Skip to main content
Glama
Perplexity MCP Server

Perplexity MCP Server

by RossH121

Perplexity MCP Server

An MCP server that gives Claude (and any other MCP client) access to Perplexity: AI-synthesized web search, raw ranked results, the multi-step Agent API, background research jobs, the Decisions API and embeddings. It exposes 22 tools; 6 of them are deprecated and kept for compatibility.

Sonar end of support. Perplexity's Sonar Chat Completions API reached end of support on 2026-09-27. search and async_research_submit now run on the Perplexity Agent API by default. See How search works and Migration and breaking changes.

Contents

Related MCP server: Perplexity MCP Server

Prerequisites

Setup

Clone, install and build:

git clone https://github.com/RossH121/perplexity-mcp.git
cd perplexity-mcp
npm install
npm run build

Claude Code

Add it with the CLI (use --scope project to write a shared .mcp.json instead of your user config):

claude mcp add perplexity -e PERPLEXITY_API_KEY=your-api-key -- node /absolute/path/to/perplexity-mcp/build/index.js

Or add it to .mcp.json in your project root. Claude Code expands ${VAR} references, so the key can stay in your shell environment:

{
  "mcpServers": {
    "perplexity": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/perplexity-mcp/build/index.js"],
      "env": {
        "PERPLEXITY_API_KEY": "${PERPLEXITY_API_KEY}"
      }
    }
  }
}

Tools then appear as mcp__perplexity__search, mcp__perplexity__agent, and so on. If you pin tool names in agent or permission allowlists, see the renamed tools.

Claude Desktop

Add the same entry under mcpServers in ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), with the key written in directly, then restart Claude Desktop.

Install via MCPB (Claude Desktop, macOS/Windows)

Build the bundle (requires Node.js 20+):

npm install
npm run pack:mcpb   # -> dist/mcpb/perplexity-mcp-<version>.mcpb

To install it, double-click the .mcpb file or drag it onto Claude Desktop (Settings > Extensions). Claude Desktop then asks for these settings:

Setting

Env var

Default

Notes

Perplexity API key (required)

PERPLEXITY_API_KEY

none

Stored in the OS keychain

Default Sonar model

PERPLEXITY_MODEL

sonar-pro

sonar, sonar-pro, sonar-reasoning-pro or sonar-deep-research. An invalid value stops the server from starting

Search backend

PERPLEXITY_SEARCH_BACKEND

agent

agent (Agent API) or sonar (legacy Sonar path)

Debug logging

PERPLEXITY_MCP_DEBUG

empty

Set to 1 for verbose stderr diagnostics

Claude Desktop isn't available on Linux. There, use the Claude Code .mcp.json setup, pointing node at build/index.js.

Configuration

Variable

Required

Default

Description

PERPLEXITY_API_KEY

yes

Your Perplexity API key. The server exits at startup without it.

PERPLEXITY_MODEL

no

sonar-pro

Default Sonar model for search when no routing keyword matches: sonar, sonar-pro, sonar-reasoning-pro or sonar-deep-research. Any other value is rejected at startup.

PERPLEXITY_SEARCH_BACKEND

no

agent

Backend for search and async_research_submit. agent uses the Agent API. sonar switches back to the legacy Sonar Chat Completions and async endpoints, for as long as Perplexity still answers them. Read on every call.

PERPLEXITY_MCP_DEBUG

no

unset

Any non-empty value turns on verbose diagnostics on stderr. stdout carries only MCP JSON-RPC.

Pricing: https://docs.perplexity.ai/docs/getting-started/pricing

Tools

At a glance

Purpose

Tool

Billed

Notes

Answer a question

search

yes

One AI-synthesized answer with cited sources. The default choice.

Find sources

raw_search

yes

Ranked URLs, titles and snippets with no LLM. Up to 5 queries per call.

Multi-step agent

agent

yes

Agent API loop: built-in tools, remote MCP servers, skills, file and image input, third-party models.

agent_retrieve

Poll a background agent run.

agent_cancel

Cancel an in-progress run.

agent_files

List or download files a run shared.

Background research

async_research_submit

yes

Start a long research job and get an id back.

async_research_status

Poll a job. Returns the report when done.

async_research_list

Jobs submitted by this server process.

Probabilities

decisions

yes

Calibrated yes/no, choice and rubric-score probabilities.

Embeddings

embeddings

yes

Text embeddings.

contextualized_embeddings

yes

Chunk embeddings that share per-document context.

Discovery

list_models

Model ids usable by agent.

list_skills

Custom skill ids usable by agent.

Search model state

get_model_info

local

Current Sonar model selection for search.

set_model

local

Pin a model for later search calls, or auto.

Deprecated

async_research

yes (submit)

Alias, removed next release. Use async_research_submit / _status / _list.

model_info

local

Alias, removed next release. Use get_model_info / set_model.

domain_filter

local

Use the per-call search_domain_filter on search.

recency_filter

local

Use the per-call recency or date params on search.

clear_filters

local

Only clears the deprecated stateful filters.

list_filters

local

Only lists the deprecated stateful filters.

"local" tools change or read this server's in-memory state and make no API call. Unbilled tools without "local" read existing results from the API.

Every tool is annotated with MCP read-only, destructive, idempotent and open-world hints, so clients such as Claude Code can run the read-only ones in parallel and retry them safely. Data tools also return structuredContent matching a declared outputSchema, alongside the markdown text: search, raw_search, agent, agent_retrieve, agent_files, async_research_status, async_research_list, get_model_info, list_models, list_filters, list_skills, decisions, embeddings and contextualized_embeddings.

Returns one synthesized answer with numbered sources. It uses only the query text, not your conversation, so write a specific query. Keyword routing picks the depth (see How search works).

Parameter

Options

Description

query

string

The question. Required.

effort

fast / low / medium / high / xhigh / ultra, or name@latest / name@<version>

Agent effort level for this call. Bypasses keyword routing and set_model. Agent backend only. high and above can take minutes.

search_domain_filter

string[], max 20

Allow only these domains, or exclude them with a - prefix (["-pinterest.com"]). A list is all-allow or all-exclude. [] means no domain filter for this call.

recency

hour / day / week / month / year

Time window for this call. Dropped, with a note, if search_after_date / search_before_date is also set.

search_after_date / search_before_date

MM/DD/YYYY

Published-date filter

last_updated_after / last_updated_before

MM/DD/YYYY

Last-updated filter

search_mode

web / academic / sec

academic becomes an allowlist of 20 academic domains, unless you set domain filters. sec adds the finance_search tool and a sec.gov filter.

search_context_size

low / medium / high

How much retrieved context the model gets

search_type

fast / pro / auto

fast uses fast web search. pro raises effort fast to low. auto has no Agent equivalent and is ignored.

reasoning_effort

minimal / low / medium / high

Sent as reasoning.effort

return_images

boolean

Adds the image_search tool and an ## Images section. Billed per image search.

image_domain_filter / image_format_filter

string[]

Restrict images (first 10 domains; bmp, gif, jpeg, png, webp, svg)

country / city / region / latitude / longitude

Localize results

language_preference

ISO 639-1

Response language

disable_search

boolean

Answer with perplexity/sonar and no tools. Filters don't apply.

response_format

JSON schema

Structured output

temperature / top_p / max_tokens

number

Sampling and length controls (max_tokens is sent as max_output_tokens)

show_cost

boolean

Append a request-cost footer

strip_thinking

boolean

Remove <think> blocks (only the legacy backend produces them)

stream

boolean

Legacy backend only. The result is the same either way.

search_language_filter, stream_mode, return_related_questions, image_results_enhanced_relevance, enable_search_classifier, stop

Legacy Sonar backend only. Ignored on the agent backend, with a line under "Backend notes".

Examples:

  • "What's the latest Node.js LTS?" routes to sonar-pro, effort fast.

  • "Deep research analysis of CRISPR gene editing advances" routes to sonar-deep-research, effort high.

  • search { query: "...", effort: "medium", search_domain_filter: ["nodejs.org"] } sets the depth and sources directly.

Ranked results straight from the Search API, with no LLM. Cheaper and faster than search. Useful for URL discovery, source lists and fact-checking pipelines.

Parameter

Options

Description

query

string or up to 5 strings

Each query counts separately against the rate limit.

max_results

1-20, or 1-50 with search_type: people

Default 10

max_tokens / max_tokens_per_page

number

Content budget overall and per result

search_context_size

low / medium / high

Content extracted per page (default high). Undocumented but still effective; prefer the token budgets.

search_type

web / fast / people

fast is cheaper and lower-latency. people routes to People Search.

search_domain_filter

string[], max 20

Allow, or exclude with -

recency, search_after_date / search_before_date, last_updated_after / last_updated_before

Time filters

search_language_filter

["en","de"]

Source languages

country

ISO 3166-1 alpha-2

Localize results

raw_search has no search_mode: the /search endpoint rejects it. To narrow it to a corpus, use search_domain_filter, for example ["arxiv.org", "pubmed.ncbi.nlm.nih.gov"] or ["sec.gov"].

agent

The Perplexity Agent API: a multi-step loop that can call built-in tools, remote MCP servers and skills, and can run third-party models. With no effort, model or profile, it runs effort low.

Parameter

Options

Description

input

string

The task. Required. May be empty only with approval_responses.

effort

fast / low / medium / high / xhigh / ultra, or name@latest / name@<version> (e.g. low@2026-11-11.0)

A configuration bundle (model, tools, steps, search type). Default low. wide-research is a legacy alias of xhigh. Can't be combined with profile.

preset

Deprecated alias of effort. effort wins if both are set.

profile

{type:"custom", id, version?}

A saved configuration from the API Portal. Request fields override it, except tools, which merge per tool.

model / models

e.g. anthropic/claude-sonnet-5-5, openai/gpt-6-sol

A provider-qualified model, or a fallback chain. Call list_models for current ids. An invalid id comes back with the current list in the error.

instructions

string

System prompt

tools

web_search / fetch_url / people_search / finance_search / image_search / sandbox

Built-in tools

web_search_options

object

search_type (fast default, or web), max_results (1-50), token budgets, search_context_size, domain/recency/date filters, user_location. Setting it enables web_search.

tool_choice

none / auto / required

Whether the model may, must or must not call tools

max_steps

1-500

Agentic steps. A direct model run defaults to 1.

max_output_tokens

number

Output cap

reasoning_effort

none / minimal / low / medium / high / xhigh / max

How hard the model reasons. Separate from effort.

response_format

JSON schema

Structured output

images

string[]

http(s):// or data: image URLs

files

[{file_url | file_data, filename?}]

PDF, DOC, DOCX, TXT or RTF input, max 30. Not available to ZDR organizations.

mcp_servers

object[]

Remote MCP servers (see below)

approval_responses

[{approval_request_id, approve, reason?}]

Answer approval-gated MCP calls. Needs previous_response_id and the same mcp_servers.

skills

object[], max 16

builtin, inline or custom (see below)

background

boolean

Queue the run. Poll with agent_retrieve, cancel with agent_cancel. Use it for xhigh / ultra.

previous_response_id / store

Continue a prior run. store: false hides the run from agent_retrieve.

language_preference, temperature, top_p

Response language and sampling

service_tier

auto / default / flex / priority / fast

flex is best effort at 0.5x (OpenAI models). priority (alias fast) costs 2x. The output header shows the tier that ran.

prompt_cache_key

string

Override the automatic prompt cache key

The output header reads [Agent model: X | effort: name@version | service_tier: Y]. Approval requests, MCP activity, images and shared files get their own sections.

Remote MCP servers. Streamable HTTP endpoints only (no SSE):

{
  "server_label": "docs",
  "server_url": "https://example.com/mcp",
  "authorization": "<bearer token>",
  "allowed_tools": ["search_docs"],
  "require_approval": "always"
}

By default every MCP call runs automatically. require_approval takes always, never, or {always?, never?: {tool_names?, read_only?}}. A gated call pauses the run and is listed with an approval_request_id. To continue, call agent again with previous_response_id, approval_responses and the same mcp_servers. A single unreachable server fails the whole run with HTTP 424, so configure only servers you trust and expect to be up.

Skills. Selecting any skill enables the sandbox:

{ "type": "builtin", "name": "office/pdf" }
{ "type": "inline", "name": "house-style", "description": "Our formatting rules.", "instructions": "..." }
{ "type": "custom", "id": "skill_..." }

Builtin names are office (all four), office/docx, office/pdf, office/pptx and office/xlsx. Use list_skills to find custom ids.

agent_retrieve, agent_cancel

agent_retrieve { response_id } returns a background run's status, and its full output once it completes. agent_cancel { response_id } stops a run. Cancellation is asynchronous, so poll agent_retrieve to see the final status.

agent_files

Lists (action: "list") or downloads (action: "content", with file_id) the files a run delivered with its share_file tool. The office/* skills do this, and such files also appear under "Shared files" in the agent output. Files the agent merely wrote to disk during code execution are not listed, so ask it to share the file.

agent_files { action: "list", response_id: "resp_..." }
agent_files { action: "content", response_id: "resp_...", file_id: "file_..." }

Shared files are also MCP resources at perplexity-agent-file://{response_id}/{file_id}. list returns resource links; content (or resources/read) returns the bytes as an embedded resource, as text for UTF-8 text types and as a base64 blob otherwise. Files over 5 MB are reported, not inlined. resources/list shows the files seen in the current session.

async_research_submit, async_research_status, async_research_list

Long research as a background Agent API run, so the call doesn't block.

Tool

Parameters

Description

async_research_submit

query, model, reasoning_effort, search_mode

Returns a resp_... id. model is a Sonar model mapped to an effort level (default sonar-deep-research, which maps to high).

async_research_status

request_id, strip_thinking

Read-only. Says "not ready yet" until the run completes. Bare-UUID ids from the old async Sonar API are still polled through the legacy endpoint while it answers.

async_research_list

Ids submitted by this server process (kept in memory, lost on restart), plus any legacy async jobs.

The id also works with agent_retrieve and agent_cancel. For full control (tools, models, structured output), use agent with background: true.

decisions

Ask named questions about some content and get calibrated probabilities back instead of prose. No rationale text is returned.

Parameter

Options

Description

state

string / object / array

The content the questions refer to. It may embed OpenAI-style image_url parts with base64 data URLs, up to 8 per question.

questions

object

Name → {type, instructions?, criteria?}. noul: yes/no, returns P(yes); needs instructions or criteria: {true, false}. choice: criteria maps each option to a description or null (1-255 options). score: criteria is an ordered array of 1-10 levels (index = score).

model

string

Default pplx-decider-latest (v1.2, 27B). pplx-decider-flash-latest (4B) is half price.

mode

web_grounding

One web search per question (max 100 questions). A URL-only state is fetched first. Sources are listed.

max_staleness

integer (seconds)

Max age of the fetched page copy (web grounding with a URL state only)

Pricing: $0.02 per million input tokens ($0.01 for flash), output free, plus $0.001 per web search or fetch. The output shows an estimated cost, because the API returns token counts but no cost.

decisions({
  state: "The headphones sound great, but the battery stopped charging after two weeks.",
  questions: {
    defect:    { type: "noul",   instructions: "Does the review report a product defect?" },
    sentiment: { type: "choice", criteria: { positive: "Mostly satisfied", mixed: null, negative: "Mostly dissatisfied" } },
    severity:  { type: "score",  instructions: "How severe?", criteria: ["Cosmetic", "Inconvenient", "Unusable"] }
  }
})

embeddings, contextualized_embeddings

Parameter

embeddings

contextualized_embeddings

input

string or string[] (max 512)

string[][]: one array of chunks per document (max 512 documents, 16,000 chunks)

model

pplx-embed-v1-0.6b (default) / pplx-embed-v1-4b

pplx-embed-context-v1-0.6b (default) / pplx-embed-context-v1-4b

dimensions

128-1024 (0.6b) or 128-2560 (4b)

same

encoding_format

base64_int8 (default; there is no float output) / base64_binary

same

full

Include the raw base64 vectors (default: summary only)

same

The two model families are not interchangeable. Contextualized embeddings let chunks from the same document share context, which improves RAG retrieval.

list_models, list_skills

list_models { provider? } lists the models available to your account from the live GET /v1/models endpoint, grouped by provider. These are the provider-qualified ids for agent's model / models (e.g. anthropic/claude-sonnet-5-5, openai/gpt-6-sol, perplexity/sonar). It doesn't list the Sonar models search routes between; get_model_info shows those.

list_skills lists your project's uploaded custom skills (limit, page_token), or describes one by skill_id (with an optional revision). Pass the id to agent as skills: [{ type: "custom", id }]. Uploading and deleting skills are not exposed.

get_model_info, set_model

get_model_info shows the current Sonar selection for search, the default model and the routing keywords. set_model { model } pins sonar, sonar-pro, sonar-reasoning-pro or sonar-deep-research for every later search call in this server process, or "auto" restores keyword routing. A query that strongly matches another model's keywords still overrides a pinned model. For a single call, use search's effort instead, which doesn't touch shared state.

Deprecated tools

These still work. Each alias's result ends with a deprecation note.

Tool

Replacement

Status

async_research (action: submit / status / list)

async_research_submit / async_research_status / async_research_list

Removed next release

model_info

get_model_info (view) / set_model (change). Called with no arguments, model_info resets the selection.

Removed next release

domain_filter, recency_filter

search's per-call search_domain_filter, recency and date params

Deprecated, no removal date

clear_filters, list_filters

Not needed with per-call params

Deprecated, no removal date

The stateful filters apply to every later search in the server process, including parallel ones. Per-call params override them for that call without changing them.

How search works

search and async_research_submit run on the Perplexity Agent API unless PERPLEXITY_SEARCH_BACKEND=sonar.

  1. Routing. Keywords in the query pick a Sonar model, unless set_model pinned one.

  2. Effort mapping. That model maps to an Agent effort level, following Perplexity's Sonar migration guide:

Keywords (examples)

Sonar model

Agent effort

deep research, comprehensive, thorough, in-depth, expert

sonar-deep-research

high

reasoning, solve, analyze, think, figure out, logic

sonar-reasoning-pro

low

quick, simple, brief, basic, short

sonar

fast

anything else

sonar-pro (or PERPLEXITY_MODEL)

fast

  1. Override. A per-call effort skips both steps.

  2. Request. Filters, location and search_context_size go on the web_search tool. return_images adds image_search, and search_mode becomes domain filters or tools.

The header line shows what ran, for example [Using model: sonar-pro -> Agent effort fast (ran fast@<version> on <model>) - ...], or [Using effort override: medium (ran ...)]. Parameters with no Agent equivalent are listed under "Backend notes" at the end of the result.

On a live comparison of six queries (2026-11-12), the agent backend gave equivalent answers at the same latency, cost 2-3x less on text queries, and returned images where the legacy backend returned none. Academic mode is only approximated: it returned 10 sources to Sonar's 20.

Rollback. PERPLEXITY_SEARCH_BACKEND=sonar restores the legacy Sonar Chat Completions and async paths for as long as Perplexity still answers them. On that backend effort is ignored, the Sonar-only params work again, and async_research_submit accepts only sonar-deep-research. Legacy Sonar docs: https://docs.perplexity.ai/docs/legacy/sonar/.

Migration and breaking changes

Renamed and deprecated tools

  • New tools: async_research_submit, async_research_status, async_research_list, get_model_info, set_model, decisions, list_skills.

  • async_research and model_info are deprecated aliases, removed in the next release. Their results end with a deprecation note.

  • domain_filter, recency_filter, clear_filters and list_filters are deprecated in favour of per-call params.

  • Clients that pin an exact tool list (for example a .claude/agents/*.md allowlist containing mcp__perplexity__model_info) need the new names added.

  • set_model requires model; pass "auto" to reset. Under model_info, calling with no arguments reset the selection.

  • The header line now names the effort level and the version that ran. On the legacy backend it reads [Using model: X (legacy Sonar backend) - ...].

  • At effort low and above, inline citations look like [web:N]. Sources are still numbered [N].

  • These params have no effect on the default backend and are reported under "Backend notes": search_language_filter, stream_mode, image_results_enhanced_relevance, return_related_questions, search_type: "auto", stop, enable_search_classifier.

  • return_images now actually returns images, billed at about $0.0025 per image search.

  • disable_search answers with perplexity/sonar, and the domain, recency and date filters are ignored.

  • A recency filter (stateful or per-call) combined with search_after_date / search_before_date is dropped, with a note.

  • A per-call search_domain_filter that mixes allow and - entries, has more than 20 entries or has empty entries is rejected, as is a malformed effort.

Background research

  • async_research_submit returns resp_... ids, which also work with agent_retrieve and agent_cancel.

  • Status values are lowercase (queued, in_progress, completed, failed, incomplete, cancelled) instead of COMPLETED / FAILED. The 7-day expiry line is gone.

  • list shows only runs submitted since the server process started, plus legacy async jobs.

  • On the agent backend all four Sonar models are accepted and mapped to an effort level.

agent

  • preset is replaced by effort, which takes the same level names. preset still works as an alias, and effort wins if both are set. wide-research now runs xhigh.

  • max_steps goes up to 500 (was 100).

  • The output header now includes the effort version and service tier.

  • More than 5 queries, empty strings in a query array, and max_results over 20 (over 50 for people) are now rejected client-side. The API rejected them anyway.

Embeddings

  • Omitting encoding_format gives base64_int8. There never was a full-precision float output.

Results

  • Data tools return structuredContent alongside the text. Clients that validate results against outputSchema get typed data.

  • agent_files content returns text, not a base64 blob, for UTF-8 text types.

  • resources/read for an unknown or malformed perplexity-agent-file:// URI, or one the API answers with 400/404, now returns JSON-RPC error -32602 (Invalid Params) instead of -32002. The message still starts Resource not found:.

Runtime

  • The server is built on MCP SDK v2 (@modelcontextprotocol/server). Node.js versions before 20 are no longer supported.

  • Over stdio it serves both protocol eras: the initialize handshake for 2024-10-07, 2024-11-05, 2025-03-26, 2025-06-18 and 2025-11-25 (Claude Code negotiates 2025-11-25), and the stateless 2026-07-28 era, which starts with server/discover. In 2026-07-28, instructions come back on server/discover, and resource list_changed notifications go out only on a subscriptions/listen stream the client opens.

  • Install and run commands, the build/index.js entrypoint, env vars, tool names and result shapes are unchanged.

Development

npm run build   # compile TypeScript to build/
npm start       # run the built server on stdio
npm test        # build, then run the node:test suite (no network)

The unit tests use fakes and never call the API. A separate script checks every request parameter against the live API, because the SDK's types are not reliable enough to catch a misnamed field:

PERPLEXITY_API_KEY=... node scripts/validate-params.mjs                    # cheap checks
PERPLEXITY_API_KEY=... node scripts/validate-params.mjs --include-costly   # adds priority tier, sandbox file round-trip, legacy async submit

It prints PASS, FAIL or SKIP per check. Legacy Sonar canaries print OK or LOST, which is informational. The MCP approval round-trip runs against a public server by default; set PROBE_APPROVAL_MCP_URL=skip to skip it.

Packaging:

  • npm run pack:mcpb builds the MCPB bundle into dist/mcpb/ (gitignored). The script does a production-only install, runs mcpb validate and mcpb pack, then unpacks the bundle and runs a smoke test.

  • npm run mcpb:manifest regenerates the version and tools fields of manifest.json from package.json and the built server's tools/list (--check fails if they are stale). Don't hand-edit those two fields.

Source is in src/. After editing, rebuild and restart your MCP client to load the changes.

License

MIT

Available Tools

6 tools
clear_filtersA

Remove all domain filters (both allowed and blocked). Use when switching search contexts or starting fresh. Does not affect recency filter.

Inputs: no named parameters.

domain_filterA

Configure domain filtering for search results. Use 'allow' to prioritize trusted sources (e.g., documentation sites, academic domains) or 'block' to exclude unreliable sources. Maximum 20 domains total. Filters persist across searches until cleared.

Inputs: domain (required), action (required).

list_filtersA

Display current filter configuration including allowed domains, blocked domains, and active recency setting. Useful for debugging search behavior.

Inputs: no named parameters.

model_infoA

View available Perplexity models and their specializations, or manually override model selection. By default, models are auto-selected based on query intent (research, reasoning, general search).

Inputs: model.

recency_filterA

Control the time window for search results. Essential for time-sensitive queries like news, updates, or recent developments. Filter persists until changed.

Inputs: filter (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: clear_filters removes filters, domain_filter configures domains, list_filters displays current settings, model_info shows models, recency_filter controls time windows, and search performs web searches. The descriptions reinforce these unique roles, making misselection unlikely.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case (e.g., clear_filters, domain_filter, list_filters, model_info, recency_filter, search). The naming is predictable and readable throughout, with no deviations or mixed conventions.

    Tool Count5/5

    With 6 tools, this server is well-scoped for its purpose of configuring and executing Perplexity AI searches. Each tool earns its place by covering essential aspects like filtering, model selection, and search execution, without being overly sparse or bloated.

    Completeness5/5

    The tool set provides complete coverage for the domain of Perplexity AI search configuration and execution. It includes setup (filters, model info), control (recency, domain filters), status (list_filters), and core functionality (search), with no obvious gaps that would cause agent failures.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
      2
      566
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables AI assistants to perform web searches on Perplexity.ai using browser automation instead of an official API. It supports persistent authenticated sessions and returns search results along with cited sources directly to the client.
      3
      46 npm
      14
      MIT