Skip to content

Behalf (PXP v0) MCP server

io.github.JulesNsenda/behalfJulesNsendastreamable-httpv0.2.0Scanned

Negotiate for your human under PXP: tagged claims, escalation, decision brief, hash-chained ledger

8 tools: 1 do something that can't be undone, 4 change things and 3 only read.

Tools: 0 delete, 1 irreversible, 4 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 8
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Behalf (PXP v0) MCP server can do

The Behalf (PXP v0) MCP server is published by the GitHub account JulesNsenda. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_envelope) and create or change data (4 tools: create_room, join_room, seal_intent_card and answer_escalation), but cannot delete data. 3 tools only read.

8 tools bring in text other people can write (create_room, join_room, seal_intent_card and 5 more); 1 tool can send data out of your system (send_envelope).

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 15, 2026, version 0.2.0.

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.

8 tools

Can't be undone 1Claude Code: ask
  • send_envelopeSend one PXP envelope on your turn.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_envelope" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_envelope" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send one PXP envelope on your turn. The server enforces the rules: untagged or unreferenced claims become "assumed", agreeing while raising a conflict is refused. The enforced envelope is returned.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 4Claude Code: ask
  • answer_escalationWhen the room is paused for your principal, ask them the question verbatim and relay their exact answer.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    When the room is paused for your principal, ask them the question verbatim and relay their exact answer. It is sealed into their card as an amendment. Never answer on their behalf.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • create_roomOpen a new room.Reads text others writeNo findings

    Why it is in this group

    • The name "create_room" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Open a new room. Your principal takes seat A, and you get a private invite link for the other person (seat B). Send the invite only to that person. Use this when your principal wants to negotiate with someone and has no room yet. This server requires sign-in: your MCP client must send your principal's agent key as an Authorization: Bearer header (not as an argument). Your principal gets a key at https://behalf.dropkit.sh/key. No passcode is needed. counterpart_proxy "builtin" also needs "Use our AI" access, which your principal asks for at https://behalf.dropkit.sh/start; without it, use "external".

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • join_roomTake your principal's seat with their private link.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Take your principal's seat with their private link. Returns the room state, your principal's card (if sealed), and what to do next.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: true
  • seal_intent_cardSeal your principal's Intent Card.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Seal your principal's Intent Card. Only after they confirmed every line. Once sealed it cannot change except through escalation answers.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_briefThe decision brief once the room has ended: agreed terms, authority per term, unverified assumptions, escalations, ledger head.Reads text others writeNo findings

    Why it is in this group

    • The name "get_brief" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The decision brief once the room has ended: agreed terms, authority per term, unverified assumptions, escalations, ledger head.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_roomCurrent state from your seat: status, whose turn, transcript, claims you still need to review, unverified assumptions, and the next action.Reads text others writeNo findings

    Why it is in this group

    • The name "get_room" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Current state from your seat: status, whose turn, transcript, claims you still need to review, unverified assumptions, and the next action.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • wait_for_turnBlocks up to timeout_seconds (max 25) until it is your turn, your principal must answer a question, or the room ends.Reads text others writeNo findings

    Why it is in this group

    • The name "wait_for_turn" says "wait": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Blocks up to timeout_seconds (max 25) until it is your turn, your principal must answer a question, or the room ends. Call it again if it times out.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write8
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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, 18:58 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
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
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 5 tools that change things (1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://behalf.dropkit.sh/mcp: tools/list returned 8 tools to an anonymous client, including send_envelope (irreversible), create_room (write), join_room (write), seal_intent_card (write), answer_escalation (write)

    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 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http behalf https://behalf.dropkit.sh/mcp
claude mcp add --transport http behalf https://behalf.dropkit.sh/mcp

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__behalf__get_room",
      "mcp__behalf__wait_for_turn",
      "mcp__behalf__get_brief"
    ],
    "ask": [
      "mcp__behalf__create_room",
      "mcp__behalf__join_room",
      "mcp__behalf__seal_intent_card",
      "mcp__behalf__send_envelope",
      "mcp__behalf__answer_escalation"
    ],
    "deny": []
  }
}

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 behalf. Review it before you use it.

Capability tags behind 8 rules
  • mcp__behalf__create_room untrusted-input
  • mcp__behalf__join_room untrusted-input
  • mcp__behalf__seal_intent_card untrusted-input
  • mcp__behalf__get_room untrusted-input
  • mcp__behalf__wait_for_turn untrusted-input
  • mcp__behalf__send_envelope untrusted-input, outbound
  • mcp__behalf__answer_escalation untrusted-input
  • mcp__behalf__get_brief untrusted-input

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/io.github.JulesNsenda/behalf/verify?hash=41da627d9387b3df97e3c449f2c086ebc73ad46f4a99910eaef444b7cab79f41" | jq -e '.changed == false'

Pinned hash 41da627d9387, from Nov 15, 2026, 23:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.JulesNsenda/behalf/changes.xml

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

Badge

Anlyon Radar badge for io.github.JulesNsenda/behalf
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.JulesNsenda/behalf.svg)](https://radar.anlyon.com/servers/io.github.JulesNsenda/behalf)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.

Behalf (PXP v0) MCP server: questions and answers

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

Is the Behalf (PXP v0) MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 5 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 Behalf (PXP v0) MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Behalf (PXP v0) MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_envelope.

What tools does the Behalf (PXP v0) MCP server have?

8 tools: 1 irreversible, 4 write, 3 read. send_envelope, create_room, join_room, seal_intent_card, answer_escalation, get_room, wait_for_turn and get_brief.

Does the Behalf (PXP v0) MCP server need sign-in or OAuth?

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

Does the Behalf (PXP v0) MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_envelope.

Has the Behalf (PXP v0) MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.