PeakInfer MCP Server
Server Configuration
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 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
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 |
Prompts
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 |
Resources
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 |
TDQS
Scored across 8 tools
Most tools target distinct actions and resources. The only potential confusion is between get_helicone_events and get_langsmith_traces, but their descriptions clearly indicate different source platforms, making them distinguishable.
Tool names follow a consistent verb_noun snake_case pattern with get_*, list_*, save_*, and compare_to_*. The exception is 'analyze' which lacks an explicit object, but its purpose is still clear from the description.
Eight tools is a well-scoped set that covers code analysis, external data retrieval, benchmarking, template management, and persistence without unnecessary bloat. It fits the 3-15 tool range comfortably.
The set covers analysis, saving, comparison, and template browsing, but lacks any way to retrieve or list previously saved analyses. This creates a dead end after saving, as agents cannot access historical results directly.