PlanExe exposes plan creation, progress inspection and recovery workflows through a hosted or self-hosted MCP service.
PlanExe exposes plan creation, progress inspection and recovery workflows through a hosted or self-hosted MCP service.
PlanExe turns a task description into a structured planning job. The documented interface includes plan creation, status inspection and recovery options. Choose a model profile appropriate to the request and inspect the available profiles rather than assuming every deployment has the same models.
The hosted MCP route uses an X-API-Key header with a PlanExe account key. The project also documents a local Docker endpoint for operators running the stack themselves. A localhost URL is a deployment example, not a second public service. Authentication, credits and model availability follow the selected deployment.
Submit a bounded test request and retain its plan identifier. Poll the status and inspect the generated deliverable before using it. Retry and resume are different operations: retry addresses a failed or stopped job, while resume depends on a compatible saved pipeline state. Repeating an unchanged request with invalid credentials or insufficient credits does not resolve those errors. The result is a plan to evaluate, not proof that the proposed work has been carried out.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| plan_create | Create a planning job from a prompt and model profile. |
| plan_status | Inspect the status of a planning job. |
| plan_retry | Retry a failed or stopped plan. |
| plan_resume | Resume a compatible saved planning state. |
| model_profiles | Inspect available model profiles. |
| example_prompts | Retrieve example planning prompts. |
{
"mcpServers": {
"planexe": {
"url": "https://mcp.planexe.org/mcp",
"headers": {
"X-API-Key": "YOUR_PLANEXE_API_KEY"
}
}
}
}An HTTP MCP client, a PlanExe account key and available credits for the hosted route; a configured Docker stack for self-hosting.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Enables AI assistants to interact with and manage n8n workflows through natural language.
Dify Workflows MCP exposes configured Dify applications as assistant tools through a local TypeScript server.
Integrate Linear project management with Claude for enhanced workflow automation.
Build and run agents and automations across hundreds of apps using natural language.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs