---
title: "planned"
description: "Bring Planned into your agent workflow."
canonical: https://agentpluginsdirectory.com/plugins/planned
last-updated: 2026-11-13
---

# planned
Bring Planned into your agent workflow.
## Package we checked
plugin.json sits at the package root in planned-inc/agent-plugin, which is the plugin directory the 1.0.0 spec describes. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists no skills and 1 MCP server (planned). Extension keys: com.openai.codex. Stored mcp.json transports: planned streamable-http.
- Slug: planned
- Publisher: Planned
- Repository: https://github.com/planned-inc/agent-plugin
- Manifest: plugin.json
- Version: 1.0.0
- Category (editorial): integrations
- Skills: 0
- MCP servers: 1 (planned)
- Stars: 0
- Repository created: 2026-08-18
- Repository last pushed: 2026-08-31
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/planned
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What planned does, in the publisher's words

Bring Planned into your agent through one MCP server, so you can work with your events without leaving the tool you are already in.

The plugin connects your agent to Planned's client-facing MCP server. Planned serves its multi-tool workflows through the read-only load_skill tool, so every client receives current instructions without a plugin update.

Everything the plugin can do runs through the Planned MCP server, acting as the Planned user who authorized the connection. The package itself is manifests, Markdown, and an icon, it ships no executable code.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/planned-inc/agent-plugin/HEAD/README.md

## MCP servers

- planned: transport: streamable-http; url: https://mcp.planned.com/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.
