mcpspend / setup / openai-agents
Setup guide

Set up MCPSpend in OpenAI Agents SDK

communitystdiounknownno verified config · noindex

Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted


01Configuration
# MCPSpend via OpenAI Agents SDK # transport: stdio # launch: npx -y @mcpspend/proxy@latest

OpenAI Agents SDK connects to MCP servers in code. Use its MCP client with the command/URL below; exact API varies by version.


02Steps
  1. Make sure OpenAI Agents SDK is installed and up to date.
  2. Wire the server into OpenAI Agents SDK using its MCP client API.
  3. Provide any required API keys/credentials as environment variables.
  4. Restart OpenAI Agents SDK and confirm MCPSpend’s tools appear.

03Other runtimes

04Provenance
config_sourcegenerated from captured install method
last_checked2026-07-22 08:29Z
sourcesGitHub repo search [p4]

Next step

Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.

Explore Apex →

See also: server page · is it safe? · alternatives