Skip to main content
Glama

Search UGC Database

search_ugc_database
Read-onlyIdempotent

Instantly browse the UGC Database: tens of thousands of already-sourced, email-verified Instagram and TikTok creators, with filters for niche, followers, country, state/region, city, language, gender, estimated age, email type, signals (ugc, portfolio, collabs, proven, for_hire), brands worked with, hit rate, median views, creator type, services, portfolio type, content style (on camera, setting, production), brand saturation and stated rate (max_rate_usd). Proven UGC: each creator's proven lists brands they verifiably made UGC for (videos, median and best views) and performance gives their hit rate (share of posts past 10K / 100K views); to hire creators whose UGC already hit, use signals=['proven'] or brands, plus min_hit_rate, and sort='proven' or 'hit_rate'. Stated rates: rate_min_usd (from $X per UGC video, in USD) and rates (item, price, currency, usd, unit) are the creator's own prices from their rate card or portfolio page (self-published, not verified; say so when you quote them), with turnaround_days and portfolio_brands (past clients the page lists, also in claimed_brands and brands_worked); for a budget use max_rate_usd and sort='rate_asc'. Proof post URLs, sample_videos and portfolio_pages stay hidden until unlocked. No search run and no charge; emails stay masked until unlocked. Try this before run_ugc_agent when the user wants creators fast. Pass creator_id to get one creator's full profile. Use unlock_ugc_database_creators to reveal emails, proof posts and sample videos.

Input Schema

NameRequiredDescriptionDefault
uidNoOptional Firebase uid. Must match the URL uid unless local fallback is enabled.
sortNofit (default); proven = verified UGC brand work first; hit_rate = share of posts past 10K views; median_views = median views per post; rate_asc = lowest stated UGC video rate first (creators without one last).
viewNoall (default), net_new = not yet delivered to the user, unlocked = already unlocked.
limitNoPage size, 1-100 (default 25).
queryNoWord-prefix search over handle, name, niche, labels and bio ('ugc' matches kit.ugc).
tiersNostarter 0-999, nano 1k-9,999, micro 10k-99,999, mid 100k-499,999, macro 500k+ followers.
brandsNoWorked with any of these brands ('Poppi', 'Cal AI'), verified (proven) or named in their bio; case-insensitive. get_ugc_database_facets lists brand names.
citiesNoCities the creator says they are based in, English names ('Austin', 'London', 'Mexico City'); case-insensitive. Combine with countries to disambiguate.
cursorNoThe next_cursor from the previous page. Keep the other filters identical.
nichesNoNiche labels or keys; use get_ugc_database_facets for valid values.
gendersNo
regionsNoStates or regions the creator says they are based in, English names ('Texas', 'England', 'Ontario'); case-insensitive. Combine with countries to disambiguate. get_ugc_database_facets lists valid values.
signalsNoAll must match: ugc wording, portfolio link, brand collabs, engagement stats, untapped (no other brand got this creator), proven (verified UGC made for at least one brand, with proof posts), for_hire (says they take paid UGC work), has_rates (publishes their own rates on a rate card or portfolio page).
servicesNoOffers any of these services.
settingsNoWhere their recent posts are usually filmed.
age_bandsNoEstimated age band from profile photos and bio (an estimate, not a verified age); unknown = not estimated.
countriesNoISO alpha-2 codes (GB is read as UK), or 'unknown'.
languagesNo
on_cameraNoAppears on camera in recent posts (no = faceless).
platformsNo
creator_idNoA database creator id to fetch one creator. Filters are ignored.
email_kindsNo
productionsNoProduction style of recent posts.
saturationsNoHow many brands they already work with: fresh 0, low 1-2, medium 3-5, high 6+.
bearer_tokenNoOptional Firebase ID token. Hosted clients normally authenticate with an API key header or ?uid= in the URL instead.
max_rate_usdNoBudget cap in USD: only creators whose lowest stated UGC video rate (rate_min_usd) is at or below this. Creators who state no rate are excluded. Rates are self-published by the creator, not verified.
min_hit_rateNoMinimum hit rate: share of the creator's posts with 10,000+ views, as a 0-1 fraction (0.25 = 25%). Creators without post metrics are excluded.
creator_typesNoAccount type; ugc_creator and both are creators who make UGC for brands.
max_followersNo
min_followersNo
exclude_nichesNo
portfolio_typesNoWhere the creator keeps their portfolio, from their links.
min_median_viewsNoMinimum median views per post.
added_within_daysNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations by disclosing cost ('No search run and no charge'), data masking ('emails stay masked until unlocked', proof post URLs/sample_videos/portfolio_pages hidden), and data provenance ('self-published, not verified; say so when you quote them'). It also explains what `proven` and `performance` actually contain, which no annotation covers.

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?

Purpose and the key differentiator are front-loaded, and the three paragraphs map to browse / proven / rates concerns. It is dense and long, and the rate-card sentence packs several field names into one clause, but no sentence is filler.

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?

For a 34-parameter, zero-required search tool with no output schema, the description covers the essentials an agent needs: cost, privacy/masking, the recommended fast path, the unlock follow-up, and the shape of the returned creator fields. Pagination via cursor is left to the schema, which documents it adequately.

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 34 parameters at 76% schema coverage, the description adds real value by explaining how filters combine and which sort to pair with which filter (max_rate_usd + sort='rate_asc', min_hit_rate + sort='hit_rate'). It also defines return-side fields (rate_min_usd, rates, turnaround_days, portfolio_brands) that the schema only names. It does not touch many remaining filters (view, tiers, saturations, settings), so it is additive but not exhaustive.

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?

Opens with a specific verb and resource ('browse the UGC Database') and immediately scopes it: tens of thousands of email-verified Instagram and TikTok creators with a named filter set. It is clearly distinguishable from siblings like run_ugc_agent (slower agentic path), unlock_ugc_database_creators (reveals hidden fields), and get_ugc_database_facets (facet lookup).

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?

Explicit routing: 'Try this before run_ugc_agent when the user wants creators fast' and 'Use unlock_ugc_database_creators to reveal emails, proof posts and sample videos.' It also states the single-creator mode ('Pass creator_id to get one creator's full profile') and gives concrete filter recipes ('signals=[\'proven\'] or brands, plus min_hit_rate, and sort=\'proven\' or \'hit_rate\'').

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources