{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_vzsd6addzuwv","handle":"iflow-mcp-joshualelon-deep-research-mcp","url":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-joshualelon-deep-research-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-joshualelon-deep-research-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-joshualelon-deep-research-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-joshualelon-deep-research-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-joshualelon-deep-research-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-joshualelon-deep-research-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_joshualelon-deep-research-mcp","summary":"A multi-agent research framework using Python and MCP (Message Control Protocol)","description":"# Deep Research MCP\n\nThis repository provides a multi-agent research framework using Python and MCP (Message Control Protocol). The default entrypoint is `mcp_server.py`, which sets up a FastMCP server named **Deep Research** and exposes a tool named `deep_research`.\n\n## Setup\n\n1. **Clone the Repository:**\n   ```bash\n   git clone https://github.com/yourusername/deep-research-mcp.git\n   cd deep-research-mcp\n   ```\n\n2. **Create/Populate Your `.env` File:**\n   ```bash\n   cp .env.example .env\n   # Then edit the new .env file to fill in your secrets and environment variables\n   # For example:\n   # OPENAI_API_KEY=sk-123-yourkey\n   # Additional environment variables can be placed here\n   ```\n\n3. **Install Dependencies:**\n   ```bash\n   pip install -r multi_agents/requirements.txt\n   ```\n\n4. Edit your `claude_desktop_config.json` file to include the following:\n    ```\n    {\n        \"mcpServers\": {\n            \"deep-research-mcp\": {\n                \"command\": \"path/to/your/python/interpreter\",\n                \"args\": [\n                    \"/path/to/this/project/deep-research-mcp/mcp_server.py\"\n                ]\n            }\n        }\n    }\n    ```\n\n5. **Run the MCP Server:**\n   ```bash\n   python mcp_server.py\n   ```\n   This starts the FastMCP tool server locally. From here, any MCP-compatible client or the CLI can invoke the `deep_research` tool.\n\n## Project Overview\n\n- **multi_agents**  \n  - **agents**: Contains the various AI agents (ResearchAgent, EditorAgent, etc.).  \n  - **memory**: Typed dictionaries to store research and draft states.  \n  - **main.py**: Core logic to load tasks and orchestrate agents.  \n  - **README.md**: Additional instructions on usage, file output settings, etc.\n- **mcp_server.py**: Main FastMCP server file (entrypoint).\n- **utils**: Shared functions and enums used across the codebase.\n- **.gitignore**, **requirements.txt**, etc.: Standard setup files.\n\nBelow is a copy of the `multi_agents/README.md` in a tree-like structure for reference:\n\n```\nmu…","publisher":null,"homepage":"https://github.com/JoshuaLelon/deep-research-mcp","repository":"https://github.com/JoshuaLelon/deep-research-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_joshualelon-deep-research-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"research.web","name":"Deep Web Research","confidence":1,"provenance":"derived"}],"categories":["dev","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_joshualelon-deep-research-mcp","registry":"pypi","observedAt":"2026-11-03T07:25:47.753Z","publishedAt":"2026-02-11T22:43:31.073075Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_joshualelon-deep-research-mcp","url":"https://pypi.org/project/iflow-mcp_joshualelon-deep-research-mcp/","firstSeenAt":"2026-09-09T19:24:19.427Z","fetchedAt":"2026-11-03T07:23:57.553Z","normalizedAt":"2026-11-03T07:23:57.553Z"}]},"firstSeenAt":"2026-09-09T19:24:19.427Z","updatedAt":"2026-11-03T07:25:47.753Z"}