Influship

semantic_search_creators

Read-only

Semantic discovery search for influencers/content creators using natural-language queries.

Use this only when the user asks to discover creators by topic, audience, geography, niche, content style, or campaign criteria (e.g., "fitness creators in NYC", "vegan recipe creators with high engagement", "tech reviewers who cover phones"). The query is matched against creator profiles, extracted facts, and visual style via hybrid vector search.

Do not use this for exact handles, usernames, or known creator names. If the user gives a specific platform and handle (for example "@niickjackson on Instagram"), use get_profile first. For rough name/handle lookup, use search_creators. For multiple known handles, use lookup_profiles. Semantic search can return lookalike or topical matches and is allowed to miss an exact username.

Examples:

User: "Find news creators with 1M+ followers" -> use this tool.
User: "Find creators in LA who make cinematic travel videos" -> use this tool.
User: "Pull @niickjackson on Instagram" -> use get_profile, not this tool.
User: "Is @niickjackson a fit for Pixel?" -> use get_profile first, optionally get_posts, then match_creators.

Returns a ranked list of creators (id, platform, username, follower count, engagement rate, top categories, evidence facts). Use the flat follower, engagement-rate, and verified fields to constrain results when the user gives concrete numeric constraints.

Use find_lookalike_creators instead when you want creators SIMILAR to known ones. Use match_creators when you want to SCORE specific creators against a brief.

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": {
      "query": "<query>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "semantic_search_creators"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum results to return.
`query`	Yes	Natural-language semantic discovery query by topic, niche, audience, geography, or content style. Do not pass exact handles or usernames here; use get_profile, lookup_profiles, or autocomplete_creators instead.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`verified`	No	When set, only return verified or unverified creators.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`platforms`	No	Platforms to search. Omit for all.
`creator_kinds`	No	Optional creator kind filter. Omit for no creator-kind filter.
`max_followers`	No	Maximum follower count.
`min_followers`	No	Minimum follower count.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.
`max_engagement_rate`	No	Maximum engagement rate as a percentage from 0 to 100.
`min_engagement_rate`	No	Minimum engagement rate as a percentage from 0 to 100.

Output Schema

Name	Required	Description	Default
`ok`	No
`data`	No
`count`	No
`results`	No
`has_more`	No
`not_found`	No
`next_cursor`	No
`suggested_followups`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 5, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "query"
-]New value: +[
+  "query",
+  "context",
+  "llm_model"
+]

Changed2 schema fields changedOct 23, 2026
- removedOutput schema / properties / next_cursor / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / next_cursor / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedMay 28, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld/destructive=false, and the description adds real behavioral context: hybrid vector matching, the fact that results can be lookalike or topical, and the accepted failure mode of missing an exact username. It also discloses the return shape (id, platform, username, followers, engagement rate, categories, evidence facts). It does not cover pagination or result-set size behavior, keeping it at 4.

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 primary when-not routing are front-loaded before the examples, which is good structure. The four-bullet example block plus a separate returns paragraph makes it longer than strictly necessary for an agent already given a fully documented schema.

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?

Covers selection criteria, exclusions, alternatives, matching mechanism, and result contents for a 12-parameter discovery tool; an output schema exists, so the brief return summary is a bonus rather than a gap.

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 baseline is 3; the description goes beyond it by explaining how to use the flat follower, engagement-rate, and verified filters for concrete numeric constraints. The analytics-only params (context, llm_model, conversation_id) are left to the schema, which documents them 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 verb+resource+mechanism: 'Semantic discovery search for influencers/content creators using natural-language queries', and immediately clarifies it matches against profiles, extracted facts, and visual style via hybrid vector search. It is clearly distinguished from name/handle lookup siblings.

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 when-to-use criteria (topic, audience, geography, niche, content style, campaign criteria), explicit when-not (exact handles, usernames, known names), and named alternatives for each case: get_profile, search_creators, lookup_profiles, find_lookalike_creators, match_creators. Worked examples reinforce the routing.

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

All Influship 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.