Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OpenFateAI Assistant MCP compare two job offers side by side"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
npx -y openfateai-mcpRelated MCP server: Toki Toki no Mi
{
"mcpServers": {
"openfateai": {
"command": "npx",
"args": ["-y", "openfateai-mcp"]
}
}
}Tool | Purpose |
| Compare user-provided options, facts, assumptions, constraints, priorities, and reversible tests. |
| Create a guided, non-clinical reflection sequence. |
| Arrange candidate actions into phases and review checkpoints. |
| Organize source notes into a transparent report outline. |
| Return intended uses, safety boundaries, and payment guidance. |
| Return canonical workspace, pricing, support, and legal links. |
The package also exposes the decision_review and weekly_reflection MCP prompts.
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.
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.
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.
The portable skill is located at skills/openfateai-assistant/SKILL.md.
npm install
npm run build
npm run smokeRequires Node.js 20 or newer.
MIT
Arrange user-provided candidate steps into a time-bounded plan with checkpoints. The tool organizes steps and does not invent expert recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | The outcome the user wants to move toward. | |
| constraints | No | Constraints the plan must respect. | |
| horizonDays | No | Planning horizon in days. | |
| currentState | Yes | A concise description of the current situation. | |
| candidateSteps | Yes | Candidate actions already identified by the user or agent. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already indicate safe, non-destructive behavior. The description adds value by clarifying that the tool only organizes steps and does not generate new recommendations, which goes beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two concise sentences that front-load the core purpose and limitation. Every phrase earns its place with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 5 parameters with full schema descriptions and no output schema, the description provides adequate context about the tool's behavior (organizing, time-bounded, checkpoints). However, it lacks details on plan structure and return format, slightly limiting completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter is documented. The description adds no further parameter-level detail beyond stating the general function, so it meets the baseline of 3 without adding extra meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'arrange' and resource 'user-provided candidate steps into a time-bounded plan with checkpoints', distinguishing it from sibling tools like 'create_reflection_session' and 'structure_decision'. It also explicitly notes what it does not do ('does not invent expert recommendations'), enhancing clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for organizing existing steps but does not explicitly state when to use it over alternatives or when not to use it. The mention 'does not invent expert recommendations' suggests limitations but lacks direct guidance on choosing between siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a guided self-reflection sequence from a user-provided situation and desired outcome. The output is educational and non-clinical.
| Name | Required | Description | Default |
|---|---|---|---|
| focus | No | The main reflection area. | general |
| intensity | No | How emotionally intense the situation feels, from 1 to 5. | |
| situation | Yes | The situation the user wants to reflect on. | |
| desiredOutcome | No | What the user hopes to understand or change. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so safety profile is clear. The description adds 'educational and non-clinical' context, but does not elaborate on how the reflection is generated, any AI usage, or rate limits. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is two sentences, front-loaded with the action and purpose. No wasted words. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has 4 parameters, no output schema. Description explains the outcome is a 'guided self-reflection sequence' and educational, but lacks details on what the returned data structure looks like or how the sequence is generated. Adequate but incomplete given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter already has a description. The tool description does not add any additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'create' and resource 'guided self-reflection sequence', and specifies it's from user-provided situation and desired outcome. It distinguishes from siblings like 'build_action_plan' or 'structure_decision' by focusing on reflection rather than action or decision support.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'structure_decision' or 'build_action_plan'. The description does not mention prerequisites, exclusions, or typical use cases. Sibling names provide implicit context, but no direct 'when to use' statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the product boundaries and response guidance for OpenFateAI assistant workflows.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe, idempotent read. The description adds that it returns 'product boundaries and response guidance', which is useful context but does not disclose additional behavioral traits like rate limits or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. It conveys the essential purpose efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description adequately states what it returns. However, it could mention the format or structure of the policy (e.g., text, JSON) to improve completeness, but it is sufficient for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the schema coverage is 100%. The description does not need to add parameter information. The baseline for 0 parameters is 4, and the description is clear enough.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'product boundaries and response guidance for OpenFateAI assistant workflows', specifying both the verb ('return') and the resource ('policy'). It is distinct from sibling tools like 'get_openfateai_resources' but does not explicitly differentiate itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, contexts where this tool is preferred, or when to avoid it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return canonical OpenFateAI links for the workspace, one-time credit pricing, support, terms, privacy, refunds, and source code.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations fully cover safety (readOnlyHint, idempotentHint, destructiveHint). Description adds no behavioral context beyond listing returned links, which is sufficient but does not exceed annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 15 words, directly states purpose with no fluff. Well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and comprehensive annotations, description adequately lists what is returned. Possibly could mention output format, but not necessary for this simple retrieval.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so description cannot add meaning beyond schema. Baseline 4 is appropriate; description lists returned items, adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly uses the verb 'Return' and specifies the exact resources: canonical OpenFateAI links, pricing, support, terms, etc. It distinguishes from sibling 'get_openfateai_policy' which returns only policy.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage through listing content, but lacks explicit guidelines on when to use this tool versus siblings like 'get_openfateai_policy' or 'build_action_plan'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Organize user-provided notes into a transparent report outline without adding facts, citations, or conclusions that were not supplied.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | Source notes to organize without inventing facts. | |
| title | Yes | Title for the digital report. | |
| purpose | Yes | The report purpose or question it should answer. | |
| audience | No | Intended audience. | Personal use |
| reportType | No | Report structure to use. | general |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds that the tool does not add facts, citations, or conclusions, which is consistent and provides valuable behavioral context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys action, resource, output, and constraints. Every word serves a purpose, and the description is front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, thorough schema descriptions (100% coverage), and annotations, the description adequately explains the tool's purpose and constraints. It could mention the output format (e.g., 'outline' is already there) but is otherwise complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with adequate descriptions for all 5 parameters. The description reinforces the overall behavior but does not add new per-parameter semantics beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('organize'), resource ('user-provided notes'), and output ('transparent report outline'), with explicit constraints against adding facts, citations, or conclusions. This distinguishes it from sibling tools like 'build_action_plan' or 'structure_decision'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use this tool: to organize notes without inventing content. It implies not to use it when external knowledge or conclusions are needed, but does not name alternative tools directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Organize user-provided options, facts, assumptions, constraints, and priorities into a neutral comparison. This tool does not choose an option or predict an outcome.
| Name | Required | Description | Default |
|---|---|---|---|
| facts | No | Facts that are directly known. | |
| options | Yes | Two to eight options being compared. | |
| deadline | No | Optional human-readable decision deadline. | |
| decision | Yes | The decision or question being considered. | |
| priorities | No | Values or outcomes that matter most. | |
| assumptions | No | Beliefs that still need verification. | |
| constraints | No | Time, money, policy, or personal constraints. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) are already provided. The description adds value by stating it does not choose or predict, confirming non-destructive behavior. It does not contradict annotations and provides additional context about the tool's neutral role.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no redundancy. The first sentence states the action and inputs, the second clarifies a key limitation. Every word earns its place, making it highly scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and the description does not describe the output format or what 'organize into a neutral comparison' means in practice. While annotations cover side effects, the description lacks detail on the structure of the output, which is important for an agent to know what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description mentions 'options, facts, assumptions, constraints, and priorities', which aligns with schema parameters, but adds no new meaning beyond what the schema already documents. It repeats parameter names without deeper semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Organize user-provided options, facts, assumptions, constraints, and priorities into a neutral comparison.' It also explicitly distinguishes what it does not do ('does not choose an option or predict an outcome'), which differentiates it from sibling tools like 'build_action_plan'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear 'when to use' by stating it structures inputs neutrally and does not make choices, but it does not explicitly name alternative tools or state when not to use it in favor of siblings. The context of sibling names fills some gaps, but the description itself is slightly vague on usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0build_action_plancreate_reflection_sessionget_openfateai_policyget_openfateai_resourcesprepare_digital_reportstructure_decisionScored across 6 tools
Each tool targets a distinct activity: planning, reflection, policy retrieval, resource links, report drafting, and decision structuring. No two tools have overlapping purposes.
All tool names consistently use a verb_noun pattern in snake_case (e.g., build_action_plan, create_reflection_session). No mixing of styles.
With 6 tools, the set is well-scoped for an AI assistant focused on planning, reflection, decision support, and information lookup. Each tool earns its place.
The tools cover core workflows: plan creation, reflection, decision structuring, report preparation, and access to policies/resources. Minor gaps like a tool to update plans are absent, but the surface is largely complete for the stated purpose.
MCP server for generating rough-draft project plans from natural-language prompts.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP tool for governed nonclinical pattern interruption, emotional clarity, and next-step guidance.
