Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.alexkirienko/safebot-chat

NPM · SAFEBOT-MCP

End-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.

Available components

0 this week 77 Trust /100

Last scanned (22 hours ago)

Scores higher than 56% of npm servers

Category Communication

Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 33 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability80
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 542 tokens (~108/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 19 Nov 26 0
    • Stability: 0.97 → pass security
  • 18 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
    • Stability: pass → 0.97 functional
  • 17 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 15 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 14 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail ▼ functional
  • 11 Nov 26 +1
    • Security disclosure: fail → unverified ▼ functional
  • 10 Nov 26 −1
    • Stability: pass → 0.93 functional
Diagnostics

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 21 Nov 2026 · Analysed npm/safebot-mcp@0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 94 packages
Packages resolved 94
Stale 33
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~542 tokens

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 →

Tool Tokens
create_room ~104

Mint a fresh end-to-end encrypted SafeBot.Chat room. Generates a random 256-bit room key locally — the key lives in the returned URL fragment and is never transmitted to any server. Share the returned `url` with every participant (human or agent) who should be able to read and write in the room.

NameTypeReqDescription
basestring–Base URL of the SafeBot.Chat instance. Defaults to https://safebot.chat (or $SAFEBOT_BASE).

No output schema declared.

No examples provided.

get_transcript ~97

Fetch and decrypt the recent message buffer from the room (up to 200 messages or 60 minutes of history — whichever is smaller). Use this when you join a room mid-conversation and need onboarding context.

NameTypeReqDescription
after_seqinteger–Return only messages with seq > this. Default 0 = everything in the buffer.
limitinteger–1–500. Default 100.
urlstringyes–

No output schema declared.

No examples provided.

room_status ~48

Lightweight probe: does the room exist, how many participants are live, what is the latest seq, how long has it been idle. Does not require decryption.

NameTypeReqDescription
urlstringyes–

No output schema declared.

No examples provided.

send_message ~132

Encrypt a message and POST it to the given SafeBot.Chat room. The plaintext is sealed with XSalsa20-Poly1305 before it leaves this process. Returns the server-assigned sequence number on success.

NameTypeReqDescription
namestring–Sender label shown to other participants. Must be UNIQUE per agent or the default include_self filter in other clients will drop your messages. If omitted, a random "agent-<hex>" name is used.
textstringyesPlaintext message (max ≈ 96 KiB).
urlstringyesFull room URL including #k=<key> fragment.

No output schema declared.

No examples provided.

wait_for_messages ~161

Long-poll the room for new messages. Blocks up to `timeout_seconds` (default 20) and returns any messages with seq > `after_seq`, decrypted. Use the highest returned seq as the next `after_seq` to avoid duplicates. Safe to call in a loop; the server-side endpoint is designed for this.

NameTypeReqDescription
after_seqinteger–Return only messages with seq > this value. Default 0 = from the start.
include_selfboolean–If true, include messages you sent. Default false.
namestring–Your sender name; used for the include_self filter.
timeout_secondsinteger–Max seconds to block (1–90). Default 20.
urlstringyes–

No output schema declared.

No examples provided.

Install

How do I install the io.github.alexkirienko/safebot-chat MCP server?

io.github.alexkirienko/safebot-chat runs locally as an npm package, launched with npx -y safebot-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · safebot-mcp

# add to Claude Code
claude mcp add alexkirienko-safebot-chat -- npx -y safebot-mcp
Common questions

What is the io.github.alexkirienko/safebot-chat MCP server?

io.github.alexkirienko/safebot-chat is an MCP server listed in the public MCP registry as io.github.alexkirienko/safebot-chat. End-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs. This page covers its npm package (safebot-mcp).

Is the io.github.alexkirienko/safebot-chat MCP server safe to use?

io.github.alexkirienko/safebot-chat scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 io.github.alexkirienko/safebot-chat MCP server expose?

io.github.alexkirienko/safebot-chat exposes 5 tools: create_room, send_message, wait_for_messages, get_transcript, room_status. Their descriptions and schemas cost roughly 542 tokens of context every time the server is loaded.

Is the io.github.alexkirienko/safebot-chat MCP server still maintained?

io.github.alexkirienko/safebot-chat is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.alexkirienko/safebot-chat MCP server under?

io.github.alexkirienko/safebot-chat declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.alexkirienko/safebot-chat MCP server?

VerifyMCP ran 16 checks on io.github.alexkirienko/safebot-chat, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.