MCP + CrewAI Agentic Integration
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | Yes | API Key for Groq to power the LLM engine (Llama 3.1). | |
| SERPER_API_KEY | Yes | API Key for Serper (Google Search API) used for news retrieval. | |
| WEATHER_API_KEY | Yes | API Key for WeatherAPI to access real-time meteorology data. | |
| AGENTOPS_API_KEY | Yes | API Key for AgentOps for observability, tracing, cost management, and debugging. |
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 |
|---|---|
| add_noteB | Append a new note to the note file. Args: message (str): The note content to be added. Returns: str: Confirmation message indicating the note was saved. |
| search_newsB | Fetch search results from Google News via Serper |
| fetch_weatherB | Fetch current weather for a city |
| read_notesB | Read and return all notes from the note file. Returns: str: All notes as a single string separated by line breaks. If no notes exist, a default message is returned. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| note_summary_prompt | Generate a prompt asking the AI to summarize all current notes. Returns: str: A prompt string that includes all notes and asks for a summary. If no notes exist, a message will be shown indicating that. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_latest_note | Get the most recently added note from the note file. Returns: str: The last note entry. If no notes exist, a default message is returned. |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: add_note and read_notes handle note management, fetch_weather retrieves weather data, and search_news fetches news results. There is no overlap in functionality, making tool selection straightforward for an agent.
The tool names follow a consistent verb_noun pattern (add_note, fetch_weather, read_notes, search_news), which is predictable and readable. The minor deviation is that 'fetch_weather' and 'search_news' use different verbs ('fetch' vs. 'search'), but the overall pattern remains clear.
With only 4 tools, the set feels thin for a server named 'MCP + CrewAI Agentic Integration', which suggests broader agentic capabilities. While the tools cover basic utilities (notes, weather, news), the scope seems limited compared to the implied integration purpose, bordering on under-scoped.
Inferring the domain as agentic integration utilities, there are significant gaps: no tools for agent coordination, task management, or data processing beyond simple fetches. The note tools lack update/delete operations, and overall coverage is incomplete for enabling complex agent workflows.