{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hmnxkxf44zrv","handle":"sarvam-mcp","url":"https://wellknown.network/agents/sarvam-mcp","links":{"self":"https://wellknown.network/agents/sarvam-mcp/record.json","html":"https://wellknown.network/agents/sarvam-mcp","markdown":"https://wellknown.network/agents/sarvam-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sarvam-mcp","status":"https://wellknown.network/api/v1/agents/sarvam-mcp/status","claim":"https://wellknown.network/agents/sarvam-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sarvam-mcp/claim.json","badge":"https://wellknown.network/agents/sarvam-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sarvam-mcp/history","tools":"https://wellknown.network/api/v1/agents/sarvam-mcp/tools"},"ard":{"identifier":"urn:air::server:sarvam-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sarvam-mcp","summary":"Official Sarvam AI MCP server — STT, TTS, Translate, Transliterate, LLM, Vision OCR for Indic languages","description":"# sarvam-mcp\n\nOfficial Sarvam MCP server. Exposes every public Sarvam API — STT, TTS, Translate, Transliterate, Language ID, Text Analytics, LLM (30B / 105B), Vision Document Intelligence, Pronunciation Dictionaries — as first-class MCP tools so any MCP-aware client (Claude Desktop, Claude Code, Cursor, Windsurf, Zed) can call Sarvam with zero boilerplate.\n\nCross-platform Python package: **macOS, Windows, and Linux** (Python 3.11+).\n\n## Quickstart\n\n### 1. Get your API key\n\nSign up or log in at **[dashboard.sarvam.ai/key-management](https://dashboard.sarvam.ai/key-management)** and copy your API key (`sk_...`).\n\n### 2. Add to your MCP client\n\nPaste this into your MCP config JSON:\n\n```json\n{\n  \"mcpServers\": {\n    \"sarvam\": {\n      \"command\": \"uvx\",\n      \"args\": [\"sarvam-mcp\"],\n      \"env\": {\n        \"SARVAM_API_KEY\": \"sk_...\"\n      }\n    }\n  }\n}\n```\n\nReplace `sk_...` with your actual API key.\n\nIf you've installed via `pip install sarvam-mcp`, you can use the console script directly:\n\n```json\n{\n  \"mcpServers\": {\n    \"sarvam\": {\n      \"command\": \"sarvam-mcp\",\n      \"env\": {\n        \"SARVAM_API_KEY\": \"sk_...\"\n      }\n    }\n  }\n}\n```\n\n### 3. Config file locations\n\n| Client | Config path |\n|---|---|\n| **Cursor** | `~/.cursor/mcp.json` (macOS/Linux) · `%USERPROFILE%\\.cursor\\mcp.json` (Windows) |\n| **Claude Desktop** | `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) · `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows) |\n| **Claude Code** | `claude mcp add sarvam -- uvx sarvam-mcp` (then set `SARVAM_API_KEY` env var) |\n| **Windsurf** | Cascade settings → MCP servers |\n| **Zed** | `settings.json` → `context_servers` |\n\n### Alternative: credentials file\n\nInstead of setting `SARVAM_API_KEY` in the JSON config, you can store it in `~/.sarvam/credentials`:\n\n```ini\napi_key = sk_...\n```\n\nThe server checks `SARVAM_API_KEY` env var first, then falls back to `~/.sarvam/credentials`.\n\n## Install\n\n```bash\n# Option A: run directly (no install needed)\nuvx s…","publisher":null,"homepage":"https://docs.sarvam.ai","repository":"https://github.com/sarvamai/sarvam-mcp/releases","version":"0.2.12","license":null,"protocols":["mcp"],"tags":["indian-languages","indic","mcp","model-context-protocol","sarvam","stt","translation","tts"],"pricing":null,"endpoints":[{"url":"pypi:sarvam-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":"content.translation","name":"Translation","confidence":1,"provenance":"declared"},{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"declared"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"}],"categories":["content","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":"sarvam-mcp","registry":"pypi","observedAt":"2026-10-22T19:28:02.055Z","publishedAt":"2026-10-08T11:03:09.815409Z","latestVersion":"0.2.12"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sarvam-mcp","url":"https://pypi.org/project/sarvam-mcp/","firstSeenAt":"2026-09-10T11:27:53.587Z","fetchedAt":"2026-10-22T19:26:44.027Z","normalizedAt":"2026-10-22T19:26:44.027Z"}]},"firstSeenAt":"2026-09-10T11:27:53.587Z","updatedAt":"2026-10-22T19:28:02.055Z"}