Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Flickr photos

flickr_photos_search
Read-onlyIdempotent

Search Flickr photos by text, tags, dates, licence, media, user or place to find matching images. Filter by geo, upload or taken windows and license type, with cursor pagination.

Instructions

Search Flickr photos by text, tags, dates, licence, media, user or place. Optional inputs: cursor, page, limit, query, tags and 13 more. Returns a list (use cursor when paginated).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "flickr_photos_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, 1-based. Default: 1. A page past the last returns an empty list with `hasMore: false`. Prefer `cursor` when continuing.
sortNoOrder. Default: relevance. For a taken window use `date-taken-asc` or `date-taken-desc`: pages end as soon as the window is passed. Newest-first sorts can repeat a row; `uploadedFrom`/`uploadedTo` give a stable walk.
tagsNoSpace- or comma-separated tags.
limitNoRows per page, 1 to 100. Default: 100.
mediaNoRestrict results to `photos` or `videos`.
queryNoFree text to match photo titles, descriptions or tags.
cursorNoCursor from `page.nextCursor` of the previous response. It only works with the same filters. Send it without `page`; it keeps the page size it was issued with, so `limit` may be sent again and has no effect.
hasGeoNoOnly geotagged photos.
radiusNoRadius in kilometres for a geo search.
userIdNoOnly this user photos.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
licenseNoLicence ids, comma-separated. `0` all rights reserved; `1` to `6` and `11` to `16` Creative Commons; `7` no known copyright; `8` US government work; `9` and `10` public domain.
tagModeNoWhether every tag or any tag must match. Default: all.
takenToNoLatest taken time as in `dates.takenAt`, ISO 8601 or a date (00:00; use `2024-01-31T23:59:59` for a whole day). A time zone or offset is ignored. Pages can hold fewer rows than `limit`.
latitudeNoLatitude for a geo search.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
longitudeNoLongitude for a geo search.
takenFromNoEarliest taken time as in `dates.takenAt`, ISO 8601 or a date (00:00). A time zone or offset is ignored. Before `takenTo`. Pages can hold fewer rows than `limit`; sort by taken date to end paging at the window.
uploadedToNoLatest upload time, ISO 8601 or a date. A date-only value means 00:00 UTC on that day; to include the whole day, pass a full time such as `2024-01-31T23:59:59Z`.
uploadedFromNoEarliest upload time, ISO 8601 or a date. A date-only value means 00:00 UTC on that day.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered elsewhere. The description adds only that the result is a list and that pagination should be continued with a cursor. It says nothing about result volume, rate limits or how filters interact, so the addition beyond annotations is modest.

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?

Two short sentences with the capability front-loaded and the pagination hint trailing, which is the right order. The phrase 'and 13 more' is low-value filler that an agent cannot act on, but the overall size is well matched to a 21-parameter 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 tool with 21 parameters and no output schema, the description covers the search surface and the pagination contract but omits the two required parameters (context and llm_model) that every call must supply. Return shape is described only as 'a list'. Adequate but with clear gaps for a tool of this complexity.

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 100%, so every parameter including cursor, sort and the date windows is already explained in the schema. The description merely names a few parameters and says 'and 13 more', which adds no meaning beyond what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource ('Search Flickr photos') and enumerates the dimensions that can be searched: text, tags, dates, licence, media, user, place. An agent can immediately tell this is a filtered photo search. It stops short of differentiating itself from lookalike siblings such as flickr_users_photos_search or flickr_tags_photos_list, which is the only thing keeping it off a 5.

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 only implied by the filter list; there is no explicit statement of when to prefer this over the user-scoped, tag-scoped or group-scoped photo tools. The one concrete piece of guidance is pagination ('use cursor when paginated'), which is a calling convention rather than a tool-selection rule. No exclusions or prerequisites are given.

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

Deploy Server

Other Tools