Skip to main content
Glama
jacob-bd

Perplexity Web MCP

by jacob-bd
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

pplx_council

Query multiple AI models in parallel to get a synthesized consensus. Choose from available models and customize source focus for comprehensive answers.

Instructions

Model Council — query multiple models in parallel, get synthesized consensus.

IMPORTANT — BEFORE calling this tool, you MUST:

  1. Tell the user the available models: sonar, gpt54, gpt55, claude_sonnet, claude_opus, gemini_pro, nemotron, glm52, kimi_k26

  2. Check pplx_usage() first. If Subscription is Pro, do not include Max-only models: gpt55, claude_opus

  3. Ask the user WHICH models they want in their council and HOW MANY

  4. Inform them of the cost: each council model = 1 Pro Search query, plus synthesis (default chairman sonar = Sonar 2 pass — still counts as a normal query toward limits)

  5. Get explicit confirmation before executing

Default council: GPT-5.4, Claude Sonnet 5.0, Gemini 3.1 Pro (Pro-compatible, 3 diverse providers).

Args: query: The question to ask all council models source_focus: Source type for all models (none/web/academic/social/finance/all or connector source ID) models: Comma-separated model names to use as council members. Available: sonar, gpt54, gpt55, claude_sonnet, claude_opus, gemini_pro, nemotron, glm52, kimi_k26. Default: "gpt54,claude_sonnet,gemini_pro" (3 models + synthesis = 4 Pro Searches) Max-only: gpt55, claude_opus. Exclude these when pplx_usage shows a Pro subscription. synthesize: Whether to synthesize a consensus from all responses. Set false to get only individual responses (saves 1 Sonar 2 call). thinking: Enable extended thinking for council models (gpt54, gpt55, claude_sonnet, claude_opus, kimi_k26 support toggle; gemini_pro, nemotron, and glm52 are always thinking). chairman: Model to use for synthesis (default: "sonar" / Sonar 2). Non-sonar chairmen cost 1 extra Pro Search query.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
modelsNogpt54,claude_sonnet,gemini_pro
chairmanNosonar
thinkingNo
synthesizeNo
source_focusNoweb

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Tool Definition Quality

A5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully carries the burden. It details cost implications (each council model = one Pro Search), synthesis behavior, thinking support per model, and default behavior. No contradictions or omissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite length, the description is well-structured with a lead sentence, numbered preconditions, a default explanation, and a clear Args section. Every sentence adds value; no fluff. Information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, multiple models, subscription-dependent behavior), the description covers all necessary context: model availability, cost calculation, thinking support, synthesis toggle, and source focus. The presence of an output schema does not diminish the need for this context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, yet the description explains all 6 parameters: query, models, chairman, thinking, synthesize, source_focus. It provides allowed values, defaults, and behavioral context (e.g., which models support thinking, default chairman is sonar). This compensates fully for missing schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear statement: 'query multiple models in parallel, get synthesized consensus.' This specifies the verb (query, get), resource (multiple models, consensus), and distinguishes this tool from siblings like pplx_ask or single-model tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a numbered list of prerequisites: check pplx_usage, inform the user, get explicit confirmation. It also explains when to avoid Max-only models based on subscription, providing clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jacob-bd/perplexity-web-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server