Skip to content

PZERO MCP server

studio.pzero/mcppzero.studiostreamable-httpv1.0.0Scanned

Prepaid inference for agents over hosted MCP. Chat, image, and video.

18 tools: 3 can delete or cancel things, 9 change things and 6 only read.

Tools: 3 delete, 0 irreversible, 9 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

12 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the PZERO MCP server can do

The PZERO MCP server is published by pzero.studio, a domain the MCP Registry verified. It has 18 tools. It can delete or cancel things (3 tools: generate_video, revoke_key and video_queue) and create or change data (9 tools: chat_completions, create_key, funding_instructions, generate_image and 5 more). 6 tools only read.

4 tools can send data out of your system (chat_completions, video_complete, video_queue and 1 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

18 tools

Deletes or cancels 3Claude Code: deny
  • generate_videoIntent tool: POST /v1/video/queue (settles then enqueues).No findings

    Why it is in this group

    • The name "generate_video" says "generate": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Intent tool: POST /v1/video/queue (settles then enqueues). Returns queue_id + cost. Confirm before calling — this spends prepaid USDC. Poll with get_generation_status or wait_for_video.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • readOnlyHint: false
  • revoke_keyDELETE /v1/agent/keys/{id} — irreversible.No findings

    Why it is in this group

    • The name "revoke_key" says "revoke": a word for removing or ending something.
    • The description says "irreversible".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    DELETE /v1/agent/keys/{id} — irreversible. Do not revoke the key used by this MCP session unless intentional.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • readOnlyHint: false
  • video_queuePOST /v1/video/queue — paid settle+enqueue.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "post": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • outboundThe description's first verb is "post": it sends or publishes something to other people.
    Description, as the server wrote it
    POST /v1/video/queue — paid settle+enqueue. Prefer generate_video for agents.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • readOnlyHint: false
Changes things 9Claude Code: ask
  • chat_completionsPOST /v1/chat/completions (buffered).Can send data outNo findings

    Why it is in this group

    • The description's first verb is "post": a word for a change.

    What it can reach

    • outboundThe description's first verb is "post": it sends or publishes something to other people.
    Description, as the server wrote it
    POST /v1/chat/completions (buffered). Pass a live model id from get_models. Returns completion plus cost trace headers.
  • create_keyPOST /v1/agent/keys — mint another key.No findings

    Why it is in this group

    • The name "create_key" says "create": a word for a change.
    Description, as the server wrote it
    POST /v1/agent/keys — mint another key. Does NOT add USDC credit. Plaintext shown once.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • readOnlyHint: false
  • funding_instructionsHow to fund a PZERO account and authenticate MCP.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    How to fund a PZERO account and authenticate MCP. MCP never accepts payment or wallet keys. Fund via Studio x402 top-up or agent HTTP signup/refill, then use Authorization Bearer pzero_…
  • generate_imagePOST /v1/image/generate — intent tool for image generation.No findings

    Why it is in this group

    • The name "generate_image" says "generate": a word for a change.
    Description, as the server wrote it
    POST /v1/image/generate — intent tool for image generation. Rejects enable_web_search. Returns images plus cost trace.
  • get_generation_statusPOST /v1/video/retrieve once — JSON status or delivered MP4.No findings

    Why it is in this group

    • The name "get_generation_status" says "get": a word for reading.
    • The description's first verb is "post": a word for a change.
    Description, as the server wrote it
    POST /v1/video/retrieve once — JSON status or delivered MP4.
  • set_max_pricePATCH /v1/agent/max-price — raise/lower ceiling (30-80).No findings

    Why it is in this group

    • The name "set_max_price" says "set": a word for a change.
    Description, as the server wrote it
    PATCH /v1/agent/max-price — raise/lower ceiling (30-80). Use when tools return no_eligible_supply with cheapest_posted_cents. Does not auto-apply.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • readOnlyHint: false
  • video_completePOST /v1/video/complete — optional cleanup after retrieve.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "post": a word for a change.

    What it can reach

    • outboundThe description's first verb is "post": it sends or publishes something to other people.
    Description, as the server wrote it
    POST /v1/video/complete — optional cleanup after retrieve.
  • video_quotePOST /v1/video/quote — no settle, no job.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "post": a word for a change.

    What it can reach

    • outboundThe description's first verb is "post": it sends or publishes something to other people.
    Description, as the server wrote it
    POST /v1/video/quote — no settle, no job. Check clears_now vs price ceiling vs funding before queue.
  • video_retrievePOST /v1/video/retrieve — power-user status/media poll.No findings

    Why it is in this group

    • The name "video_retrieve" says "retrieve": a word for reading.
    • The description's first verb is "post": a word for a change.
    Description, as the server wrote it
    POST /v1/video/retrieve — power-user status/media poll.
Only reads 6Show 6 read-only tools
  • agent_meGET /v1/agent/me — balances, key prefix, max price.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    GET /v1/agent/me — balances, key prefix, max price. Pending USDC is not spendable until confirmed. If confirmed is low, call funding_instructions.
  • get_capacityGET /v1/capacity — routable DIEM and price bands before funding or spend decisions.No findings

    Why it is in this group

    • The name "get_capacity" says "get": a word for reading.
    Description, as the server wrote it
    GET /v1/capacity — routable DIEM and price bands before funding or spend decisions.
  • get_modelsGET /v1/models — resolve a live model id before inference.No findings

    Why it is in this group

    • The name "get_models" says "get": a word for reading.
    Description, as the server wrote it
    GET /v1/models — resolve a live model id before inference. Optional id retrieves one public row (same object as that id in the list). Do not hardcode model ids.
  • get_requestGET /v1/agent/requests/{support_reference} — recover cost/trace for a prior request.No findings

    Why it is in this group

    • The name "get_request" says "get": a word for reading.
    Description, as the server wrote it
    GET /v1/agent/requests/{support_reference} — recover cost/trace for a prior request.
  • list_keysGET /v1/agent/keys — list active API key metadata (never plaintext).No findings

    Why it is in this group

    • The name "list_keys" says "list": a word for reading.
    Description, as the server wrote it
    GET /v1/agent/keys — list active API key metadata (never plaintext).
  • wait_for_videoPoll video retrieve until delivered or failed.No findings

    Why it is in this group

    • The name "wait_for_video" says "wait": a word for reading.
    Description, as the server wrote it
    Poll video retrieve until delivered or failed. Backs off on 502.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:19 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
12
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.pzero.studio/.well-known/oauth-protected-resource/mcp
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 12 tools that change things (3 destructive, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.pzero.studio/mcp: tools/list returned 18 tools to an anonymous client, including generate_video (destructive), revoke_key (destructive), video_queue (destructive), chat_completions (write), create_key (write) and 7 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http pzero https://mcp.pzero.studio/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http pzero https://mcp.pzero.studio/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__pzero__agent_me",
      "mcp__pzero__get_capacity",
      "mcp__pzero__get_models",
      "mcp__pzero__get_request",
      "mcp__pzero__list_keys",
      "mcp__pzero__wait_for_video"
    ],
    "ask": [
      "mcp__pzero__chat_completions",
      "mcp__pzero__create_key",
      "mcp__pzero__funding_instructions",
      "mcp__pzero__generate_image",
      "mcp__pzero__get_generation_status",
      "mcp__pzero__set_max_price",
      "mcp__pzero__video_complete",
      "mcp__pzero__video_quote",
      "mcp__pzero__video_retrieve"
    ],
    "deny": [
      "mcp__pzero__generate_video",
      "mcp__pzero__revoke_key",
      "mcp__pzero__video_queue"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as pzero. Review it before you use it.

Capability tags behind 4 rules
  • mcp__pzero__chat_completions outbound
  • mcp__pzero__video_complete outbound
  • mcp__pzero__video_queue outbound
  • mcp__pzero__video_quote outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/studio.pzero/mcp/verify?hash=e792b6864df2e299bd63747437831af56d759ba418f5becb1bc860a6f6719c67" | jq -e '.changed == false'

Pinned hash e792b6864df2, from Nov 19, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/studio.pzero/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for studio.pzero/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/studio.pzero/mcp.svg)](https://radar.anlyon.com/servers/studio.pzero/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.

PZERO MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the PZERO MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 12 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the PZERO MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: generate_video, revoke_key and video_queue.

Can the PZERO MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the PZERO MCP server have?

18 tools: 3 destructive, 9 write, 6 read. generate_video, revoke_key, video_queue, chat_completions, create_key, funding_instructions, generate_image, get_generation_status and 10 more.

Does the PZERO MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the PZERO MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): chat_completions, video_complete, video_queue and video_quote.

Has the PZERO MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.