# Puenteo (pypi · puenteo)

Let coding agents talk: search every agent session's history and message live sessions.

- Trust score: 60/100 (medium)
- Change this week: +37
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `puenteo`: 60/100 (this document), [markdown](https://verifymcp.io/servers/mano7onam-puenteo/puenteo.md), [page](https://verifymcp.io/servers/mano7onam-puenteo/puenteo)

## Channel facts

- Registry: `pypi`
- Package: `puenteo`
- Version: `0.13.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 94/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Declares code that runs automatically (setup.py) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1266 tokens (~57/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 70/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 11% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 23 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Puenteo MCP server?

Puenteo runs locally as a PyPI package, launched with uvx puenteo. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mano7onam-puenteo -- uvx puenteo
```

### Cursor

```json
{
  "mcpServers": {
    "mano7onam-puenteo": {
      "command": "uvx",
      "args": [
        "puenteo"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mano7onam-puenteo": {
      "command": "uvx",
      "args": [
        "puenteo"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mano7onam-puenteo -- uvx puenteo
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mano7onam-puenteo": {
      "type": "local",
      "command": [
        "uvx",
        "puenteo"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mano7onam-puenteo --command uvx --arg puenteo
```

### Hermes

```yaml
mcp_servers:
  mano7onam-puenteo:
    command: "uvx"
    args: ["puenteo"]
```

### Netclaw

```json
{
  "McpServers": {
    "mano7onam-puenteo": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "puenteo"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mano7onam-puenteo -t stdio -c uvx -a puenteo
```

### Other

```json
{
  "mcpServers": {
    "mano7onam-puenteo": {
      "command": "uvx",
      "args": [
        "puenteo"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-14 (score 60, +22)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 11
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass

### 2026-10-13 (score 38, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-12 (score 23, 0)

- [functional] Package version: 0.9.1 → 0.13.0

### 2026-10-08 (score 23)

First indexed and scored.

## MCP tools (22)

### `whoami` (~29 tokens)

Your own session address on the puenteo bus (agent:session_id), cwd, and unread count.

### `sessions` (~77 tokens)

List past/recent agent sessions (all vendors) newest first. Use before outline/pull.

Input parameters:

- `cwd` (string): Project path filter ('.' = current)
- `limit` (integer)
- `provider` (string): claude,codex,gemini,… (comma list)
- `since` (string): YYYY-MM-DD

### `search` (~75 tokens)

Full-text search across every local agent session (ranked). Excludes your own session by default.

Input parameters:

- `cwd` (string)
- `include_self` (boolean)
- `limit` (integer)
- `provider` (string)
- `query` (string, required)
- `session` (string): Limit to one session ref

### `outline` (~29 tokens)

Map of one session: counts, time span, milestone messages with indexes.

Input parameters:

- `session` (string, required)

### `pull` (~85 tokens)

Compact context pack from another session. mode: handoff (default) | query | decisions | errors | code | last | around.

Input parameters:

- `around` (integer)
- `max_chars` (integer)
- `mode` (string)
- `query` (string)
- `radius` (integer)
- `session` (string, required)
- `top_k` (integer)

### `show` (~48 tokens)

Raw messages of a session by index range (from outline/search).

Input parameters:

- `end` (integer)
- `last` (integer)
- `session` (string, required)
- `start` (integer)

### `peers` (~44 tokens)

Agent sessions running right now on this machine (any vendor), with how to reach them.

Input parameters:

- `agent` (string)
- `cwd` (string): '.' = only my project

### `send` (~85 tokens)

Message other live sessions. to: 'claude:<id>' (prefix ok) | '@name' | '#channel' | 'agent:codex' | 'cwd:.' | '*'. Set wait_s to block for a reply.

Input parameters:

- `text` (string, required)
- `thread` (string)
- `to` (string, required)
- `wait_s` (number)

### `reply` (~44 tokens)

Reply to a message id (routes back to the sender or its channel).

Input parameters:

- `id` (string, required)
- `text` (string, required)
- `wait_s` (number)

### `inbox` (~35 tokens)

Read messages other sessions sent you (marks them read).

Input parameters:

- `all` (boolean): include already-read
- `limit` (integer)

### `wait` (~40 tokens)

Block until a message arrives (or timeout_s passes). Optionally only for one thread.

Input parameters:

- `thread` (string)
- `timeout_s` (number)

### `thread` (~21 tokens)

Every message in a conversation thread.

Input parameters:

- `id` (string, required)

### `channels` (~34 tokens)

List channels with member counts; history=#name returns recent posts.

Input parameters:

- `history` (string)
- `limit` (integer)

### `subscribe` (~35 tokens)

Join (or leave=true) a #channel to receive its posts.

Input parameters:

- `channel` (string, required)
- `leave` (boolean)

### `set_name` (~27 tokens)

Pick a short @name peers can use to reach you.

Input parameters:

- `name` (string, required)

### `claim` (~54 tokens)

Advisory lock on files/dirs/tasks so peers don't edit the same thing. Fails if a peer holds an overlapping claim.

Input parameters:

- `note` (string)
- `resources` (array, required)
- `ttl_s` (integer)

### `release` (~24 tokens)

Release your claims (all when resources is omitted).

Input parameters:

- `resources` (array)

### `mesh_peers` (~43 tokens)

Other machines on the puenteo mesh (LAN / relays) and their live sessions. Address a remote session as '<address>@<node>' in send/reply.

### `find` (~41 tokens)

Search the bazaar: sessions on other machines that published an offer (what they can help with).

Input parameters:

- `limit` (integer)
- `query` (string)

### `offer` (~67 tokens)

Publish what YOU can help with to other machines (bazaar). Opting in allows remote requests to reach you. withdraw=<id> removes an offer.

Input parameters:

- `tags` (array)
- `text` (string)
- `ttl_s` (integer)
- `withdraw` (string)

### `room_join` (~54 tokens)

Join a many-to-many room bridged across machines; then send to '#<room>@*'. secret = private room.

Input parameters:

- `leave` (boolean)
- `room` (string, required)
- `secret` (string)

### `claims` (~32 tokens)

Active claims; with check=[paths] only those held by others that overlap the paths.

Input parameters:

- `check` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/mano7onam-puenteo/puenteo#diagnostics

## Score history

- 2026-10-17: 60
- 2026-10-16: 60
- 2026-10-15: 60
- 2026-10-14: 60
- 2026-10-13: 38
- 2026-10-12: 23
- 2026-10-08: 23

## Common questions

### What is the Puenteo MCP server?

Puenteo is an MCP server listed in the public MCP registry as io.github.mano7onam/puenteo. Let coding agents talk: search every agent session's history and message live sessions. This page covers its PyPI package (puenteo).

### Is the Puenteo MCP server safe to use?

Puenteo scores 60 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. 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 Puenteo MCP server expose?

Puenteo exposes 22 tools: whoami, sessions, search, outline, pull, and 17 more. Their descriptions and schemas cost roughly 1,023 tokens of context every time the server is loaded.

### Is the Puenteo MCP server still maintained?

Puenteo is still listed as active in the MCP registry. We last reached this channel on 17 October 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 Puenteo MCP server under?

Puenteo declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/puenteo/
- Socket report: https://socket.dev/pypi/package/puenteo
- Repository: https://github.com/mano7onam/puenteo
- Changelog RSS feed: https://verifymcp.io/servers/mano7onam-puenteo/puenteo.xml
- Changelog JSON feed: https://verifymcp.io/servers/mano7onam-puenteo/puenteo.json
- HTML version of this page: https://verifymcp.io/servers/mano7onam-puenteo/puenteo