What is localsend-mcp?

A peer-to-peer file-transfer skill that lets AI agents discover one another and send or receive files over local or private networks. It also supports voice announcements and several connection methods.

It is for discovering peers, transferring files, announcing agent presence, and checking peer identity.

It provides alternative ways to connect when one network route is unavailable and verifies the identity of the communicating peer.

localsend-mcp — Skill for Claude Code and Codex by plurigrid/asi

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add plurigrid/asi --skill skill

Clone the repo

git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/skill/github.svg)](https://agentmods.dev/skills/plurigrid/asi/skill)

Your own site

<a href="https://agentmods.dev/skills/plurigrid/asi/skill"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/plurigrid/asi/skill"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,758 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 9 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Data Exfiltration · line 73
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium MCP Rug Pull · line 163
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 164
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 173
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 182
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 191
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 368
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 369
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 370
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.02758
Opus 5.5	$0.00008	$0.01103
Sonnet 5.5	$0.00004	$0.00552
Haiku 4.5	$0.00002	$0.00276

Measured 2mo ago against content hash d5b7bdf13e9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localsend-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://100.69.33.107:53317/

ies/music-topos/packages/localsend-mcp/skill/SKILL.md · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LocalSend MCP Skill v2.0

WHO WE ARE (Redundant Self-Description)

Identity Declaration (Say This Out Loud)

I am an AI agent with LocalSend capability.
My peer name is derived from my hostname.
My color is deterministically assigned by Gay.jl seed.
I can send and receive files over Tailscale mesh network.
I announce my presence via voice synthesis.
I am ready for bidirectional skill exchange.

Machine-Readable Identity

{:agent {:type :localsend-peer
         :protocol-version "2.0"
         :capabilities [:send :receive :discover :announce :verify]}
 
 :identity {:name (hostname)
            :seed (hash (hostname))
            :color (gay-color seed)
            :fingerprint (sha256 (hostname))}
 
 :network {:tailscale {:ip "100.x.x.x"
                       :dns "hostname.tailnet.ts.net"
                       :port 53317}
           :lan {:ip "192.168.x.x"
                 :port 53317
                 :may-be-blocked true}}
 
 :voice {:primary "Emma (Premium)"
         :fallback ["Anna (Premium)" "Amélie (Premium)" "Samantha"]
         :language :multilingual}}

HOW TO CONNECT (5 Redundant Methods)

Method 1: Tailscale IP (RECOMMENDED)

# Most reliable - bypasses firewalls
curl http://100.69.33.107:53317/

Method 2: Tailscale DNS

# Human-readable
curl http://causality.pirate-dragon.ts.net:53317/

Method 3: LAN IP (May Be Blocked)

# Only works if firewall allows
curl http://192.168.1.40:53317/

Method 4: LocalSend App Discovery

1. Open LocalSend app
2. Look for device named "causality" or hostname
3. Tap to connect

Method 5: Voice Announcement (Listen!)

The agent will speak:
"Attenzione! LocalSend peer available!
 Connect to [hostname] punto [tailnet] punto ts net,
 porta cinque tre tre uno sette!"

MUTUAL DISCOVERY PROTOCOL

Step 1: Both Peers Announce

# Peer A announces
say -v "Emma (Premium)" "Peer A ready! Seed 1069! Color teal!"

# Peer B announces  
say -v "Anna (Premium)" "Peer B ready! Seed 2069! Color green!"

Read the full file on GitHub · 443 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 443 lines · 21 tokens per session scan A d5b7bdf13e9b

Subscribe to this mod's changes

localsend-mcp is a skill published in the GitHub repository plurigrid/asi (72 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 2,758 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Productivity development file-transfer localsend mcp mutual-discovery nats p2p skill-exchange tailscale voice

localsend-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
localsend-mcpplurigrid/asi	Skill	72	7d ago	MIT	A	21	Claude Code, Codex
orientericrisco/rsc-harness	Skill	503	2d ago	MIT	A	132	Claude Code, Codex
a0-developmentagent0ai/agent-zero	Skill	20k	yesterday	none	A	24	Claude Code, Codex
ai-phone-call-assistantrondoflow/rondoflow	Skill	29	2d ago	MIT	A	45	Claude Code, Codex
voice-ai-agentoyi77/1ai-skills	Skill	17	yesterday	MIT	A	40	Claude Code
telegram-userbotoyi77/1ai-skills	Skill	17	yesterday	MIT	A	70	Claude Code
postai-automationoyi77/1ai-skills	Skill	17	yesterday	MIT	B	38	Claude Code

localsend-mcp