decisio-mcp-server
OfficialClick 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., "@decisio-mcp-server Help me choose between two job offers"
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.
Decisio MCP Server
Structured decision-making for AI assistants — powered by the Analytic Hierarchy Process (AHP), the same framework trusted by NASA, Boeing, and the World Bank.
When someone asks an AI "help me choose between job offers" or "which city should I move to", the AI can use Decisio's MCP tools to run a mathematically rigorous analysis instead of just listing pros and cons.
Tools
Tool | Description |
| Browse built-in templates (career, business, technology, etc.) |
| Start a new AHP analysis with criteria and options |
| Set pairwise comparisons (Saaty 1-9 scale) |
| Run AHP calculation — get ranked results with scores |
| Challenge the winning option |
| All-in-one: define + compare + calculate in a single call |
Related MCP server: Sequential Thinking MVP Server
Quick Start
Install
npm install -g decisio-mcp-serverConfigure in Claude Desktop / VS Code / Cursor
Add to your MCP config:
{
"mcpServers": {
"decisio": {
"command": "npx",
"args": ["-y", "decisio-mcp-server"]
}
}
}Build from source
git clone https://github.com/decisio-app/decisio-mcp-server.git
cd decisio-mcp-server
npm install
npm run buildExample Conversation
User: Help me choose between Berlin, Lisbon, and Austin for relocation.
AI (uses decisio_create_decision with relocation template):
Created decision with criteria: Cost of Living, Career Opportunities, Quality of Life, Weather & Climate, Social & Community.
AI (walks through pairwise comparisons):
Which matters more to you: Cost of Living or Career Opportunities?
User: Career, definitely — about 5x more important.
AI (uses decisio_compare):
Got it. How about Career vs Quality of Life?
(... continues through all pairs ...)
AI (uses decisio_calculate):
Results (AHP Analysis)
Lisbon — 38.2%
Austin — 32.1%
Berlin — 29.7%
Consistency Ratio: 0.04 (Very High confidence)
AI (uses decisio_devils_advocate):
The gap between Lisbon and Austin is only 6.1pp. If Career Opportunities weighted less, Austin could overtake...
How AHP Works
Define your goal, criteria, and options
Compare criteria pairwise: "Is Cost more important than Quality? By how much?"
Compare options under each criterion: "For Cost, is Berlin better than Lisbon?"
Calculate — AHP computes weighted scores using eigenvector mathematics
Validate — Consistency Ratio checks if your comparisons are logically coherent
The Saaty scale (1-9) quantifies preferences:
Value | Meaning |
1 | Equal importance |
3 | Moderate importance |
5 | Strong importance |
7 | Very strong importance |
9 | Extreme importance |
2,4,6,8 | Intermediate values |
1/3, 1/5, etc. | Inverse (B preferred over A) |
Full Experience
For Playbook, Outcome Tracking, PDF Export, and the full AI-powered Devil's Advocate — download Decisio on iOS:
License
MIT
Available Tools
6 toolsdecisio_calculateA
Run AHP calculation on a decision. Returns ranked options with scores, criteria weights, and consistency check. Works best when all pairwise comparisons are set, but will produce results with partial data.
Inputs: decision_id (required).
decisio_compareA
Set one or more pairwise comparisons for criteria or options. Use Saaty scale 1-9 (or fractions like 0.333 for inverse). For criteria: omit criterion. For options: provide criterion to specify which criterion the comparison is under.
Inputs: comparisons (required), decision_id (required).
decisio_create_decisionA
Start a new AHP decision analysis. Provide a goal, criteria, and options — or use a template (career, business, technology, investment, vendor, relocation, hiring).
Inputs: goal (required), options, criteria, template.
decisio_devils_advocateA
Challenge the winning option. Analyzes how close the runner-up is and what would need to change for the result to flip.
Inputs: decision_id (required).
decisio_list_templatesA
List available decision templates (career, business, technology, etc.) with their default criteria and options.
Inputs: no named parameters.
decisio_quick_decideA
Run a complete AHP analysis in a single call. Provide the goal, criteria, options, and ALL pairwise comparisons at once. Best for when you already know all the comparisons. Returns ranked results immediately.
Inputs: goal (required), options (required), criteria (required), option_comparisons (required), +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct aspect of the AHP workflow: template listing, decision creation, pairwise comparisons, calculation, adversarial analysis, and one-shot analysis. There is no overlap or ambiguity between tool purposes.
All tools share the 'decisio_' prefix, but the second part varies: some are verb_noun (list_templates, create_decision), some are bare verbs (compare, calculate), and one is a noun phrase (devils_advocate). This is mostly consistent with minor deviations.
Six tools is a well-scoped set for a decision analysis server, covering the entire AHP process without unnecessary bloat or missing essential actions.
The toolset covers the full AHP workflow: listing templates, creating decisions, setting comparisons, calculating results, challenging outcomes, and quick one-shot analysis. No obvious gaps for the domain.
Related MCP Connectors
Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables structured, iterative reasoning for complex problem-solving with features like confidence tracking, revision mechanisms, and branching support. Provides flexible validation and multiple output formats for systematic analysis and decision-making tasks.1111 npm72MIT
- AlicenseBqualityNot gradedmaintenanceEnables AI assistants to perform structured, step-by-step reasoning by breaking down complex problems into numbered thoughts, with support for revising previous steps and exploring alternative reasoning paths.5-
- AlicenseNot gradedqualityDmaintenanceProvides linear programming (LP), mixed-integer programming (MIP), and quadratic programming (QP) optimization capabilities using the HiGHS solver, enabling AI assistants to solve complex optimization problems like production planning, logistics, and portfolio optimization.26 npm17MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create, manage, and break down tasks into subtasks with priorities, and track progress through a hierarchical task list.8 npm12GPL 3.0