pulsemcp scanned Safe content atomic mcp-remote

Perplexity Sonar

This MCP server provides AI assistants with three-tiered access to Perplexity's Sonar API for web search and reasoning capabilities, built using Python with httpx for HTTP communication and comprehensive error handling. The implementation offers small (sonar-pro), medium (sonar-reasoning-pro), and large (sonar-deep-research) complexity levels that balance speed versus depth, with the small tool optimized for quick factual queries, medium for enhanced reasoning with moderate search depth, and large for comprehensive research tasks that can take 10-30 minutes but provide extensive analysis with high reasoning effort. Built with proper logging to stderr for MCP protocol compliance, automatic removal of thinking tokens from responses, and configurable timeouts, it serves users needing flexible AI-powered research capabilities ranging from instant answers to deep academic-level analysis with proper citations and web search integration.

Cognium trust score
64%
Tier
Scanned

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.

Scan details: Circle-IR · 2026-09-02 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
monitoring
Source
PulseMCP
Author type
human
Last scanned
2026-09-02
Updated
2026-09-02
View source Find related skills

Use via MCP

MCP

Resolve Perplexity Sonar from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry