{"id":"gomcpgo-perplexity-mcp-server","name":"perplexity-mcp-server","homepage":null,"repo_url":"https://github.com/gomcpgo/perplexity-mcp-server","category":"ai-ml","subcategories":[],"tags":["mcp","search","internet-research","citations","caching","go","perplexity-api"],"what_it_does":"Provides a Model Context Protocol (MCP) server (and CLI mode for testing) that lets LLM agents query Perplexity AI’s search capabilities (general web, academic, financial, and filtered search) and optionally cache results locally for later retrieval by ID.","use_cases":["Real-time internet research for general questions with source URLs/citations","Finding academic papers and scholarly sources for literature review","Searching financial/SEC-related information and recent market context","Agent workflows that require controlled filtering (domain, recency, content type, geo, etc.)","Caching search results locally to reference earlier findings within a conversation"],"not_for":["High-sensitivity deployments where local caching and unencrypted at-rest data are unacceptable","Environments that require a standard HTTP/REST API contract for integration (this is an MCP/CLI tool)","Use cases needing first-party data residency controls or formal compliance guarantees (not documented here)"],"best_when":"You want an LLM agent to perform tool-augmented internet research with citations and (optionally) local result caching.","avoid_when":"You cannot securely handle an external Perplexity API key or you need strong guarantees about data handling/compliance beyond what is documented.","alternatives":["Direct Perplexity API integration (without MCP)","Other MCP web-search or browsing servers","General web search tools (e.g., SerpAPI/Google CSE-like services) wrapped for MCP","Framework-based browsing/search integrations (LangChain/LLM toolkits) where supported"],"af_score":68.0,"security_score":53.8,"reliability_score":35.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:46:01.853978+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["PERPLEXITY_API_KEY (environment variable)"],"oauth":false,"scopes":false,"notes":"Authentication appears to be via a single API key provided through an environment variable; no OAuth or scope model is described."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing is not described in the repository README; costs depend on the Perplexity API plan and usage."},"requirements":{"requires_signup":true,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":68.0,"security_score":53.8,"reliability_score":35.0,"mcp_server_quality":70.0,"documentation_accuracy":75.0,"error_message_quality":null,"error_message_notes":"README lists common HTTP error codes (400/401/429/500) and states messages are descriptive, but it does not show concrete MCP error payload examples or tool-level error schemas.","auth_complexity":90.0,"rate_limit_clarity":40.0,"tls_enforcement":90.0,"auth_strength":55.0,"scope_granularity":10.0,"dependency_hygiene":40.0,"secret_handling":70.0,"security_notes":"Uses an API key via environment variable, which is generally safer than hardcoding. README does not describe whether requests/response data is logged, whether the API key is masked, or how local cached files are protected (at-rest encryption/permissions not documented). Rate limiting and parameter validation are mentioned, but detailed security controls are not provided.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":50.0,"error_recovery":45.0,"idempotency_support":"false","idempotency_notes":"Caching behavior explicitly creates new cached entries per search; no idempotency guidance for repeated tool calls is documented.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Caching is not reused for identical queries (each search creates a new cached entry), which may cause unbounded growth if repeatedly called.","If the MCP client runs the server as a subprocess, ensure PERPLEXITY_API_KEY is available in that process environment.","Tool calls may be subject to Perplexity API rate limits; README mentions 429 but does not provide agent retry/backoff guidance."]}}