IQFluence MCP

Search influencers

search_influencers

Read-only

Find influencers by niche, location, size, engagement and audience demographics.

The first 3 results of each search are free; further rows come back hidden (stats without the username) and are revealed only with unlock_search_results for 0.02 credits each. With audience filters every row, hidden ones too, has audience_pct: its audience share in each filtered country, gender, age range and language. Screen candidates by it; a report is not needed for that. Prefer one well-targeted search over many variations. Use get_influencer_report for full analytics on a creator.

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": {
      "platform": "<platform>"
    },
    "name": "search_influencers"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`topic`	No	Niche as hashtags and/or lookalike accounts, e.g. '#fitness' or '@nike'. Plain words become hashtags, which are mostly English: for a niche in another language use keywords. Every extra tag narrows the results, so start with one or two core tags
`offset`	No
`sort_by`	No	Default: relevance with topic, keywords with keywords, otherwise followers
`keywords`	No	Phrase the creator uses in captions (IG/TT) or says in videos (YT)
`language`	No	Creator language: name or ISO code
`platform`	Yes	Social network
`has_email`	No	Only creators with a public email
`locations`	No	Where the creator is based: countries, states or cities by name (any matches). A creator based in a country may have most of the audience elsewhere: to reach a market, use audience_locations
`bio_contains`	No	Phrase in the creator's bio or name
`avg_views_min`	No	Minimum average views per post (TikTok, YouTube)
`followers_max`	No
`followers_min`	No
`verified_only`	No
`creator_gender`	No
`audience_age_to`	No	Audience age range end, e.g. 34
`audience_brands`	No	Instagram only. Brands the audience likes
`audience_gender`	No
`audience_age_from`	No	Audience age range start, e.g. 18
`audience_language`	No	Audience language: name or ISO code
`audience_interests`	No	Instagram only. Audience interest categories, see lookup_filter_values(kind='interest')
`audience_locations`	No	Audience countries/cities by name (any matches)
`audience_age_min_pct`	No	Minimum share of the audience inside the age range
`audience_gender_min_pct`	No
`engagement_rate_min_pct`	No	Minimum engagement rate, percent
`last_posted_within_days`	No	Posted within N days (min 30)
`audience_location_min_pct`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false, openWorld false), and the description goes well beyond them by disclosing the billing/quota model: the first 3 rows are free, further rows return without usernames, and each unlock costs 0.02 credits. That is exactly the kind of cost and gating behavior an agent cannot infer from structured fields.

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 is front-loaded in one sentence, then cost behavior, then the screening rule and the sibling alternative. Every sentence does work, though the inserted line breaks make it read as a flat block and the audience_pct explanation is denser than it needs to be.

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 27-parameter search tool with no output schema and safe annotations, the definition covers the two things an agent would otherwise get wrong: why most rows look anonymous and how to widen without spending credits. It stops short of explaining pagination against the free/unlocked cutoff, which would matter for a large result set.

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 67% schema coverage the schema carries most parameter documentation, but the description adds meaning it does not: that audience filters change the payload for every row (audience_pct for country, gender, age and language) and that this field is the screening signal. It does not explain pagination (offset/limit) or how sorting interacts with keywords versus topic, which is the remaining gap.

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 plus the filter dimensions it searches on (niche, location, size, engagement, audience demographics), which is exactly what an agent needs to distinguish it from get_influencer_report and compare_influencers. The name, title and first sentence agree, and the scope is unambiguous.

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 routes the agent: screen with audience_pct instead of pulling a report, use get_influencer_report for full analytics, use unlock_search_results to reveal hidden rows, and prefer one well-targeted search over many variations. These are concrete when/when-not statements plus named alternatives, not implied usage.

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

All IQFluence MCP tools Inspect

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

Need Help?