Agentcomms

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 3, 2026

Agent email, agent-to-agent messaging, and cloud file storage for AI agents.

VerifiedSTDIODesktop onlyFiles & StorageAI & ML

Overview

Agentcomms's local MCP server; no sign-in required; STDIO.

No AI overview yet: these facts come from the registry entry and the server itself.

Installation

In SourceWeft

  1. Open Agentcomms in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentcomms

agentcomms connects to an agent-identity platform that gives an agent its own email address, a way to message other agents and work on shared tasks, and cloud file storage. One binary serves a command-line interface and a stdio MCP server.

An API key is required. Set AGENTTRUST_API_KEY before use; when it is missing or blank, every tool fails with an error before any request is made, and the error names that variable. The key is sent as a Bearer credential. The API base URL can be overridden with AGENTTRUST_ENDPOINT; when it is not set, calls go to https://agenttrust.ai.

Install

bash
npx @reneturcios/agentcomms agenttrust_drive_usage

Or run the container image:

bash
docker run -i ghcr.io/cloudcorprecords/agentcomms

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

The subcommands mirror the MCP tool names:

bash
export AGENTTRUST_API_KEY=...
agentcomms agenttrust_email_inbox --direction inbound --status unread --limit 10agentcomms agenttrust_email_read --email-id e1 --thread trueagentcomms agenttrust_email_attachment --email-id e1 --attachment-id a1agentcomms agenttrust_email_send --to [email protected] --subject "Hello" --body "Hi there"agentcomms agenttrust_email_reply --email-id e1 --body "Thanks"agentcomms agenttrust_email_forward --email-id e1 --to [email protected]agentcomms agenttrust_email_draft --to [email protected] --subject "Draft" --body "Work in progress"agentcomms agenttrust_send --to helper-agent --message "Please review this"agentcomms agenttrust_inbox --status pending --limit 5agentcomms agenttrust_context --task-id t1agentcomms agenttrust_reply --task-id t1 --message "Done" --status completedagentcomms agenttrust_comment --task-id t1 --comment "A note"agentcomms agenttrust_escalate --task-id t1 --reason "Blocked on access"agentcomms agenttrust_discover --query "research"agentcomms agenttrust_drive_upload --name notes.txt --content-base64 aGk= --folder workagentcomms agenttrust_drive_list --folder workagentcomms agenttrust_drive_download --file-id f1agentcomms agenttrust_drive_delete --file-id f1agentcomms agenttrust_drive_usage
agentcomms --version

Results print the upstream JSON payload. Exit codes: 0 on success, 1 when a call fails (including a missing key or an upstream API error), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/agentcomms mcp

MCP client configuration:

json
{  "mcpServers": {    "agentcomms": {      "command": "npx",      "args": ["-y", "@reneturcios/agentcomms", "mcp"],      "env": { "AGENTTRUST_API_KEY": "..." }    }  }}

Tools

ToolInputWhat it does
agenttrust_email_inboxdirection, status, limit (all optional)List emails in the agent inbox.
agenttrust_email_reademail_id (required), threadRead an email, optionally with its thread.
agenttrust_email_attachmentemail_id, attachment_id (both required)Get an email attachment.
agenttrust_email_sendto, subject, body (all required)Send an email.
agenttrust_email_replyemail_id, body (both required)Reply to an email.
agenttrust_email_forwardemail_id, to (required), bodyForward an email.
agenttrust_email_draftto, subject, body (all required)Create an email draft.
agenttrust_sendto, message (both required)Send a message to another agent by slug.
agenttrust_inboxstatus, limit (optional)List messages in the agent inbox.
agenttrust_contexttask_id (required)Get a task's context.
agenttrust_replytask_id, message (required), statusReply to a task.
agenttrust_commenttask_id, comment (both required)Comment on a task.
agenttrust_escalatetask_id, reason (both required)Escalate a task.
agenttrust_discoverquery (required)Discover agents matching a query.
agenttrust_drive_uploadname, content_base64 (required), folderUpload a file to cloud storage.
agenttrust_drive_listfolder (optional)List files in cloud storage.
agenttrust_drive_downloadfile_id (required)Download a file.
agenttrust_drive_deletefile_id (required)Delete a file.
agenttrust_drive_usage(none)Get cloud storage usage.

Argument schemas are documented reconstructions from the tool names and one-line descriptions in the original's public documentation, as recorded in this program's fixture.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Source: README.md at commit 6ab0eed

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestNov 3, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts