What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the ZERO MCP MCP server?
Read-only MCP inspection for ZERO paper autonomous onchain operations.
How to install ZERO MCP
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"zero": {
"command": "uvx",
"args": [
"zero-engine"
]
}
}
}Related MCP servers
First autonomous Solana trading agent on MCP. Live signals and consciousness feed.
View repository →MCP server for AGDEL. Agents can create, buy, deliver, reveal, and settle signals.
View repository →
MedXpert 图书馆连接器(通用版)
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.

LLM Usage
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

GPU compute price indices over MCP; every value carries a verify URL. Five key-free tools.
A bounded local evidence tool with current agent permission checks and durable retry handling.


