{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_wnh7rwwa35sw","handle":"splitwise-mcp-2","url":"https://wellknown.network/agents/splitwise-mcp-2","links":{"self":"https://wellknown.network/agents/splitwise-mcp-2/record.json","html":"https://wellknown.network/agents/splitwise-mcp-2","markdown":"https://wellknown.network/agents/splitwise-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/splitwise-mcp-2","status":"https://wellknown.network/api/v1/agents/splitwise-mcp-2/status","claim":"https://wellknown.network/agents/splitwise-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/splitwise-mcp-2/claim.json","badge":"https://wellknown.network/agents/splitwise-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/splitwise-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/splitwise-mcp-2/tools"},"ard":{"identifier":"urn:air::server:splitwise-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"splitwise-mcp","summary":"MCP server for Splitwise integration with AI-powered voice expense logging","description":"# Splitwise MCP Server\n\n[![MCP](https://img.shields.io/badge/MCP-Enabled-blue)](https://modelcontextprotocol.io)\n[![PyPI](https://img.shields.io/pypi/v/splitwise-mcp)](https://pypi.org/project/splitwise-mcp/)\n\nA Model Context Protocol (MCP) server that integrates with [Splitwise](https://splitwise.com). Connect your AI assistant (Claude, Cursor, etc.) to manage Splitwise expenses using natural language — with voice support!\n\n## How It Works\n\n```mermaid\nflowchart LR\n    Client[Claude / Cursor] -->|MCP| Server[splitwise-mcp]\n    Server -->|audio| Deepgram[Deepgram STT]\n    Deepgram -->|text| Gemini[Gemini 3 Flash]\n    Gemini -->|action| Splitwise[Splitwise API]\n```\n\n## Features\n\n| Tool | Description |\n|------|-------------|\n| `voice_command` | Send audio → Deepgram transcribes → Gemini processes → Splitwise executes |\n| `text_command` | Send text → Gemini processes → Splitwise executes |\n| `add_expense` | Add expenses with support for groups, percentages, exclusions, and specific payers |\n| `delete_expense` | Delete an expense by ID |\n| `list_friends` | List your Splitwise friends |\n| `configure_splitwise` | Configure API credentials |\n| `login_with_token` | Login with OAuth2 token |\n\n**Smart Name Matching**: If Deepgram transcribes \"Humeet\" but your friend is \"Sumeet\", Gemini will ask for clarification instead of guessing.\n\n### Advanced Splits\n- **Percentages**: \"Split 40% for me and 60% for Alice\"\n- **Groups**: \"Add to Apartment group\" (Auto-fetches members)\n- **Exclusions**: \"Add to Apartment but exclude Bob\"\n- **Payer**: \"Alice paid $50\"\n- **Deletion**: \"Delete expense 12345\"\n\n## Installation\n\n### Option 1: Install from PyPI (Recommended)\n\n```bash\npip install splitwise-mcp\n```\n\n### Option 2: Install from Source\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/hubshashwat/the-splitwise-mcp.git\n   cd the-splitwise-mcp\n   ```\n\n2. **Create and activate a virtual environment**:\n   ```bash\n   python3 -m venv .venv\n   source .venv/bin/activate\n  …","publisher":null,"homepage":null,"repository":null,"version":"0.1.2","license":"MIT","protocols":["mcp"],"tags":["ai","claude","mcp","model-context-protocol","splitwise","voice-assistant"],"pricing":null,"endpoints":[{"url":"pypi:splitwise-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":0.791,"provenance":"derived"}],"categories":["dev","media"],"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":"splitwise-mcp","registry":"pypi","observedAt":"2026-10-28T23:22:08.692Z","publishedAt":"2026-02-11T18:25:22.049070Z","latestVersion":"0.1.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"splitwise-mcp","url":"https://pypi.org/project/splitwise-mcp/","firstSeenAt":"2026-09-10T13:19:11.138Z","fetchedAt":"2026-10-28T23:20:08.726Z","normalizedAt":"2026-10-28T23:20:08.726Z"}]},"firstSeenAt":"2026-09-10T13:19:11.138Z","updatedAt":"2026-10-28T23:22:08.692Z"}