Skip to main content
Glama
jacob-bd

Perplexity Web MCP

by jacob-bd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to Perplexity Web MCP

No user-submitted related servers found.

    Related Servers

    • Perplexity Web MCP

      devdotbo
      A
      license
      C
      quality
      F
      maintenance
      MCP server providing 22 tools to query Perplexity AI's premium models (GPT-5.4, Claude 4.7 Opus, etc.) with citations, source discovery, and rate limit checking for AI agents.
      23
      17
      MIT

    • Perplexity MCP Server

      jschuller
      A
      license
      B
      quality
      C
      maintenance
      Connects AI assistants to Perplexity AI's search API, enabling natural language web search with fine-grained control over recency, citations, images, and model parameters directly from MCP clients like Claude.
      1
      28 npm
      6
      MIT

    • MCP Perplexity Pro

      cfdude
      A
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive MCP server that provides intelligent access to Perplexity AI's search and reasoning models with automatic model selection, conversation management, and project-aware storage. Supports real-time search, deep research, chat sessions, and async operations for complex queries.
      32 npm
      3
      MIT
    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

    C2.7/5.0

    Scored across 30 tools

    Disambiguation2/5

    Massive overlap among query tools: pplx_query, pplx_ask, pplx_smart_query, pplx_sonar, and ~14 model-specific tools (pplx_gpt56_terra, pplx_grok45, pplx_claude_sonnet, etc.) all essentially perform web queries, with the model-specific ones duplicating pplx_query(model=...). Descriptions steer toward pplx_smart_query, which helps somewhat, but an agent still faces many near-identical choices and redundant model tools like pplx_kimi_k26 vs pplx_kimi_k26_thinking.

    Naming Consistency4/5

    Names consistently use the pplx_ prefix with snake_case verbs/nouns, which is largely predictable. Minor deviations: 'think' (pplx_claude_sonnet_think, pplx_claude_opus_think, pplx_gemini_pro_think) versus 'thinking' (pplx_gpt56_terra_thinking, pplx_nemotron_thinking), and pplx_glm52 omits a thinking suffix despite always thinking.

    Tool Count2/5

    30 tools exceeds the typical well-scoped range and is inflated by 14+ per-model tools that largely duplicate pplx_query's model parameter, plus three auth tools and three deep-research tools. Many tools do not independently earn their place, making the surface heavier than the domain requires.

    Completeness4/5

    Coverage of the web-query domain is strong: querying, quota-aware routing, deep research (sync and async with status polling), thread browsing/retrieval, connectors, usage, and full auth lifecycle are all present. Only minor gaps like thread deletion or management operations are absent, which agents can work around.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources