Feedbagel MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FEEDBAGEL_API_KEY | Yes | API key for Feedbagel, minted at https://feedbagel.com/dashboard/keys with 'Agent' scope. | |
| FEEDBAGEL_API_BASE | No | Base URL for the Feedbagel API. Defaults to production. | https://api.feedbagel.com |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_subscriptionsA | [read] Unified list of the user's feed follows and webhook subscriptions. Each item is tagged kind: 'follow' or 'webhook'. |
| follow_feedA | [write] Add a feed to the user's follow list. Idempotent. Counts against the subscription cap. |
| unfollow_feedB | [write] Remove a feed from the user's follow list. |
| list_webhooksA | [read] List all webhook subscriptions owned by the user. |
| create_webhookA | [write] Create a webhook subscription. The response includes webhook_secret ONCE; the bot must persist it for HMAC validation. Counts against the subscription cap. |
| delete_webhookA | [write] Delete a webhook subscription and all its feed attachments. |
| pause_webhookA | [write] Pause deliveries for a webhook subscription. Existing attachments stay; the poller skips this subscriber until resumed. |
| resume_webhookA | [write] Resume deliveries for a paused webhook subscription. |
| attach_feed_to_webhookA | [write] Attach a feed to a webhook subscription so its new entries get delivered. |
| detach_feed_from_webhookB | [write] Stop delivering a feed's entries to a webhook subscription. |
| meA | [read] Return the authenticated account's email, plan, and status. Use as a smoke test before other calls. |
| search_feedsA | [read] Search the feed catalog by keyword. Matches feed titles, urls, and hostnames. Returns up to 20 results with recency stats. |
| search_feeds_by_urlA | [read] Find feeds at a specific hostname or URL fragment. Use this when the user already knows the site (e.g. 'theverge.com') and wants its feeds. |
| get_host_metadataB | [read] Get metadata (title, description, favicon, feed list) for a host domain. |
| list_entriesA | [read] List recent entries across all feeds, paginated. Use sort_by='published' (default) for newest first. |
| get_entryB | [read] Fetch a single entry by numeric id. |
| get_entry_by_slugA | [read] Fetch a single entry by its URL slug (matches /post/ on the site). |
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 17 tools
Each tool targets a distinct action or resource (e.g., feed follow/unfollow, webhook CRUD, entry retrieval, search variants). The two search tools are differentiated by search method (keyword vs URL), and webhook state management tools (pause/resume) are clearly separate from creation/deletion.
All tool names follow a consistent verb_noun pattern (e.g., follow_feed, create_webhook, get_entry), with some longer phrases like attach_feed_to_webhook that remain predictable. No mixing of camelCase or inconsistent verb styles.
With 17 tools, the set is slightly above the typical 3-15 range but still well-scoped for a feed/webhook management server. Each tool serves a clear purpose, and none feel superfluous.
Core workflows are covered: feed following/unfollowing, webhook creation/deletion/pause/resume, entry retrieval, and search. Minor gaps exist (e.g., no webhook update, no feed creation), but they do not severely hinder typical use cases.