Perplexity Agent
PYPI · PERPLEXITY-AGENT-MCP · SCANNED SEP 20
Multi-step web research with citations via Perplexity's Agent API. Standard library only.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency35
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (BSD License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 48 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 443 tokens (~147/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Perplexity Agent MCP server?
Perplexity Agent runs locally as a PyPI package, launched with uvx perplexity-agent-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · perplexity-agent-mcp
claude mcp add zalez-perplexity-agent-mcp -- uvx perplexity-agent-mcp
{
"mcpServers": {
"zalez-perplexity-agent-mcp": {
"command": "uvx",
"args": [
"perplexity-agent-mcp"
]
}
}
} {
"servers": {
"zalez-perplexity-agent-mcp": {
"command": "uvx",
"args": [
"perplexity-agent-mcp"
]
}
}
} codex mcp add zalez-perplexity-agent-mcp -- uvx perplexity-agent-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"zalez-perplexity-agent-mcp": {
"type": "local",
"command": [
"uvx",
"perplexity-agent-mcp"
],
"enabled": true
}
}
} openclaw mcp add zalez-perplexity-agent-mcp --command uvx --arg perplexity-agent-mcp
mcp_servers:
zalez-perplexity-agent-mcp:
command: "uvx"
args: ["perplexity-agent-mcp"] {
"McpServers": {
"zalez-perplexity-agent-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"perplexity-agent-mcp"
]
}
}
} assistant mcp add zalez-perplexity-agent-mcp -t stdio -c uvx -a perplexity-agent-mcp
{
"mcpServers": {
"zalez-perplexity-agent-mcp": {
"command": "uvx",
"args": [
"perplexity-agent-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −2
- Stability: pass → 0.83 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/perplexity-agent-mcp@0.4.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
perplexity_agent Perplexity Agent Research ~196
Run a research query through Perplexity's Agent API (multi-step web research with citations). Use for deep or multi-hop questions where a single synthesized, sourced answer is wanted. With wait=true (default) this blocks until the answer is ready; if it takes too long you get a response_id to collect later with perplexity_agent_result.
| Name | Type | Req | Description |
|---|---|---|---|
| domains | array | – | Restrict sources to these domains. Prefix with '-' to exclude. Allowlist or denylist, not both. |
| preset | string | – | Research depth: fast, low, medium, high, xhigh, wide-research. Deeper takes longer. |
| query | string | yes | The research question. |
| recency | string | – | Only use sources published within this window. |
| wait | boolean | – | Block until the answer is ready. Set false to get a response_id immediately — useful for running several deep queries in parallel while you do other work. |
No output schema declared.
No examples provided.
perplexity_agent_cancel Cancel Perplexity Research ~62
Ask Perplexity to stop a research run that is no longer needed. Perplexity does not report usage for cancelled runs, so this cannot tell you whether it changed your bill.
| Name | Type | Req | Description |
|---|---|---|---|
| response_id | string | yes | The response_id from perplexity_agent. |
No output schema declared.
No examples provided.
perplexity_agent_result Collect Perplexity Research ~114
Retrieve the result of a research run started by perplexity_agent. If it is still running, reports what it has done so far and how to check again.
| Name | Type | Req | Description |
|---|---|---|---|
| response_id | string | yes | The response_id from perplexity_agent. |
| wait_seconds | integer | – | Block up to this many seconds waiting for completion. 0 checks once. A larger value is silently CLAMPED to this server's configured wait budget (55s here; set PERPLEXITY_AGENT_WAIT_SECONDS to raise i… |
No output schema declared.
No examples provided.
What is the Perplexity Agent MCP server?
Perplexity Agent is an MCP server listed in the public MCP registry as io.github.zalez/perplexity-agent-mcp. Multi-step web research with citations via Perplexity's Agent API. Standard library only. This page covers its PyPI package (perplexity-agent-mcp).
Is the Perplexity Agent MCP server safe to use?
Perplexity Agent scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Perplexity Agent MCP server expose?
Perplexity Agent exposes 3 tools: perplexity_agent, perplexity_agent_result, perplexity_agent_cancel. Their descriptions and schemas cost roughly 372 tokens of context every time the server is loaded.
Is the Perplexity Agent MCP server still maintained?
Perplexity Agent is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.