pyunto-agentSAFE
Invite an AI agent into a Pyunto diary: replies in the thread or serves Claude via MCP. Decrypts only on your machine.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Make an external agent the partner of a Pyunto exchange diary. The agent is an ordinary member: its own Pyunto account, its own X25519 identity key, invited with the normal invite link. The server is unchanged and never sees plaintext; decryption happens in this process.
**Pyunto for iPhone and iPad** · **Pyunto for Android** · **pyunto-robotics** — the same idea, with a robot at the other end (watch it, 100 s)
A real run with Claude Code as the model: a strength-coach persona in a Markdown file, and a client logging sessions from their phone. The second reply compares with the day before. [Watch the full 90-second video](https://pyunto.com/media/coach-demo.mp4).
Two kinds of agent
The same package, the same account, the same keys. What differs is who starts the conversation.
1. Agent — it writes to your users
You write; it replies, unprompted, in the same thread.
your phone your computer ┌───────────────┐ ┌──────────────────────┐ │ Pyunto app │ │ pyunto-agent run │ │ │ │ │ │ "tough day │ ───────▶ │ reads the entry │ │ at work" │ encrypted │ decrypts it HERE │ │ │ │ │ │ │ │ │ ▼
bb0aa7588893OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add pyunto-agent --env PYUNTO_PASSWORD=${PYUNTO_PASSWORD} -- uvx pyunto-agent==0.3.0 mcpTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (6)
nonce = base64.b64decode(_normalize_b64(enc.nonce))
ciphertext = base64.b64decode(_normalize_b64(enc.ciphertext))
key = base64.b64decode(_normalize_b64(s))
combined = base64.b64decode(_normalize_b64(enc.ciphertext))
nonce = base64.b64decode(_normalize_b64(enc.nonce))
Gates applied: no_behavioural_pass.
bb0aa7588893full audit observations/trust-audit/mcp-server/utagoeinc__pyunto-agent.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | bb0aa7588893 | SAFE | B | 89 | first audit |
Questions
What is the pyunto-agent MCP server?
Invite an AI agent into a Pyunto diary: replies in the thread or serves Claude via MCP. Decrypts only on your machine.
Is pyunto-agent safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does pyunto-agent need?
It reads ANTHROPIC_API_KEY, PYUNTO_AGENT_SECRET and PYUNTO_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does pyunto-agent run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as pyunto-agent.
How current is this page?
The grade is for one exact copy of the source (bb0aa7588893), read on 2026-10-11. The repository is watched and re-audited when it changes.