About OpenFateAI Assistant MCP
OpenFateAI Assistant MCP is a local server for organizing decisions, reflection, action plans, and report outlines. It is for people who want structured support based on their own information, without automated decisions or professional advice.
Key features
- 01Structure options, facts, and constraints
- 02Create guided reflection sessions
- 03Arrange actions into phases
- 04Outline reports from source notes
- 05Look up policy and resource links
Use cases
- 01Compare options and reversible tests
- 02Plan actions with review checkpoints
- 03Reflect through a guided sequence
- 04Turn notes into a report outline
MCP support
It is a local stdio MCP server with tools for decision structure, reflection, planning, report outlines, policy, and resources. It also provides the `decision_review` and `weekly_reflection` prompts.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| facts | any | No | Facts that are directly known. |
| options | array | Yes | Two to eight options being compared. |
| deadline | string | No | Optional human-readable decision deadline. |
| decision | string | Yes | The decision or question being considered. |
| priorities | any | No | Values or outcomes that matter most. |
| assumptions | any | No | Beliefs that still need verification. |
| constraints | any | No | Time, money, policy, or personal constraints. |
Details
From the project READMEOpenFateAI Assistant MCP
A local, open-source Model Context Protocol server for structured decisions, guided reflection, action planning, and transparent digital report outlines.
The server runs over stdio, does not require an API key, and does not send tool inputs to OpenFateAI servers.
Install
npx -y openfateai-mcp
MCP configuration
{
"mcpServers": {
"openfateai": {
"command": "npx",
"args": ["-y", "openfateai-mcp"]
}
}
}
Tools
| Tool | Purpose |
|---|---|
structure_decision | Compare user-provided options, facts, assumptions, constraints, priorities, and reversible tests. |
create_reflection_session | Create a guided, non-clinical reflection sequence. |
build_action_plan | Arrange candidate actions into phases and review checkpoints. |
prepare_digital_report | Organize source notes into a transparent report outline. |
get_openfateai_policy | Return intended uses, safety boundaries, and payment guidance. |
get_openfateai_resources | Return canonical workspace, pricing, support, and legal links. |
The package also exposes the decision_review and weekly_reflection MCP prompts.
Product boundary
This MCP is a local organizational layer. It does not predict outcomes, provide professional advice, process payments, or collect payment credentials.
OpenFateAI Chat uses one-time credit packs on the official website. Stripe and Alipay checkout remain on the website and are not exposed as MCP tools.
Compliance posture
- Local stdio transport only; no OpenFateAI API key is required.
- Read-only tools; no files, network resources, accounts, or payments are modified.
- No payment-card, Alipay, password, or sensitive credential collection.
- Outputs organize user-provided information and should preserve uncertainty.
- Consequential legal, medical, financial, tax, mental-health, and safety decisions should remain with qualified professionals.
Tooling contract
The server exposes deterministic organizational helpers only:
- Decision structure, not decision automation.
- Reflection prompts, not clinical care.
- Action-plan organization, not professional recommendation.
- Report outlines, not invented evidence or citations.
- Policy/resource lookup, not billing execution.
Agent Skill
The portable skill is located at skills/openfateai-assistant/SKILL.md.
Development
npm install
npm run build
npm run smoke
Requires Node.js 20 or newer.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.