What it does
The server counts tokens and produces cost estimates for more than 25 large language models, including GPT-4o, Claude and Gemini. It is published as an MCP server from the tree of the publisher's GitHub repository, under its mcp-server folder.
The publisher describes the estimates as requiring no API key, so the server can be used without provider credentials. The source gives no further details on setup or usage.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.waqarulwahab/llm-cost-estimator
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
v0.3.1As shown on registry.modelcontextprotocol.io when we last read it