{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_favnzdadvn4r","handle":"csv-token-counter-mcp","url":"https://wellknown.network/agents/csv-token-counter-mcp","links":{"self":"https://wellknown.network/agents/csv-token-counter-mcp/record.json","html":"https://wellknown.network/agents/csv-token-counter-mcp","markdown":"https://wellknown.network/agents/csv-token-counter-mcp/record.md","api":"https://wellknown.network/api/v1/agents/csv-token-counter-mcp","status":"https://wellknown.network/api/v1/agents/csv-token-counter-mcp/status","claim":"https://wellknown.network/agents/csv-token-counter-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/csv-token-counter-mcp/claim.json","badge":"https://wellknown.network/agents/csv-token-counter-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/csv-token-counter-mcp/history","tools":"https://wellknown.network/api/v1/agents/csv-token-counter-mcp/tools"},"ard":{"identifier":"urn:air::server:csv-token-counter-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"csv-token-counter-mcp","summary":"MCP server to count tokens in CSV and Excel files","description":"# csv-token-counter-mcp\n\nA lightweight MCP (Model Context Protocol) server that counts tokens in CSV \nand Excel files using [tiktoken](https://github.com/openai/tiktoken). \nWorks with VS Code, Claude Desktop, and any MCP-compatible application.\nNo LLM or API key required — runs fully offline.\n\n---\n\n## Why Use This?\n\nBefore sending CSV or Excel data to any LLM (ChatGPT, Claude, Gemini etc.),\nyou need to know how many tokens your data contains — to estimate cost,\ncheck context window limits, or split large files. This tool does exactly\nthat, directly inside your editor or AI assistant.\n\n---\n\n## Features\n\n- Count total tokens across an entire CSV or Excel file\n- Break down token counts column by column\n- Analyze tokens in a single specific column (avg, min, max per row)\n- Preview file schema — column names, types, row counts\n- Supports `.csv`, `.xlsx`, and `.xls` formats\n- Works fully offline — no API key or internet needed\n- Compatible with VS Code, Claude Desktop, and any MCP client\n\n---\n\n## Installation\n\n### Option 1 — pip (traditional)\n```bash\npip install csv-token-counter-mcp\n```\n\nAdd to your `.vscode/mcp.json`:\n```json\n{\n  \"servers\": {\n    \"csv-token-counter\": {\n      \"type\": \"stdio\",\n      \"command\": \"csv-token-counter-mcp\",\n      \"args\": []\n    }\n  }\n}\n```\n\n### Option 2 — uvx (recommended, no install needed)\n\nFirst install `uv` if you don't have it:\n```bash\npip install uv\n```\n\nAdd directly to your `.vscode/mcp.json` — no separate install step needed:\n```json\n{\n  \"servers\": {\n    \"csv-token-counter\": {\n      \"type\": \"stdio\",\n      \"command\": \"uvx\",\n      \"args\": [\"csv-token-counter-mcp\"]\n    }\n  }\n}\n```\n\n### Option 3 — Claude Desktop\n\nAdd to your Claude Desktop config file:\n\n**Mac:** `~/Library/Application Support/Claude/claude_desktop_config.json`  \n**Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n```json\n{\n  \"mcpServers\": {\n    \"csv-token-counter\": {\n      \"command\": \"uvx\",\n      \"args\": [\"csv-token-counter-mcp\"]\n    }\n  }\n}\n```\n\n---\n\n## Available T…","publisher":null,"homepage":"https://pypi.org/project/csv-token-counter-mcp","repository":null,"version":"1.0.1","license":"MIT License\n        \n        Copyright (c) 2026 Anup\n        \n …","protocols":["mcp"],"tags":["csv","excel","llm","mcp","tiktoken","tokens"],"pricing":null,"endpoints":[{"url":"pypi:csv-token-counter-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","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":1,"provenance":"declared"}],"categories":["documents"],"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":"csv-token-counter-mcp","registry":"pypi","observedAt":"2026-10-27T22:27:57.599Z","publishedAt":"2026-03-27T20:46:06.336906Z","latestVersion":"1.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"csv-token-counter-mcp","url":"https://pypi.org/project/csv-token-counter-mcp/","firstSeenAt":"2026-09-09T13:20:59.605Z","fetchedAt":"2026-10-27T22:27:17.818Z","normalizedAt":"2026-10-27T22:27:17.818Z"}]},"firstSeenAt":"2026-09-09T13:20:59.605Z","updatedAt":"2026-10-27T22:27:57.599Z"}