Crewai-MCP
Build an MCP agent using Crewai
Workflow of MCP powered Crewai RStudy Assistant
graph TD
%% User Interface Layer
A["🌐 User Interface<br/>Streamlit App<br/>(streamlit_app.py)"] --> B["⚙️ API Layer<br/>main_api.py"]
%% API Processing
B --> C["🚀 Subprocess Call<br/>python main.py {topic}"]
%% CrewAI Core
C --> D["🤖 CrewAI Application<br/>(main.py)<br/>Research Agent + Writer Agent"]
%% MCP Protocol Communication
D --> E["📡 MCP Protocol<br/>Model Context Protocol<br/>Communication Layer"]
%% MCP Servers
E --> F["🔍 Search MCP Server<br/>(servers/search_server.py)<br/>Python Implementation"]
E --> G["🎨 Image MCP Server<br/>(servers/image_server.py)<br/>Python Implementation"]
E --> H["📁 Filesystem MCP Server<br/>(NPX - Disabled)<br/>Node.js v14 Issue"]
%% External APIs
F --> I["🦁 Brave Search API<br/>Web Search Results"]
G --> J["🎭 Segmind API<br/>AI Image Generation"]
%% File Output Generation
D --> K["📄 File Generation"]
K --> L["📊 search_results.json<br/>Search Data"]
K --> M["📝 summary.txt<br/>Research Summary"]
K --> N["🖼️ generated_images/<br/>AI Generated Images"]
%% Result Processing
B --> O["🔄 Result Extraction<br/>File Detection & Parsing"]
O --> P["📋 Summary Extraction<br/>Multiple Pattern Recognition"]
O --> Q["🔍 Search Results Parsing<br/>JSON Processing"]
O --> R["🖼️ Image Collection<br/>File Listing"]
%% Display Results
P --> S["📑 Summary Tab<br/>Streamlit Display"]
Q --> T["🔍 Search Results Tab<br/>Streamlit Cards"]
R --> U["🎨 Generated Images Tab<br/>Streamlit Gallery"]
%% User Features
S --> V["💾 Download Summary<br/>Text File"]
U --> W["💾 Download Images<br/>ZIP Archive"]
%% System Monitoring
A --> X["📊 System Status<br/>MCP Server Health Check"]
%% Styling for different component types
classDef streamlit fill:#ff6b6b,stroke:#ff5252,stroke-width:3px,color:#fff
classDef crewai fill:#4ecdc4,stroke:#26a69a,stroke-width:3px,color:#fff
classDef mcp fill:#45b7d1,stroke:#039be5,stroke-width:3px,color:#fff
classDef api fill:#96ceb4,stroke:#66bb6a,stroke-width:3px,color:#fff
classDef files fill:#feca57,stroke:#ff9800,stroke-width:3px,color:#fff
%% Apply styles
class A,S,T,U,V,W,X streamlit
class D crewai
class E,F,G,H mcp
class I,J api
class K,L,M,N,O,P,Q,R files
class B,C streamlit
🏗️ Architecture Breakdown
📱 Frontend Layer
- streamlit_app.py - Main web interface with beautiful UI
- streamlit_app_backup.py - Backup version for safety
🔄 API & Integration Layer
- main_api.py - Bridge between Streamlit and CrewAI
- app.py - Alternative interface implementation
🤖 AI Core Layer
- main.py - CrewAI agents (Research + Writer)
- debug_summary.py - Summary extraction utilities
📡 MCP Server Layer
- servers/search_server.py - Web search via Brave API
- servers/image_server.py - Image generation via Segmind API
📊 Data Storage Layer
- servers/search_results/ - JSON files with search data (40+ topics)
- servers/images/ - Generated AI images (30+ visuals)
⚙️ Configuration & Utilities
- requirements.txt - Dependencies management
- setup_nodejs.py - Environment setup
- test_python_version.py - Compatibility testing
Run the Application without the UI
python main.py
Run the Application using streamlit
# Launch Streamlit app
streamlit run streamlit_app.py
Streamlit Interface
Metadata
Release files for iflow-mcp_plaban1981-crewai-search 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_plaban1981_crewai_search-0.1.0.tar.gz | 40.3 MB | Without provenance | Details for iflow_mcp_plaban1981_crewai_search-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_plaban1981_crewai_search-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_plaban1981_crewai_search-0.1.0-py3-none-any.whl |
Total release size: 80.7 MB
Release files / iflow_mcp_plaban1981_crewai_search-0.1.0.tar.gz
| Download URL | iflow_mcp_plaban1981_crewai_search-0.1.0.tar.gz |
|---|---|
| Size | 40.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2c82f15c5fc7e98f5354b0792c28af500f1fb39da94668a59a09a2c42d2ee88e
|
|
BLAKE2b-256 checksum How to use checksums |
758af4c55339cbb2bf0f8de35d1352e53a5c1db92cbc4019dbe57265d8bd2992
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_plaban1981_crewai_search-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_plaban1981_crewai_search-0.1.0-py3-none-any.whl |
|---|---|
| Size | 40.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d4fe13f202545ad5c9956a3be5931afd073b99b79da48a4defa2c792a11719ac
|
|
BLAKE2b-256 checksum How to use checksums |
dd09e7e365df5a63818eb9565e40a53f85565b802485a6772556f3133383969a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_plaban1981-crewai-search 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.