Skip to main content
Glama
AldereteSergio

Pepe-MCP-Server

by AldereteSergio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PERPLEXITY_BROWSER_DATA_DIRNoDirectory for the browser profile.~/.perplexity-mcp
PERPLEXITY_PERSISTENT_PROFILENoSet to 'false' for anonymous mode.true

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
chat_perplexityA

Hilo conversacional con Pepe; guarda contexto (chat_id). Usa CPQO en message o turnos cortos si el hilo ya cargó el brief.

extract_url_contentA

Texto limpio de una URL (menos ruido que la página). No reemplaza CPQO en search; sirve para traer evidencia puntual.

get_documentationB

Buscar documentación y ejemplos oficiales vía Pepe. query en CPQO: qué stack, qué falla, qué entregables (snippets, breaking changes, etc.).

find_apisB

Descubrir/comparar APIs externas vía Pepe. query en CPQO: restricciones (región, SLA, presupuesto), preguntas de comparación, objetivos medibles.

check_deprecated_codeB

Contrastar código o patrones con estado actual en la web. query en CPQO: stack, snippet o patrón, y qué certeza necesitás (reemplazo, fecha deprecación, migración).

searchA

Investigación web en una pasada (Perplexity). Elegí detail_level: brief ≈1–2 objetivos, normal ≈3–5, detailed ≈6–8 en OBJECTIVES (skill pepe-research-brief). Para informe amplio multi-fuente usá deep_research.

list_available_modelsA

Lista modelos Pro disponibles en tu cuenta Perplexity antes de fijar model en search/chat.

deep_researchA

Modo investigación amplia (más pasadas/fuentes que search). Mismo CPQO; suele requerir muchos OBJECTIVES (≥6 si el tema es grande). Skill pepe-research-brief.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 8 tools

Disambiguation4/5

Each tool targets a visibly different research workflow: URL extraction, conversational chat, documentation lookup, API discovery, deprecation checking, one-pass search, deep research, and model listing. Search and deep_research are intentionally related, but their descriptions explicitly distinguish breadth and depth, keeping misselection risk low.

Naming Consistency4/5

Most names follow a snake_case verb_noun pattern (extract_url_content, find_apis, list_available_models, check_deprecated_code). Search and deep_research deviate slightly, but the overall naming remains predictable and readable.

Tool Count5/5

Eight tools is a well-scoped size for a Perplexity-backed research assistant; each tool adds a meaningful capability without redundancy. The count feels appropriate for the server's purpose.

Completeness4/5

The surface covers common research workflows: one-pass and deep web research, conversational follow-up, documentation/API/deprecation lookups, URL evidence extraction, and model selection. Minor gaps exist such as no explicit citation or history management tool, but agents can work around them using chat or search.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources