{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4repjfn3nqn2","handle":"iflow-mcp-rajeevchandra-client-server","url":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server","links":{"self":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server/record.json","html":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server","markdown":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-rajeevchandra-client-server","status":"https://wellknown.network/api/v1/agents/iflow-mcp-rajeevchandra-client-server/status","claim":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-rajeevchandra-client-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-rajeevchandra-client-server/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-rajeevchandra-client-server/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-rajeevchandra-client-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp-rajeevchandra-client-server","summary":"MCP Server example with add and multiply tools","description":"# MCP + Ollama Local Tool Calling Example\n\nThis project demonstrates how a local AI agent can **understand user queries** and **automatically call Python functions** using:\n\n- Model Context Protocol (**MCP**)\n- **Ollama** for running a local LLM (e.g., Llama3)\n- **Python** MCP Client and Server\n\n---\n\n## 🔗 Sequence Diagram\n\n```mermaid\nsequenceDiagram\n    participant User\n    participant MCP_Client\n    participant Ollama_LLM\n    participant MCP_Server\n\n    User->>MCP_Client: 1) User types: \"What is 5 + 8?\"\n    MCP_Client->>Ollama_LLM: 2) Send available tools + user query\n    Ollama_LLM->>Ollama_LLM: 3) Understand query & tool descriptions\n    Ollama_LLM->>Ollama_LLM: 4) Select tool: add(a=5, b=8)\n    Ollama_LLM->>MCP_Client: 5) Return tool_call\n    MCP_Client->>MCP_Server: 6) Execute add(a=5, b=8)\n    MCP_Server-->>MCP_Client: 7) Return result: 13\n    MCP_Client-->>User: 8) Show final answer: 13\n```\n\n---\n\n## 📚 Project Structure\n\n```\n.\n├── math_server.py      # MCP Server exposing add() and multiply() tools\n├── ollama_client.py    # MCP Client interacting with Ollama\n├── README.md           # Project documentation\n```\n\n---\n\n## 🛠️ Setup Instructions\n\n### 1. Install Requirements\n\n```bash\npip install \"mcp[cli] @ git+https://github.com/awslabs/mcp.git\" openai==0.28 httpx\n```\n\nMake sure you have **Ollama installed** and running.\n\n### 2. Pull or run an LLM model\n\n```bash\nollama run llama3\n```\n\n(Ensure the model you run supports tool calling.)\n\n### 3. Run the MCP Server\n\n```bash\npython math_server.py\n```\n\nThe server exposes two simple tools:\n- `add(a: int, b: int) -> int`\n- `multiply(a: int, b: int) -> int`\n\n### 4. Run the MCP Client\n\n```bash\npython ollama_client.py math_server.py\n```\n\n### 5. Interact!\n\nExample queries:\n\n```\nQuery: What is 5 + 8?\nResponse: 13\n\nQuery: Multiply 7 and 9\nResponse: 63\n```\n\nThe MCP client sends the query and available tools to Ollama. The LLM internally decides which tool to use based on the tool descriptions and user intent.\n\n---\n\n## 🚀 How It…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp-rajeevchandra-client-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"code.documentation","name":"Code Documentation","confidence":0.848,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["code","dev"],"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-rajeevchandra-client-server","registry":"pypi","observedAt":"2026-09-15T19:23:36.562Z","publishedAt":"2026-01-30T05:22:52.288198Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp-rajeevchandra-client-server","url":"https://pypi.org/project/iflow-mcp-rajeevchandra-client-server/","firstSeenAt":"2026-09-09T20:25:24.925Z","fetchedAt":"2026-09-15T19:23:00.797Z","normalizedAt":"2026-09-15T19:23:00.797Z"}]},"firstSeenAt":"2026-09-09T20:25:24.925Z","updatedAt":"2026-09-15T19:23:36.562Z"}