intelligence-hub-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_intelligence_feedA | Fetches the latest intelligence items across configured feeds (RSS, HN, arXiv) and saves them to LanceDB. Args: category: Optional category filter. limit_per_channel: Optional items per channel override. force_fetch: If True, forces fetch regardless of interval_hours. |
| search_intelligenceB | Searches stored intelligence records using semantic vector search in LanceDB. |
| list_intelligence_recordsB | Lists stored intelligence records with optional category or serendipity filtering. |
| generate_crossover_digestB | Generates an interdisciplinary crossover report combining 80% core tracking and 20% serendipity with WIRED-style narrative Markdown. |
| get_feed_statusA | Returns the current registry of feed channels and LanceDB storage statistics. |
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 5 tools
Each tool targets a distinct action: fetching, searching, listing, digesting, and status reporting. Search and list both retrieve stored records but are differentiated by semantic search versus filtered listing, so there is only minor potential confusion.
All five tools follow a consistent verb_noun pattern with underscore separators (fetch_, search_, list_, generate_, get_). No mixed conventions or ambiguous generic verbs.
Five tools is well-scoped for an intelligence aggregation hub. Each tool serves a clear part of the workflow without redundancy or bloat.
The set covers the core workflow: ingest, retrieve, search, synthesize, and monitor. Missing explicit update/delete operations and feed management are minor gaps since records are likely immutable and feeds may be configured externally.