← Index

Perplexity Agent

io.github.zalez/perplexity-agent-mcpv0.3.1AI & LLMs

Multi-step web research with citations via Perplexity's Agent API. Standard library only.

In-path gate · all MCP tools

Using Perplexity Agent in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Auditable install path →Watch it hold a drift →
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-28).

Contracts can change after screening, with no version bump. The gate pins Perplexity Agent’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
PERPLEXITY_API_KEY
requiredsecret

Your Perplexity API key. Read at call time and sent only as an Authorization header to api.perplexity.ai; never logged or echoed.

PERPLEXITY_AGENT_WAIT_SECONDS

How long a blocking call waits before handing back a response_id to collect later. Defaults to 55, just inside Claude Desktop's unconfigurable 60s tool-call timeout. Raise to 300 on clients without that limit.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
5
Alternatives in AI & LLMs
ai.boundaryai/boundaryai
ai.boundaryai/boundaryai

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

OpenAI Tools MCP Server
ai.com.mcp/openai-tools

Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.

Entity Enricher
ai.entityenricher/enricher

Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.