iBluSend

iBluSend

Enables secure inbox triage, safe drafting and sending, and management of contacts, devices, and compliance within a single workspace through a remote MCP endpoint.

Category
Visit Server

README

iBluSend Plugins

Official, shared plugin packaging for iBluSend on OpenAI and Claude. One package connects both providers to the same workspace-bound MCP resource and supplies three provider-neutral workflows:

  • inbox triage;
  • safe draft and send; and
  • contact, device, and compliance operations.

The public package intentionally exposes the curated public-v1 contract. It is not a bulk campaign engine, does not bypass iBluSend compliance controls, and does not ship credentials.

Repository status

This package remains a development/local beta and has not been submitted to a public marketplace. The iBluSend package now carries the real OpenAI app mapping proven in the private ChatGPT developer-mode beta; white-label output omits .app.json unless that brand has its own registered OpenAI app.

Layout

plugins/iblusend/                     Generated installable plugin
  .codex-plugin/plugin.json           OpenAI / Codex manifest
  .app.json                           Registered iBluSend OpenAI app mapping
  .claude-plugin/plugin.json          Claude manifest
  .mcp.json                           Shared remote MCP connection
  skills/                             Provider-neutral workflows
.agents/plugins/marketplace.json      Codex repository marketplace
.claude-plugin/marketplace.json       Claude repository marketplace
brands/                               Validated brand documents
scripts/                              Generator and package validator
tests/                                Determinism, parity, and leak checks
docs/                                 Beta and submission runbooks

Validate the checked-in package

Node.js 20 or newer is sufficient; there are no runtime or development dependencies.

npm test

When the provider CLIs and the OpenAI validator's PyYAML dependency are available, run their validators too. Use a temporary Python target rather than installing globally when needed:

validation_env="$(mktemp -d)"
python3 -m pip install --quiet --target "$validation_env" -r requirements-validation.txt
PYTHONPATH="$validation_env" python3 \
  "$CODEX_HOME/skills/.system/plugin-creator/scripts/validate_plugin.py" plugins/iblusend
rm -r "$validation_env"
claude plugin validate plugins/iblusend --strict
claude plugin validate . --strict

Regenerate iBluSend

npm run generate
npm run generate:check

Generated plugin files carry a header or are binary assets. Change brands/iblusend.json or the generator, then regenerate; do not patch generated copies independently.

Generate a private white-label bundle

node scripts/generate-brand-package.mjs \
  --brand brands/imessage-sender.example.json \
  --output dist/imessage-sender
node scripts/validate-packages.mjs --root dist/imessage-sender

dist/ is ignored. Agency brand documents and archives stay private. Only iBluSend is intended for the first public submissions.

See local beta, white-label packaging, and the provider submission runbooks under docs/submission/.

Security

  • The MCP endpoint is https://api.iblusend.com/functions/v1/agent-api/v1/mcp/public.
  • OAuth is discovered from the resource at runtime; no client secret or API key belongs here.
  • Every authorization grant is bound to one workspace.
  • Write tools require Read and act consent.
  • Sending workflows stop on the exact workspace, one 1:1 recipient, and final content for host approval.

Report security concerns privately to support@iblusend.com.

License and marks

Code and workflow text are licensed under MIT. iBluSend names, logos, and other brand assets are excluded from that grant; see TRADEMARKS.md.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured