Borrowing it
Nothing to install: this file belongs to safayavatsal/Sarvam-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/safayavatsal/Sarvam-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/safayavatsal/Sarvam-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/safayavatsal/sarvam-mcp/claude-md)<a href="https://agentmods.dev/instructions/safayavatsal/sarvam-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/safayavatsal/sarvam-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/safayavatsal/sarvam-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/safayavatsal/sarvam-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00691 | $0.00691 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
Sarvam-MCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Sarvam AI MCP Server
Project Overview
This is a Sarvam AI MCP Server — a Python-based MCP (Model Context Protocol) server that exposes Sarvam AI's Indic language processing APIs as MCP tools. It allows LLM clients (Claude Desktop, Gemini CLI, Warp, etc.) to perform translation, transliteration, language identification, and chat with the SarvamAI-M model.
Architecture
- Single-file server: All logic lives in
sarvam_mcp.py - Framework: Uses FastMCP (
mcp.server.fastmcp.FastMCP) - Transport: Streamable HTTP on
0.0.0.0:8080(stateless) - External API: All tools proxy requests to
https://api.sarvam.ai - Auth: Sarvam API key loaded from
.envviapython-dotenv
MCP Tools Exposed
| Tool Name | Function | Endpoint | Notes |
|---|---|---|---|
Language_Identification |
lang_ident |
POST /text-lid |
Max 2000 chars |
Transliterate |
lang_identification |
POST /transliterate |
Max 1000 chars, auto source detection |
Translate |
lang_identification |
POST /translate |
Auto source detection |
Sarvam_Chat |
sarvam_chat |
POST /v1/chat/completions |
Modes: basic, wiki (wiki_grounding) |
Supported Languages
Bengali (bn), English (en), Gujarati (gu), Hindi (hi), Kannada (kn), Malayalam (ml), Marathi (mr), Odia (od), Punjabi (pa), Tamil (ta), Telugu (te) — all with -IN locale codes.
Key Files
sarvam_mcp.py— Server entry point and all tool definitions.env— ContainsSARVAM_API_KEY(do NOT commit real keys)requirements.txt— Runtime deps:fastmcp,dotenv,httpxpyproject.toml— Project metadata (requires Python >=3.13)Dockerfile— Slim Python 3.13 image, exposes port 8080
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 56 lines · 691 tokens per session scan A 1f868256a2a7
Sarvam-MCP CLAUDE.md is an instructions file published in the GitHub repository safayavatsal/Sarvam-MCP (0 stars, last pushed 7mo ago), licensed MIT. It adds 691 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Sarvam-MCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Sarvam-MCP CLAUDE.mdsafayavatsal/Sarvam-MCP | Instructions file | 0 | 7mo ago | MIT | A | 691 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |