jev-kol-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEV_MODEL | No | Jev model to use (default: jev-latest) | jev-latest |
| FETCH_LIMIT | No | Number of matching profiles to request from Apify (default: 12) | 12 |
| JEV_API_KEY | No | TypeSafe Jev API key for niche labeling, fit scoring, and email drafting | |
| APIFY_API_TOKEN | No | Apify API token for searching TikTok and YouTube creators |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_kolsA | Search micro-KOLs by platform, niche, and follower range. Reads the local SQLite cache first. If that is thin and the community pool is enabled, reads the shared pool next. Otherwise calls Apify and passes the follower range to the actor. Fresh profiles are labeled with Jev before they are stored. They are uploaded only when sharing is on. A missing APIFY_API_TOKEN returns setup guidance and does not exit the process. |
| score_fitA | Ask Jev System One to judge niche, tone, price band, and whether outreach is worth sending. A missing JEV_API_KEY returns setup guidance. |
| draft_emailA | Draft a first collaboration email and a follow-up for day 3. A missing JEV_API_KEY returns setup guidance. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct stage of the outreach workflow: searching candidates, scoring their fit, and drafting emails. No two tools could plausibly be confused for one another.
All tool names follow a consistent snake_case verb_noun pattern (search_kols, score_fit, draft_email). The pattern is uniform and predictable.
Three tools is well-scoped for a focused micro-KOL outreach server. Each tool serves a clear purpose in the pipeline without redundancy or bloat.
The search→score→draft workflow covers the core outreach preparation lifecycle. Minor gaps exist such as no tool to manage saved KOLs or actually send emails, but these are outside the apparent scope.