abc123.

TDQS

A3.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, and the description only says 'permanently delete'—lacking details on authorization, error handling, or side effects. Minimal beyond the action itself.

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, front-loaded with the action, no wasted words. Efficiently communicates the core behavior.

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 delete tool with one parameter and no output schema, the description covers the essential: purpose, parameter role, permanence. Lacks minor details like idempotency or error cases, but 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 coverage is 100% with parameter description including an example. Description merely restates 'by id', adding no meaningful new information beyond the schema.

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 it permanently deletes an image by ID, distinguishes from siblings like upload, list, get, sign, and transform. Includes HTTP method and endpoint for precision.

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?

Usage is implied as the destructive counterpart to other image tools, but no explicit when-to-use, when-not-to-use, or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_imageGet imageA

Get metadata (CDN URL, size, MIME type, dimensions) for one PixelVault image by id (GET /v1/images/:id). The returned CDN URL supports on-the-fly transforms via query params — e.g. ?w=400&fit=cover (resize/crop), ?fmt=webp (format), ?segment=foreground (AI background removal → transparent PNG), and effects like ?blur=30&saturation=0&rotate=90. Or call transform_image to build a valid transform URL for you. See https://pixelvault.dev/docs#transforms.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesImage id to fetch, e.g. img_abc123.

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes that it is a GET request, implying read-only and safe behavior. Lists the specific metadata returned. Could be more explicit about error handling or rate limits, but no annotations exist to contradict.

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?

Concise, front-loaded with purpose, includes examples and cross-reference to another tool and docs. No wasteful sentences.

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?

No output schema, but description explains all relevant return values (metadata, transforms). References alternative tool and documentation for further details. Complete for a simple get-by-id tool.

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 100% coverage with parameter description. Description adds value by explaining the return structure and transforms, which relates to the parameter's output.

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?

Explicitly states 'Get metadata (CDN URL, size, MIME type, dimensions) for one PixelVault image by id' with specific verb and resource. Distinct from siblings like list_images, upload_image, delete_image, sign_url, transform_image.

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?

Mentions alternative tool transform_image for building transform URLs, and includes a docs link for further guidance. Does not explicitly list when to use other siblings like list_images, but provides clear context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_imagesList imagesA

List images in your PixelVault project, most recent first (GET /v1/images), paginated via page/per_page. The returned CDN URL supports on-the-fly transforms via query params — e.g. ?w=400&fit=cover (resize/crop), ?fmt=webp (format), ?segment=foreground (AI background removal → transparent PNG), and effects like ?blur=30&saturation=0&rotate=90. Or call transform_image to build a valid transform URL for you. See https://pixelvault.dev/docs#transforms.

ParametersJSON Schema
NameRequiredDescriptionDefault
pageNoPage number (default 1).
per_pageNoItems per page (default 20, max 100).

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It thoroughly discloses behavior: pagination via page/per_page, ordering, and that the returned CDN URL supports transforms. It adds significant transparency beyond the schema.

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 compact (3 sentences) and front-loaded with purpose. It includes a useful link, though the sentence on transforms is lengthy. No wasted words, but slightly dense.

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 adequately covers the tool's behavior (pagination, ordering, transforms). It does not detail return format, but that is typical for a list tool. The sibling tools and link provide additional context.

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 coverage is 100%, so baseline is 3. The description reiterates pagination defaults (default 1, 20, max 100) already in the schema, adding no new semantic meaning beyond referencing the transform capability.

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 'List images' with the endpoint, ordering ('most recent first'), and pagination. It distinguishes from sibling tool 'transform_image' by referencing it for URL building, making the purpose specific and unambiguous.

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 indicates when to use (listing images with pagination) and mentions transform_image as an alternative for URL transforms. However, it does not explicitly state when not to use or provide exclusions, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sign_urlSign private URLA

Mint a time-limited signed URL for a private image (POST /v1/images/:id/sign-url). The signature binds the image, so the URL can't be replayed against another; strip it and the CDN returns 403. Optional expires_in (seconds, default 3600).

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesImage id to mint a signed URL for, e.g. img_abc123.
expires_inNoSignature lifetime in seconds (60–2,592,000). Default 3600 (1 hour).

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full behavioral burden. It discloses security-critical traits: the signature binds to the image, prevents replay, and returns 403 if stripped. It also mentions the optional expires_in and default. No contradictions or hidden behaviors.

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 endpoint, then providing behavioral context. Every sentence adds value with no repetition 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 the low complexity (2 parameters, no nested objects, no output schema), the description covers the essential information: what the tool does, security behavior, and expiration. It could mention the return format (the signed URL string) but this is not critical for correct invocation.

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 coverage is 100%, so the description need not add much. It does mention that expires_in is optional with a default of 3600 seconds, which the schema also specifies. The description adds no new semantic insight beyond the schema, meeting the baseline of 3.

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 verb 'mint' and the resource 'time-limited signed URL for a private image', including the HTTP endpoint. This is distinct from sibling tools (upload, list, get, delete, transform), which all handle different operations on images.

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 implies the use case (private image, time-limited access) and explains behavioral constraints (signature binding, 403 on stripping). However, it does not explicitly state when to use this tool versus alternatives, though the purpose is sufficiently clear to differentiate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

transform_imageBuild transform URLA

Build an on-the-fly transform URL for a PixelVault image (resize, crop, format/quality, AI background removal, blur/sharpen/rotate/flip, brightness/contrast/saturation, and same-project watermark tiling). Provide exactly one of url (a PixelVault CDN URL) or id (resolved via the API), plus one or more transform params. See https://pixelvault.dev/docs#transforms.

ParametersJSON Schema
NameRequiredDescriptionDefault
idNoPixelVault image id (e.g. img_abc123); its CDN URL is resolved via the API. Provide this OR url.
fitNoResize mode. scale-down (default) never enlarges; others may upscale. Only with width/height.
urlNoAbsolute PixelVault CDN URL (as returned by upload_image / get_image / list_images). Provide this OR id.
blurNoGaussian blur (0-250).
flipNoMirror horizontally (h), vertically (v), or both (hv).
sizeNoNamed size preset: s=256px, m=640px, l=1280px, social=1200x630 OG card. Wins over width/height.
tileNoFilename of another image in the SAME project to tile as a watermark.
zoomNoFace-crop tightness 0.0-1.0, only with gravity=face.
widthNoTarget width in px (1..4000).
formatNoOutput format. auto negotiates WebP/AVIF.
heightNoTarget height in px (1..4000).
rotateNoRotate clockwise; rounded to the nearest right angle.
gravityNoCrop anchor with fit=cover|crop: face, left, right, top, bottom, auto, or 'XxY'.
qualityNoOutput quality. auto lets Cloudflare choose.
segmentNoAI background removal: foreground keeps the subject, background becomes transparent (PNG output).
sharpenNoSharpen strength (0-10).
contrastNoContrast multiplier 0-2 (1=no change).
backgroundNoFill color behind a removed/padded background: hex, rgb(), or CSS name.
brightnessNoBrightness multiplier 0-2 (1=no change).
saturationNoSaturation multiplier 0-2 (1=no change, 0=grayscale).

TDQS

A4/5.0
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 mentions 'on-the-fly' and 'resolved via the API' but does not explicitly state side effects, whether the tool makes network calls, or any rate limits. The behavior is moderately clear.

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 a brief instruction and a link. It is front-loaded with the core purpose and contains no fluff.

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?

With 20 parameters and no output schema, the description adequately lists capabilities and constraints. The return value (URL string) is implied but not explicitly stated. Overall, it is fairly complete.

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 description coverage is 100%, so baseline is 3. The description adds value by grouping parameters into categories (resize, crop, etc.) and highlighting the exclusive-or relationship between url and id.

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 builds a transform URL for PixelVault images, listing many operations. It is distinct from sibling tools like upload_image or list_images.

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 provides a key usage constraint (provide one of url or id) but does not explicitly state when to use this tool versus alternatives, such as signing vs. transforming.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

upload_imageUpload imageA

Upload an image to PixelVault and get an instant CDN URL. Prefer path — a LOCAL file path the server reads off disk and streams — so large files aren't base64-encoded into the model context. Alternatively pass source_url (a public https URL the API imports) or data (base64 bytes). Optional folder, filename, visibility (private → signed URL, needs a secret key), expires_in (auto-expiring image), sign_expires_in. Max 5 MB; JPG/PNG/GIF/WebP/AVIF/SVG. The returned CDN URL supports on-the-fly transforms via query params — e.g. ?w=400&fit=cover (resize/crop), ?fmt=webp (format), ?segment=foreground (AI background removal → transparent PNG), and effects like ?blur=30&saturation=0&rotate=90. Or call transform_image to build a valid transform URL for you. See https://pixelvault.dev/docs#transforms.

ParametersJSON Schema
NameRequiredDescriptionDefault
dataNoBase64-encoded image bytes (data URLs accepted). Prefer `path` for local files. Provide exactly one of path, source_url, or data.
pathNoAbsolute or relative path to a LOCAL image file. The server reads the file off disk and streams the bytes — nothing is base64-encoded into the model context, so large files work. Provide exactly one of path, source_url, or data.
folderNoOptional folder/path prefix for the image.
filenameNoOptional filename override, e.g. photo.png.
expires_inNoOptional time-to-live in seconds (60–2,592,000, i.e. 1 min to 30 days). The image is auto-deleted after this. Omit for a permanent image.
source_urlNoPublic https URL of an image; the PixelVault API fetches and imports it. Provide exactly one of path, source_url, or data.
visibilityNo`private` returns a signed URL only link-holders can open. Defaults to public.
sign_expires_inNoFor visibility=private: signed-URL lifetime in seconds (default 3600).

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. Discloses file size limit (5 MB), supported formats, auto-deletion with expires_in, private visibility yielding signed URLs, and on-the-fly transforms. Could mention overwrite behavior but very transparent overall.

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?

Well-structured with main action first, then parameter alternatives and optional fields. Slightly lengthy but every sentence adds value. Could be more concise by grouping transforms, but still efficient.

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?

Very complete: covers all 8 parameters, return value (CDN URL with transforms), explains transforms, mentions max size and formats, references external docs. No output schema or annotations, so description compensates fully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, description adds significant value: explains path reads local disk to avoid base64, source_url is fetched, data is base64, visibility meaning, and expires_in auto-deletion. Provides context far beyond schema descriptions.

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?

Clearly states 'Upload an image to PixelVault and get an instant CDN URL' with specific verb and resource. Distinguishes from siblings by discussing alternative input methods and mentioning transform_image for URL transformations.

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 explicit guidance on parameter preference: 'Prefer path' for large files to avoid base64 encoding. Mentions alternative tool transform_image for building transform URLs. Lacks explicit when-not-to-use but sibling names imply distinct use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 6 tool updatesv0.1.0
    • First observeddelete_image
    • First observedget_image
    • First observedlist_images
    • First observedsign_url
    • First observedtransform_image
    • First observedupload_image
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0
Disambiguation5/5

Each tool has a distinct purpose: uploading, listing, retrieving metadata, deleting, signing URLs, and building transform URLs. No functional overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (e.g., upload_image, list_images, get_image), making the set predictable.

Tool Count5/5

6 tools is appropriate for an image management server—neither too few nor too many, covering essential operations without redundancy.

Completeness4/5

The server covers upload, list, get, delete, signing, and transform URL generation. Missing an update/rename tool for metadata, but the core lifecycle is well-represented.

Maintenance

ActivitySlowing
ResponsivenessSyncing

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

Related MCP Servers

Latest Blog Posts

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/pixelvault-dev/mcp-local'

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