Skip to main content
Glama
ivanantigravity-lgtm

perplexity-polza-mcp-server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging levelINFO
POLZA_BASE_URLNoBase URL for chat completionshttps://polza.ai/api/v1
PERPLEXITY_MODELNoModel for perplexity_ask toolperplexity/sonar
POLZA_AI_API_KEYYesAPI key from polza.ai
PERPLEXITY_RESEARCH_MODELNoModel for perplexity_research toolperplexity/sonar-deep-research

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

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
perplexity_askD–
perplexity_researchD–
list_perplexity_modelsD–

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

D1.6/5.0

Scored across 3 tools

Disambiguation4/5

Tool names suggest distinct purposes: listing models, asking a question, and doing research. However, the lack of descriptions creates some ambiguity about each tool's exact scope.

Naming Consistency2/5

Naming is inconsistent: one tool uses a verb_noun pattern (list_perplexity_models), while the other two use a brand prefix followed by a verb (perplexity_ask, perplexity_research). The convention is not uniform.

Tool Count3/5

Three tools is on the lower side but could be sufficient for a focused server (e.g., listing models, asking questions, researching). However, the lack of descriptions makes the scope feel underdeveloped.

Completeness3/5

The tool set covers basic interactions with Perplexity (list models, ask, research), but without descriptions it's unclear if common operations like context management or follow-up questions are supported. The surface appears minimal but possibly complete for simple use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues