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 Cofferline MCP server?
Treasury and risk controls for agent wallets: policies, quotes, prediction-market orders.
How to install Cofferline
Copy-paste configuration for popular MCP clients.
AuthorizationsecretBearer cl_key_… API key or cl_sess_… SIWE session; obtain via POST https://api.cofferline.com/v1/auth/challenge then /verify. Public tools (quotes, benchmarks, screening, tokens, feedback list, login) work without it.
{
"mcpServers": {
"treasury": {
"url": "https://mcp.cofferline.com"
}
}
}Related MCP servers

Leading non-price Bitcoin signals over MCP: sovereign, hiring, hashrate. Not financial advice.

CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Unified dispute resolution: crypto, payments, SLA violations. 95% AI automation.
Multi-tenant business platform — 6,000+ RBAC-gated MCP tools across finance, ops, docs, agents.
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
View repository →