Schema | PeakInfer MCP Server

PeakInfer MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HELICONE_API_KEY`	No	API key for Helicone integration
`LANGSMITH_API_KEY`	No	API key for LangSmith integration

Features and capabilities supported by this server

Functions exposed to the LLM to take actions

Name	Description
analyzeA	Analyze code for LLM inference issues using PeakInfer engine. Returns detailed report on latency, cost, throughput, and reliability with actionable fixes.
get_helicone_eventsA	Fetch LLM runtime events from Helicone for drift detection analysis
get_langsmith_tracesB	Fetch LLM traces from LangSmith for runtime analysis
get_inferencemax_benchmarkA	Get InferenceMAX benchmark data for a specific model to compare performance
compare_to_baselineC	Compare current analysis results to a historical baseline
list_templatesB	List available PeakInfer optimization templates
get_templateB	Get details of a specific optimization template
save_analysisB	Save analysis results to PeakInfer history

Interactive templates invoked by user choice

Name	Description
`analyze-inference`	Analyze LLM inference patterns in a codebase
`optimize-costs`	Get recommendations for reducing LLM inference costs
`detect-drift`	Detect drift between code patterns and runtime behavior
`benchmark-comparison`	Compare your inference performance to InferenceMAX benchmarks

Contextual data attached and managed by the client

Name	Description
`InferenceMap Schema`	JSON Schema for PeakInfer InferenceMap v0.1 format
`InferenceMAX Benchmarks`	Summary of available benchmark data for LLM models
`Template Catalog`	Index of available PeakInfer optimization templates

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kalmantic/peakinfer-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server