Skip to main content
Glama

Lightdrift Images MCP

by ai.lightdrift
OverviewDiscussionsAdmin

Server Details

Search over 1.85 million captioned images with natural language, find similar images from a Lightdrift asset ID, and retrieve hosted file URLs, source licenses, and attribution. Powered by joint image-and-caption embeddings with caption text reranking. Connect with OAuth or an API key. Searches cost $0.02; image details are free. External image uploads and image-plus-text queries are not yet supported. Setup: https://docs.lightdrift.ai/guides/images-mcp

Ownership verified
Status
Healthy
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL

TDQS

A4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: natural language search, similarity search, and metadata retrieval for a specific asset. There is no overlap in intended use.

Naming Consistency5/5

All tool names follow the same verb_noun pattern (search_images, find_similar_images, get_image) using lowercase and underscores, making the interface predictable.

Tool Count5/5

Three tools are well-scoped for a focused image search and retrieval server. Each tool serves a necessary function without redundancy or bloat.

Completeness5/5

The tool set covers the core lifecycle for the stated purpose: finding images via search or similarity, and retrieving full asset details. No critical operations are missing for a licensed image index.

Available Tools

3 tools
find_similar_imagesFind similar imagesAInspect

Find similar images using the saved Voyage joint image-and-caption vector of an asset in the current search index. The seed is excluded; results are ordered by retrieval similarity without a text reranker. An asset outside the current index returns an error, with no legacy fallback. External image URLs are not accepted; use search_images for a text description, or get_image for metadata only. Returns query_id and a results array with asset_id, file and thumbnail URLs, source, dimensions, and rights including attribution. Set k for result count; defaults exclude AI-generated images, require commercial-use licenses, and require width >= 1000 pixels. Requires OAuth or an API key, available credits, and account rate-limit capacity. Each successful call charges $0.02 and records usage; repeated calls can charge again. Does not modify images or publish anything.

ParametersJSON Schema
NameRequiredDescriptionDefault
kNoMaximum number of final results (1–100, default 10). Fewer results may match the filters; this is separate from candidate-pool sizes.
ann_kNoMaximum semantic-search candidates (1–1000, default 100). Increase for a wider pool; this does not set the final result count.
ann_efNoLegacy retrieval tuning parameter (64–4096, default 2048). Accepted for compatibility; leave at the default for the current retrieval service.
explainNoInclude retrieval and ranking diagnostics with each result (default false). Use for debugging search quality.
filtersNoCombine license, source, size, and visual filters. Omitted commercial, ai_generated, min_width and nsfw_max default to true, false, 1000 and 0.2. Set any of these four to null to remove its default.
asset_idYesExact asset_id from a Lightdrift search result or previously saved asset (1–255 characters). Pass the ID unchanged, not a file URL.

TDQS

A4.9/5.0
Behavior5/5

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

The annotations are sparse and readOnlyHint is false, so the description carries the burden of behavioral disclosure. It adds concrete operational details: requires OAuth/API key, available credits, and rate-limit capacity; charges $0.02 per successful call; records usage and can charge again on repeats; and explicitly says it does not modify images or publish anything. It also discloses the seed-exclusion behavior and lack of a reranker, which are not visible in the schema or 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?

Every sentence carries distinct, decision-relevant information: mechanism, index scoping, seed exclusion, no reranker, error behavior, alternatives, return shape, defaults, auth/cost, and side-effect disclaimer. The most important facts are front-loaded, and the longer length is justified by the density and operational importance of the content.

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?

With no output schema, the description adequately names the return shape: query_id and a results array with asset_id, file and thumbnail URLs, source, dimensions, and rights including attribution. It covers error conditions, auth prerequisites, cost, and filter defaults, while delegating precise numeric bounds to the schema. For a complex tool with nested filters and no output schema, this is 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 coverage is 100%, so the baseline is 3, but the description adds value beyond the schema by explaining the effect of k, the default filters (exclude AI-generated, require commercial-use, require width >= 1000), and the fact that the seed asset is excluded from results. It also restates that asset_id must be passed unchanged. It does not summarize ann_k/ann_ef, but the schema already documents those parameters thoroughly.

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?

States a specific operation: find similar images from the saved Voyage joint image-and-caption vector of an asset in the current search index. It clearly scopes the tool and distinguishes it from siblings by explicitly rejecting external image URLs and pointing to search_images and get_image for those cases. No ambiguity about what resource is acted on.

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?

Explicitly names the alternatives and when to use them: 'use search_images for a text description, or get_image for metadata only.' It also warns that assets outside the current index return an error with no legacy fallback, and that results are ordered without a text reranker. This is strong routing guidance for an agent deciding between tools.

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

get_imageGet imageA
Read-onlyIdempotent
Inspect

Retrieve one known Lightdrift asset by the asset_id returned from search_images or find_similar_images. Returns an object with asset_id, title, source, dimensions, format, file and thumbnail URLs, and rights including attribution and provenance. Use this to inspect a selected image or retrieve a saved asset; use the search tools to discover images. Requires OAuth or an API key. Free: does not deduct search credits or modify the image; access is logged. An unknown asset_id returns a tool error. Inspect rights before using the file.

ParametersJSON Schema
NameRequiredDescriptionDefault
asset_idYesExact asset_id from a Lightdrift search result or previously saved asset (1–255 characters). Pass the ID unchanged, not a file URL.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description goes beyond these by adding that the call is free (does not deduct search credits), does not modify the image, that access is logged, and that an unknown asset_id returns a tool error. These are valuable behavioral details not present in the annotations.

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 about 100 words and every sentence contributes: purpose, return fields, usage routing, auth, cost, logging, error, and a rights warning. It is front-loaded with the core action and then packs relevant context. Slightly longer than minimal, but not padded.

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?

With no output schema, the description carries the burden of explaining return values, and it does so by listing the fields (asset_id, title, source, dimensions, format, URLs, rights). It also covers the error case, auth requirements, cost, logging, and a pre-use caution. For a one-parameter read-only tool, this is 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 coverage is 100%, so the baseline is 3. The description adds a meaningful correctness hint—'Pass the ID unchanged, not a file URL'—and frames the parameter in the context of search results and saved assets, reinforcing the expected input beyond what the raw schema property description states.

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 states a specific verb ('Retrieve') and resource ('one known Lightdrift asset'), and explicitly distinguishes itself from the search tools by saying 'use the search tools to discover images.' It also ties the asset_id to the outputs of search_images and find_similar_images, making the relationship to siblings clear.

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 gives explicit when-to-use guidance ('inspect a selected image or retrieve a saved asset') and when-not-to ('use the search tools to discover images'). It also names a prerequisite (OAuth or API key) and a safety note (inspect rights before using the file).

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

search_imagesSearch imagesAInspect

Search the Voyage index of 1,852,370 captioned images using joint image-and-caption embeddings, hybrid retrieval and caption text reranking. Image-upload queries and icon-pack search are not supported. Describe subjects, recognizable names, visible text, mood, style or composition in natural language, such as 'misty mountains at sunrise'. Use find_similar_images when you already have a Lightdrift asset_id, or get_image to retrieve one known image without a search. Returns query_id and a ranked results array with asset_id, file and thumbnail URLs, source, dimensions, and rights including attribution. Set k for result count; optional candidate and ranking controls normally need no changes. Defaults exclude AI-generated images, require commercial-use licenses, and require width >= 1000 pixels; nsfw_max defaults to 0.2. These four defaulted filters accept null to opt out; unknown NSFW scores pass. Requires OAuth or an API key and is subject to account rate limits and available credits. Each successful call charges $0.02 and records usage; repeated calls can charge again. Does not modify images or publish anything. Inspect each result's rights before use.

ParametersJSON Schema
NameRequiredDescriptionDefault
kNoMaximum number of final results (1–100, default 10). Fewer results may match the filters; this is separate from candidate-pool sizes.
modeNoRanking mode: auto (default) and text use Voyage caption text reranking; none skips reranking. Every mode uses the same joint image-and-caption index, never a legacy visual reranker.auto
ann_kNoMaximum semantic-search candidates (1–1000, default 100). Increase for a wider pool; this does not set the final result count.
queryYesDescribe the image, subject, scene, or mood to find (1–1000 characters), for example: misty mountains at sunrise.
ann_efNoLegacy retrieval tuning parameter (64–4096, default 2048). Accepted for compatibility; leave at the default for the current retrieval service.
bm25_kNoMaximum keyword-search candidates (0–1000, default 50), combined with ann_k semantic candidates. Set 0 for semantic-only retrieval.
explainNoInclude retrieval and ranking diagnostics with each result (default false). Use for debugging search quality.
filtersNoCombine license, source, size, and visual filters. Omitted commercial, ai_generated, min_width and nsfw_max default to true, false, 1000 and 0.2. Set any of these four to null to remove its default.
rerank_kNoMaximum candidates to rerank (1–500, default 60); null reranks the whole candidate pool and can exceed provider limits; prefer a bounded value. Ignored when mode is none. Independent of final result count k.
rerank_textNoLegacy reranker text toggle (default true). The current service always uses text; leave true.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations are minimal (readOnlyHint false, destructiveHint false), so the description carries the burden. It thoroughly discloses behavior: requires OAuth/API key, subject to rate limits and credits, charges $0.02 per call, does not modify or publish, defaults that affect results (AI-generated exclusion, commercial license, min width, NSFW threshold), and how to opt out of defaults. This goes well beyond the annotations.

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 lengthy but every sentence carries substance. It is front-loaded with purpose and exclusions, then provides query guidance, sibling alternatives, return format, parameter advice, defaults, auth/cost, and non-destructive behavior. A few sentences could be tightened (e.g., 'optional candidate and ranking controls normally need no changes' is helpful but perhaps redundant with schema), but overall it earns its length.

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?

The description is comprehensive for a complex tool with 10 parameters, nested filters, and no output schema. It covers the query format, exclusions, return shape (query_id and ranked results array with asset_id, URLs, source, dimensions, rights), default filter behavior, costs, auth, and non-destructive nature. Nothing an agent needs to call it correctly is missing.

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. However, the description adds meaningful context beyond the schema, such as: 'Set k for result count; optional candidate and ranking controls normally need no changes', the behavior of the four defaulted filters (commercial, ai_generated, min_width, nsfw_max) and that they can be set to null to opt out. It also clarifies that ann_k does not set final result count. This adds value over 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?

The description clearly states it searches a specific index of captioned images using joint image-and-caption embeddings. It also explicitly names unsupported query types (image-upload, icon-pack) and differentiates from siblings find_similar_images and get_image by specifying their distinct use cases.

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?

The description gives explicit guidance: 'Use find_similar_images when you already have a Lightdrift asset_id, or get_image to retrieve one known image without a search.' It also advises on natural-language query phrasing and notes that optional candidate/ranking controls normally need no changes.

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.

  1. 2 tool updates
    • Changedfind_similar_images6 fields changed
      • changedInput schema / properties / filters / description
        Previous value: -"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, and min_width default to true, false, and 1000; set those fields to null to remove their defaults."New value: +"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, min_width and nsfw_max default to true, false, 1000 and 0.2. Set any of these four to null to remove its default."
      • addedInput schema / properties / filters / properties / nsfw_max / anyOf
        Added value: +[
+  {
+    "maximum": 1,
+    "minimum": 0,
+    "type": "number"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / filters / properties / nsfw_max / description
        Previous value: -"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2. Assets without a score can still match."New value: +"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2; null removes the restriction. Assets without a score can still match."
      • removedInput schema / properties / filters / properties / nsfw_max / maximum
        Removed value: -1
      • removedInput schema / properties / filters / properties / nsfw_max / minimum
        Removed value: -0
      • removedInput schema / properties / filters / properties / nsfw_max / type
        Removed value: -"number"
    • Changedsearch_images10 fields changed
      • changedInput schema / properties / filters / description
        Previous value: -"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, and min_width default to true, false, and 1000; set those fields to null to remove their defaults."New value: +"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, min_width and nsfw_max default to true, false, 1000 and 0.2. Set any of these four to null to remove its default."
      • addedInput schema / properties / filters / properties / nsfw_max / anyOf
        Added value: +[
+  {
+    "maximum": 1,
+    "minimum": 0,
+    "type": "number"
+  },
+  {
+    "type": "null"
+  }
+]
      • changedInput schema / properties / filters / properties / nsfw_max / description
        Previous value: -"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2. Assets without a score can still match."New value: +"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2; null removes the restriction. Assets without a score can still match."
      • removedInput schema / properties / filters / properties / nsfw_max / maximum
        Removed value: -1
      • removedInput schema / properties / filters / properties / nsfw_max / minimum
        Removed value: -0
      • removedInput schema / properties / filters / properties / nsfw_max / type
        Removed value: -"number"
      • changedInput schema / properties / mode / default
        Previous value: -"visual"New value: +"auto"
      • changedInput schema / properties / mode / description
        Previous value: -"Ranking mode: visual selects the default relevance reranker; none skips reranking and returns retrieval order. Default visual."New value: +"Ranking mode: auto (default) and text use Voyage caption text reranking; none skips reranking. Every mode uses the same joint image-and-caption index, never a legacy visual reranker."
      • changedInput schema / properties / mode / enum
        Previous value: -[
-  "visual",
-  "none"
-]New value: +[
+  "auto",
+  "text",
+  "none"
+]
      • changedInput schema / properties / rerank_k / description
        Previous value: -"Maximum candidates to rerank (1–500, default 60); null reranks the whole candidate pool. Ignored when mode is none. Independent of final result count k."New value: +"Maximum candidates to rerank (1–500, default 60); null reranks the whole candidate pool and can exceed provider limits; prefer a bounded value. Ignored when mode is none. Independent of final result count k."
  2. 3 tool updates
    • Changedfind_similar_images21 fields changed
      • addedInput schema / properties / ann_ef / description
        Added value: +"Legacy retrieval tuning parameter (64–4096, default 2048). Accepted for compatibility; leave at the default for the current retrieval service."
      • addedInput schema / properties / ann_k / description
        Added value: +"Maximum semantic-search candidates (1–1000, default 100). Increase for a wider pool; this does not set the final result count."
      • addedInput schema / properties / asset_id / description
        Added value: +"Exact asset_id from a Lightdrift search result or previously saved asset (1–255 characters). Pass the ID unchanged, not a file URL."
      • addedInput schema / properties / explain / description
        Added value: +"Include retrieval and ranking diagnostics with each result (default false). Use for debugging search quality."
      • addedInput schema / properties / filters / description
        Added value: +"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, and min_width default to true, false, and 1000; set those fields to null to remove their defaults."
      • addedInput schema / properties / filters / properties / ai_generated / description
        Added value: +"Filter by AI-generated status. Defaults to false when omitted; null allows either. False does not exclude non-AI illustrations."
      • addedInput schema / properties / filters / properties / attribution_required / description
        Added value: +"Filter by whether the license requires attribution. Omit to allow either."
      • addedInput schema / properties / filters / properties / colors / description
        Added value: +"Match any listed dominant color name, for example [\"blue\", \"teal\"]. Images without matching color metadata are excluded."
      • addedInput schema / properties / filters / properties / commercial / description
        Added value: +"Require a commercial-use license when true. Defaults to true when omitted; null removes this filter."
      • addedInput schema / properties / filters / properties / derivatives / description
        Added value: +"Filter by whether the license permits modified or derivative works. Omit to allow either."
      • addedInput schema / properties / filters / properties / format / description
        Added value: +"Allowed file formats, for example [\"jpeg\", \"png\"]. Omit to allow any format."
      • addedInput schema / properties / filters / properties / license_id / description
        Added value: +"Allowed license IDs, for example [\"cc0\", \"cc-by\"]. Omit to allow all licenses compatible with the other filters."
      • addedInput schema / properties / filters / properties / min_height / description
        Added value: +"Minimum image height in pixels. Omit for no height floor."
      • addedInput schema / properties / filters / properties / min_width / description
        Added value: +"Minimum image width in pixels. Defaults to 1000 when omitted; null removes the width floor."
      • addedInput schema / properties / filters / properties / monochrome / description
        Added value: +"Filter by monochrome status. Omit to allow both monochrome and color images."
      • addedInput schema / properties / filters / properties / nsfw_max / description
        Added value: +"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2. Assets without a score can still match."
      • addedInput schema / properties / filters / properties / orientation / description
        Added value: +"Required image orientation. Omit to allow landscape, portrait, and square images."
      • addedInput schema / properties / filters / properties / source / description
        Added value: +"Allowed source IDs from result.source, for example [\"flickr\"]. Omit to search all sources."
      • addedInput schema / properties / filters / properties / year_max / description
        Added value: +"Latest year, inclusive. Use with year_min to bound the date range."
      • addedInput schema / properties / filters / properties / year_min / description
        Added value: +"Earliest year, inclusive. Images without matching year metadata are excluded."
      • addedInput schema / properties / k / description
        Added value: +"Maximum number of final results (1–100, default 10). Fewer results may match the filters; this is separate from candidate-pool sizes."
    • Changedget_image1 field changed
      • addedInput schema / properties / asset_id / description
        Added value: +"Exact asset_id from a Lightdrift search result or previously saved asset (1–255 characters). Pass the ID unchanged, not a file URL."
    • Changedsearch_images25 fields changed
      • addedInput schema / properties / ann_ef / description
        Added value: +"Legacy retrieval tuning parameter (64–4096, default 2048). Accepted for compatibility; leave at the default for the current retrieval service."
      • addedInput schema / properties / ann_k / description
        Added value: +"Maximum semantic-search candidates (1–1000, default 100). Increase for a wider pool; this does not set the final result count."
      • addedInput schema / properties / bm25_k / description
        Added value: +"Maximum keyword-search candidates (0–1000, default 50), combined with ann_k semantic candidates. Set 0 for semantic-only retrieval."
      • addedInput schema / properties / explain / description
        Added value: +"Include retrieval and ranking diagnostics with each result (default false). Use for debugging search quality."
      • addedInput schema / properties / filters / description
        Added value: +"Combine license, source, size, and visual filters. Omitted commercial, ai_generated, and min_width default to true, false, and 1000; set those fields to null to remove their defaults."
      • addedInput schema / properties / filters / properties / ai_generated / description
        Added value: +"Filter by AI-generated status. Defaults to false when omitted; null allows either. False does not exclude non-AI illustrations."
      • addedInput schema / properties / filters / properties / attribution_required / description
        Added value: +"Filter by whether the license requires attribution. Omit to allow either."
      • addedInput schema / properties / filters / properties / colors / description
        Added value: +"Match any listed dominant color name, for example [\"blue\", \"teal\"]. Images without matching color metadata are excluded."
      • addedInput schema / properties / filters / properties / commercial / description
        Added value: +"Require a commercial-use license when true. Defaults to true when omitted; null removes this filter."
      • addedInput schema / properties / filters / properties / derivatives / description
        Added value: +"Filter by whether the license permits modified or derivative works. Omit to allow either."
      • addedInput schema / properties / filters / properties / format / description
        Added value: +"Allowed file formats, for example [\"jpeg\", \"png\"]. Omit to allow any format."
      • addedInput schema / properties / filters / properties / license_id / description
        Added value: +"Allowed license IDs, for example [\"cc0\", \"cc-by\"]. Omit to allow all licenses compatible with the other filters."
      • addedInput schema / properties / filters / properties / min_height / description
        Added value: +"Minimum image height in pixels. Omit for no height floor."
      • addedInput schema / properties / filters / properties / min_width / description
        Added value: +"Minimum image width in pixels. Defaults to 1000 when omitted; null removes the width floor."
      • addedInput schema / properties / filters / properties / monochrome / description
        Added value: +"Filter by monochrome status. Omit to allow both monochrome and color images."
      • addedInput schema / properties / filters / properties / nsfw_max / description
        Added value: +"Maximum recorded NSFW score from 0 to 1; lower is stricter. Defaults to 0.2. Assets without a score can still match."
      • addedInput schema / properties / filters / properties / orientation / description
        Added value: +"Required image orientation. Omit to allow landscape, portrait, and square images."
      • addedInput schema / properties / filters / properties / source / description
        Added value: +"Allowed source IDs from result.source, for example [\"flickr\"]. Omit to search all sources."
      • addedInput schema / properties / filters / properties / year_max / description
        Added value: +"Latest year, inclusive. Use with year_min to bound the date range."
      • addedInput schema / properties / filters / properties / year_min / description
        Added value: +"Earliest year, inclusive. Images without matching year metadata are excluded."
      • addedInput schema / properties / k / description
        Added value: +"Maximum number of final results (1–100, default 10). Fewer results may match the filters; this is separate from candidate-pool sizes."
      • addedInput schema / properties / mode / description
        Added value: +"Ranking mode: visual selects the default relevance reranker; none skips reranking and returns retrieval order. Default visual."
      • addedInput schema / properties / query / description
        Added value: +"Describe the image, subject, scene, or mood to find (1–1000 characters), for example: misty mountains at sunrise."
      • addedInput schema / properties / rerank_k / description
        Added value: +"Maximum candidates to rerank (1–500, default 60); null reranks the whole candidate pool. Ignored when mode is none. Independent of final result count k."
      • addedInput schema / properties / rerank_text / description
        Added value: +"Legacy reranker text toggle (default true). The current service always uses text; leave true."
  3. 3 tool updates
    • First observedfind_similar_images
    • First observedget_image
    • First observedsearch_images

Publisher details

Operator
Lightdrift · Publisher source
Operator website
https://lightdrift.ai
Vendor relationship
First-party · Publisher source
Documentation
https://docs.lightdrift.ai/guides/images-mcp
Trust center
Not available
Restrictions
A Lightdrift account is required. Connect with OAuth or a Lightdrift API key. Each successful image search or similar-image search costs $0.02 in account credits; image metadata retrieval is free. Account rate limits apply. · Publisher source

Related MCP Connectors

Related MCP Servers

  • webfetch

    ashlrai
    A
    license
    A
    quality
    A
    maintenance
    License-first federated image search for AI agents and humans. Exposes MCP tools for concise, attribution-aware image discovery, license probing, and guarded downloads across open, platform, and editorial sources.
    7
    18 npm
    3
    MIT

  • Multimodal MCP

    erickpxd
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables semantic image search using CLIP embeddings and visual question answering through MCP tools, allowing natural language interaction with images.
    -

  • mcp-openverse

    pipeworx-io
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for searching and retrieving Creative-Commons-licensed images and audio from Openverse. Enables AI agents to query open media content.
    2 npm
    MIT

  • Wikimedia-Search-Images

    xiaobenyang-com
    A
    license
    B
    quality
    D
    maintenance
    This MCP server enables AI assistants to search for images on Wikimedia Commons, providing detailed metadata and optional thumbnail combinations to assist AI models in visual comparisons.
    1
    2
    Apache 2.0
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources