Name: Agent Intercom
Author: iambashar

Agent Intercom MCP

Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions.

Grade A Local · stdio No auth needed 3 tools v0.2.5 MIT

No reviews yet by iambasharnpm 978 Runs on your machine, nothing hosted

97/100

trust score

downloads a day

local

runs on your machine

978

downloads in 30d

What it does

Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'AGENT_NAME=${AGENT_NAME}' --transport stdio agent-intercom-mcp '--' npx -y agent-intercom serve

# 2 — ask your agent for something these tools do
#   mail_send, mail_check, mail_peers

It needs AGENT_NAME: this reads it from your environment, so export it first.

Agent Intercom costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

iambashar1 server

1 category

All 1 server

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Agent Intercom as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads AGENT_NAME (This agent's mailbox name, e.g. claude, codex or gemini) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx AGENT_NAME … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'AGENT_NAME=${AGENT_NAME}' --transport stdio agent-intercom-mcp '--' npx -y agent-intercom serve

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs settings only you can give it: AGENT_NAME — This agent's mailbox name, e.g. claude, codex or gemini. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

3 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Deliver a text message from you ("…") to another coding agent's inbox, for example to hand off a task, ask a question or report a result.

Parameter	Type	Required	Notes
to	string	yes	Recipient agent name as listed by mail_peers, e.g. "codex", "claude" or "gemini". Letters, digits, _ and -, with optional .suffix segments.
body	string	yes	Message text, in plain text or Markdown. Include everything the recipient needs, since it cannot see your conversation.
reply_to	string	no	Optional. The id of the message you are answering (the value in [brackets] from mail_check), so the recipient can match the reply to its question.

Fetch the unread messages addressed to you ("…"), oldest first. Use it when you expect a reply or want to see if another agent wrote to you.

Parameter	Type	Required	Notes
wait_seconds	number	no	How long to wait for a message if the inbox is empty, in seconds (0 to 300). 0 returns immediately.

List every agent name that has a mailbox here, so you know valid recipients for mail_send.

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Agent Intercom or to call it, at any volume.

ATrust score 97 / 100

Release 0.2.5 · scanned 19 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score97

Findings2 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digest303b157b4af664728cfb04fba59ea024015e8a28971694db5d7aaeb4a313b749

Score vectorthreat 100 → client 97

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
mail_send	state-write	state-write: declares readOnlyHint: false
mail_check	untrusted-inputstate-write	untrusted-input: keyword "fetch"; state-write: declares readOnlyHint: false
mail_peers	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest303b157b4af66472

Scanned2026-10-19

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.