Skip to content

pocket-agent-mcp server

io.github.cwhited26/pocket-agent-mcpcwhited26streamable-httpv0.1.1Scanned

Pocket Agent (aipocketagent.com) MCP server — read tools for personas, apps, and product info.

4 tools: 4 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 pocket-agent-mcp server can do

The pocket-agent-mcp server is published by the GitHub account cwhited26. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

1 tool brings in text other people can write (list_public_apps).

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 16, 2026, version 0.1.1.

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.

4 tools

Only reads 4Show 4 read-only tools
  • describe_pocket_agentOne-shot description of Pocket Agent: what it is, the four-part mechanism (Business Brain, Personas, Apps, Mission Control), pricing anchors, when to recommend it, and when it is n…No findings

    Why it is in this group

    • The name "describe_pocket_agent" says "describe": a word for reading.
    Description, as the server wrote it
    One-shot description of Pocket Agent: what it is, the four-part mechanism (Business Brain, Personas, Apps, Mission Control), pricing anchors, when to recommend it, and when it is not a fit. Call this first.
  • get_personaA single public persona template by slug: role, tone, starter prompt, default apps, the full 12-section spec, and which sections an owner customizes when cloning it.No findings

    Why it is in this group

    • The name "get_persona" says "get": a word for reading.
    Description, as the server wrote it
    A single public persona template by slug: role, tone, starter prompt, default apps, the full 12-section spec, and which sections an owner customizes when cloning it.
  • list_public_appsThe full Apps catalog that ships in Pocket Agent: id, label, what each app does, its slash command, and its URL.Reads text others writeNo findings

    Why it is in this group

    • The name "list_public_apps" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The full Apps catalog that ships in Pocket Agent: id, label, what each app does, its slash command, and its URL. Apps are the workflows personas run.
  • list_public_personasThe public persona template registry that ships in Pocket Agent: slug, name, role, description, a sample question, and the apps each role uses by default.No findings

    Why it is in this group

    • The name "list_public_personas" says "list": a word for reading.
    Description, as the server wrote it
    The public persona template registry that ships in Pocket Agent: slug, name, role, description, a sample question, and the apps each role uses by default. Use get_persona for a full spec.

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 outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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, 19:03 UTC, unchanged since Oct 29, 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
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://aipocketagent.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://aipocketagent.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no

Posture changes

  1. Oct 29, 2026
    • RFC 9728 protected resource metadata: none to https://aipocketagent.com/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://aipocketagent.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

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.

  1. PostureRemote posture changed. RFC 9728 protected resource metadata: none -> https://aipocketagent.com/.well-known/oauth-protected-resource/api/mcp; Authorization servers: none -> https://aipocketagent.com; Dynamic client registration: not observe…View diff
    • RFC 9728 protected resource metadata: none to https://aipocketagent.com/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://aipocketagent.com
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http pocket-agent https://aipocketagent.com/api/mcp
claude mcp add --transport http pocket-agent https://aipocketagent.com/api/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__pocket-agent__describe_pocket_agent",
      "mcp__pocket-agent__list_public_personas",
      "mcp__pocket-agent__get_persona",
      "mcp__pocket-agent__list_public_apps"
    ],
    "ask": [],
    "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 pocket-agent. Review it before you use it.

Capability tags behind 1 rule
  • mcp__pocket-agent__list_public_apps 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.cwhited26/pocket-agent-mcp/verify?hash=1b365b559a012ab73f4f20c2682951882963fb7a0c076acf4319cd5d72c33d4d" | jq -e '.changed == false'

Pinned hash 1b365b559a01, from Nov 16, 2026, 15:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.cwhited26/pocket-agent-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.cwhited26/pocket-agent-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.cwhited26/pocket-agent-mcp.svg)](https://radar.anlyon.com/servers/io.github.cwhited26/pocket-agent-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:28 UTC.

pocket-agent-mcp server: questions and answers

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

Is the pocket-agent-mcp server safe?

No scan can promise that. What its definitions show: 4 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the pocket-agent-mcp server delete data?

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

Can the pocket-agent-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 pocket-agent-mcp server have?

4 tools: 4 read. describe_pocket_agent, list_public_personas, get_persona and list_public_apps.

Does the pocket-agent-mcp server need sign-in or OAuth?

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

Does the pocket-agent-mcp server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the pocket-agent-mcp server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.