Fed Speech MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FED_SPEECH_DATA_DIR | No | Data storage directory | ./data |
| FED_SPEECH_HTTP_PORT | No | HTTP API server port | 8000 |
| FED_SPEECH_MAX_RETRIES | No | Max retry attempts | 3 |
| FED_SPEECH_HTTP_TIMEOUT | No | HTTP request timeout (seconds) | 30 |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_latest_speechesA | Get the latest Federal Reserve speeches. Returns speeches sorted by publication date, most recent first. |
| get_speeches_by_speakerC | Get Federal Reserve speeches by a specific speaker. Filter by name, role, and date range. |
| get_speeches_by_typeC | Get Federal Reserve speeches by document type (speech, testimony, or prepared_remarks). |
| get_speechA | Get a specific Federal Reserve speech by its document ID. Returns the full speech content and metadata. |
| refresh_speechesC | Fetch new speeches from the Federal Reserve website. This will check RSS feeds and optionally index pages for new content. |
| search_speechesB | Search Federal Reserve speeches by keyword. Searches in title and content. |
| get_speech_statsB | Get statistics about stored Federal Reserve speeches. |
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 7 tools
Each tool has a clearly distinct purpose with no overlap. The tools cover different access patterns (latest, specific, by speaker, by type, statistics, refresh, search) without ambiguity, making it easy for an agent to select the right tool for any query about Federal Reserve speeches.
All tools follow a consistent verb_noun pattern with clear, descriptive names. The naming scheme is uniform throughout (e.g., get_latest_speeches, get_speech, get_speeches_by_speaker), making it predictable and easy to understand the tool's function from its name alone.
With 7 tools, the server is well-scoped for its domain of accessing Federal Reserve speeches. Each tool serves a specific and necessary function, covering retrieval, filtering, statistics, updating, and search operations without being overly sparse or bloated.
The tool set provides complete coverage for the domain, including CRUD-like operations (get, refresh), filtering by various attributes (speaker, type, date), search functionality, and statistical insights. There are no obvious gaps that would hinder an agent from performing typical speech-related tasks.