AI News 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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| collect_nowA | Collect new Items from every Source now. |
| list_sourcesA | Every Source with its URL, default Categories and collection state. |
| searchA | Search stored Items by text, publish time, Category and Source, in any mix. |
| read_itemA | The full text of an Item: fetches its original page and extracts the main text. |
| whats_newA | What's New: Items collected since the last Checkpoint and published in the last 7 days. |
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 operation: collect_now (force refresh), list_sources (source health), search (stored items query), read_item (full text), whats_new (checkpoint-based new items). The descriptions explicitly carve boundaries, notably between collect_now and whats_new (which auto-collects) and between whats_new and search (which never moves a Checkpoint).
Three of five names follow a verb_noun pattern (collect_now, list_sources, read_item), but `search` is a bare verb and `whats_new` follows no verb_noun convention. Still readable and predictable enough to infer behavior.
Five tools is well within a healthy range and each covers a distinct stage of the workflow: source listing, collection, discovery of new items, search, and full-text retrieval. No redundant or filler tools.
Core lifecycle (collect, inspect sources, find items, read items, checkpoint tracking) is fully covered with no dead ends. Minor gaps: no source management (add/remove/toggle) and no way to undo or reset a Checkpoint, so agents must work around these.