Zovo Decision Tree MCP

Solves and draws decision trees for business choices from user-provided numbers, computing expected values using fractions to avoid floating-point drift. It accepts indented outlines or JSON, checks probability sums, identifies optimal options, and exports results as PDF, SVG, or CSV.

Visit Zovo

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-08Published by Zovo

MCP endpoint (Streamable HTTP)

https://decision-tree.zovo.one/mcp

Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

2 of 2 have a description · 2 of 2 declare behavior hints · 2 of 2 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 8, 2026, 2:43 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Compute expected values for business decision trees
Draw decision trees as vector PDF or SVG
Validate that chance node probabilities sum to 1
Export tree data and risk profiles to CSV

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.theluckystrike/decision-tree@1.0.0 Project website

Protocol and capabilities

Server: decision-tree 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 2 advertised
Resources: 1 advertised
Resource templates: 1 advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Zovo Decision Tree draws a decision tree from decision, chance and end nodes and rolls it back to expected values with fractions, so no rounding builds up. Use make_decision_tree to compute and draw it (PDF, SVG and CSV downloads) and check_tree to check the probabilities and payoffs without drawing. It computes expected values from the numbers the user gives; it gives no advice and does not estimate probabilities. Files of large trees are kept for 1 hour so the download links work, then deleted.

Tools

2 advertised

make_decision_tree — Make decision tree

Advertised by the server during the last successful anonymous check.

Advertised read-only

Use this when the user wants a decision tree drawn or solved: options of a decision, chance events with probabilities, and payoffs, for example "which option has the higher expected value" or "draw a decision tree for launching this product". Takes the tree as an indented outline or a JSON node list, the objective (max or min), a unit, decimals, a page size and a title. Rolls the tree back with fractions: the expected value of each node, the chosen option at each decision (ties listed), branch costs applied by a stated rule, and the risk profile of the chosen strategy. Refuses a tree whose chance probabilities do not add up to 1, naming the node and the sum, and end nodes without a payoff. Returns a summary, an interactive drawing, and PDF, SVG and CSV downloads. Up to 300 nodes. Does not estimate probabilities or give advice. Download links of large trees expire after about 1 hour.

make_decision_tree input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "unit": {
      "type": "string",
      "maxLength": 40,
      "description": "Unit or currency shown with values, up to 12 characters, e.g. \"$\", \"EUR\" or \"hours\"."
    },
    "nodes": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id"
        ],
        "properties": {
          "p": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Probability of this branch when the parent is a chance node, e.g. 0.6, \"1/3\" or \"35%\"."
          },
          "id": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Unique id of the node, e.g. \"n1\"."
          },
          "cost": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Amount paid on this branch, e.g. 200."
          },
          "type": {
            "type": "string",
            "maxLength": 20,
            "description": "decision, chance or end. Optional: inferred from the branches as in the outline."
          },
          "label": {
            "type": "string",
            "maxLength": 400,
            "description": "Short name of the node or of the branch into it, e.g. \"Strong demand\"."
          },
          "parent": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Id of the parent node; leave out for the root only, e.g. \"n1\"."
          },
          "payoff": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Value at an end node, e.g. 1000 or -300."
          }
        },
        "additionalProperties": {}
      },
      "maxItems": 2000,
      "description": "The tree as a JSON list instead of outline: each node has id, parent (not for the root), label, and p, cost or payoff as needed, e.g. [{\"id\":\"r\",\"label\":\"Launch?\"},{\"id\":\"a\",\"parent\":\"r\",\"label\":\"Do not launch\",\"payoff\":0}]."
    },
    "title": {
      "type": "string",
      "maxLength": 400,
      "description": "Title printed on the drawing and used in file names, up to 80 characters, e.g. \"Product launch\"."
    },
    "outline": {
      "type": "string",
      "maxLength": 400000,
      "description": "The tree as indented text, one node per line, children indented under their parent (spaces or tabs, \"- \" bullets allowed). The first line is the root. Fields after the label: p=<probability> on branches of a chance node, cost=<amount> on any branch, payoff=<amount> on end nodes; separate them with spaces or \"|\". A node whose branches have p is a chance node, a node with branches and no p is a decision, a node with no branches is an end node; \"Decision:\", \"Chance:\" or \"End:\" before a label states the type. Numbers: decimals (0.35, -1,200.50, $300), fractions (1/3), and percents for p (35%). Up to 300 nodes. Example: \"Launch? | decision\\n  Launch | cost=200\\n    Strong demand | p=0.6 | payoff=1000\\n    Weak demand | p=0.4 | payoff=-300\\n  Do not launch | payoff=0\"."
    },
    "decimals": {
      "type": "integer",
      "maximum": 6,
      "minimum": 0,
      "description": "Decimals shown in the drawing and summary, 0 to 6 (default 2), e.g. 2. The CSV also has the fraction."
    },
    "objective": {
      "enum": [
        "max",
        "min"
      ],
      "type": "string",
      "description": "max (default): choose the option with the highest expected value, for profit or gain. min: choose the lowest, when payoffs are costs, losses or time. Example: max."
    },
    "page_size": {
      "enum": [
        "letter",
        "a4"
      ],
      "type": "string",
      "description": "PDF page: letter (default) or a4. Landscape unless portrait needs fewer pages."
    }
  }
}

make_decision_tree output schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "title",
    "objective",
    "unit",
    "decimals",
    "counts",
    "root",
    "strategy",
    "ties",
    "risk_profile",
    "nodes",
    "issues",
    "checks",
    "pdf",
    "rules",
    "warnings",
    "downloads"
  ],
  "properties": {
    "pdf": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "root": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "ties": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "unit": {
      "type": "string"
    },
    "nodes": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "rules": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "shown": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "title": {
      "type": "string"
    },
    "checks": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "counts": {
      "type": "object",
      "required": [
        "nodes",
        "decision_nodes",
        "chance_nodes",
        "end_nodes",
        "depth",
        "errors",
        "warnings"
      ],
      "properties": {
        "depth": {
          "type": "number"
        },
        "nodes": {
          "type": "number"
        },
        "errors": {
          "type": "number"
        },
        "warnings": {
          "type": "number"
        },
        "end_nodes": {
          "type": "number"
        },
        "chance_nodes": {
          "type": "number"
        },
        "decision_nodes": {
          "type": "number"
        }
      },
      "additionalProperties": false
    },
    "issues": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "decimals": {
      "type": "number"
    },
    "strategy": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "warnings": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "downloads": {
      "type": "object",
      "properties": {
        "csv": {
          "type": "string"
        },
        "pdf": {
          "type": "string"
        },
        "svg": {
          "type": "string"
        }
      },
      "additionalProperties": false
    },
    "objective": {
      "type": "string"
    },
    "risk_profile": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    }
  },
  "additionalProperties": false
}

make_decision_tree annotations

{
  "title": "Make decision tree",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

check_tree — Check decision tree

Advertised by the server during the last successful anonymous check.

Advertised read-only

Use this when the user wants a decision tree checked without a drawing, for example "do my probabilities add up to 1" or "is anything missing in this tree". Takes the same outline or node list and objective as make_decision_tree. Returns, for each chance node, the sum of its branch probabilities as a fraction and whether it is 1; end nodes without a payoff; probabilities on decision options; payoffs on nodes that have branches; single-option decisions; duplicate branch names; and the depth and node counts against the limits. When nothing is wrong it also gives the root expected value. Refuses a tree it is unable to read (unknown parent, a loop, two roots, over the limits), naming the line or id. Does not draw the tree or make files. Do not use it to estimate probabilities.

check_tree input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "nodes": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id"
        ],
        "properties": {
          "p": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Probability of this branch when the parent is a chance node, e.g. 0.6, \"1/3\" or \"35%\"."
          },
          "id": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Unique id of the node, e.g. \"n1\"."
          },
          "cost": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Amount paid on this branch, e.g. 200."
          },
          "type": {
            "type": "string",
            "maxLength": 20,
            "description": "decision, chance or end. Optional: inferred from the branches as in the outline."
          },
          "label": {
            "type": "string",
            "maxLength": 400,
            "description": "Short name of the node or of the branch into it, e.g. \"Strong demand\"."
          },
          "parent": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Id of the parent node; leave out for the root only, e.g. \"n1\"."
          },
          "payoff": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 80
              },
              {
                "type": "number"
              }
            ],
            "description": "Value at an end node, e.g. 1000 or -300."
          }
        },
        "additionalProperties": {}
      },
      "maxItems": 2000,
      "description": "The tree as a JSON list instead of outline: each node has id, parent (not for the root), label, and p, cost or payoff as needed, e.g. [{\"id\":\"r\",\"label\":\"Launch?\"},{\"id\":\"a\",\"parent\":\"r\",\"label\":\"Do not launch\",\"payoff\":0}]."
    },
    "outline": {
      "type": "string",
      "maxLength": 400000,
      "description": "The tree as indented text, one node per line, children indented under their parent (spaces or tabs, \"- \" bullets allowed). The first line is the root. Fields after the label: p=<probability> on branches of a chance node, cost=<amount> on any branch, payoff=<amount> on end nodes; separate them with spaces or \"|\". A node whose branches have p is a chance node, a node with branches and no p is a decision, a node with no branches is an end node; \"Decision:\", \"Chance:\" or \"End:\" before a label states the type. Numbers: decimals (0.35, -1,200.50, $300), fractions (1/3), and percents for p (35%). Up to 300 nodes. Example: \"Launch? | decision\\n  Launch | cost=200\\n    Strong demand | p=0.6 | payoff=1000\\n    Weak demand | p=0.4 | payoff=-300\\n  Do not launch | payoff=0\"."
    },
    "objective": {
      "enum": [
        "max",
        "min"
      ],
      "type": "string",
      "description": "max (default): choose the option with the highest expected value, for profit or gain. min: choose the lowest, when payoffs are costs, losses or time. Example: max."
    }
  }
}

check_tree output schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "ready",
    "objective",
    "counts",
    "chance_nodes",
    "issues",
    "limits"
  ],
  "properties": {
    "root": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "ready": {
      "type": "boolean"
    },
    "shown": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "counts": {
      "type": "object",
      "required": [
        "nodes",
        "decision_nodes",
        "chance_nodes",
        "end_nodes",
        "depth",
        "errors",
        "warnings"
      ],
      "properties": {
        "depth": {
          "type": "number"
        },
        "nodes": {
          "type": "number"
        },
        "errors": {
          "type": "number"
        },
        "warnings": {
          "type": "number"
        },
        "end_nodes": {
          "type": "number"
        },
        "chance_nodes": {
          "type": "number"
        },
        "decision_nodes": {
          "type": "number"
        }
      },
      "additionalProperties": false
    },
    "issues": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "limits": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "objective": {
      "type": "string"
    },
    "chance_nodes": {
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    }
  },
  "additionalProperties": false
}

check_tree annotations

{
  "title": "Check decision tree",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

1 advertised

decision-tree-widget — Zovo Decision Tree view

Advertised by the server during the last successful anonymous check.

Interactive view for Zovo Decision Tree.

decision-tree-widget URI

ui://widget/decision-tree-v1-1.0.0-cffc69e91395158c65c3fa7520d385c901b529cbd493c0c4a7416ea52170731a.html

MIME type: text/html;profile=mcp-app

decision-tree-widget-legacy — Zovo Decision Tree view (previous versions)

Advertised by the server during the last successful anonymous check.

decision-tree-widget-legacy URI template

ui://widget/decision-tree-{version}.html

MIME type: text/html;profile=mcp-app

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 915 ms
95th percentile latency: 915 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 8, 2026, 2:43 AM UTC · probe · passed · 915 ms · metadata changed · 2 tool(s), 1 resource(s), 1 resource template(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http zovo-decision-tree-mcp https://decision-tree.zovo.one/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add zovo-decision-tree-mcp --url https://decision-tree.zovo.one/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable zovo-decision-tree-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "zovo-decision-tree-mcp": {
      "url": "https://decision-tree.zovo.one/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "zovo-decision-tree-mcp": {
      "type": "streamableHttp",
      "url": "https://decision-tree.zovo.one/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start zovo-decision-tree-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "zovo-decision-tree-mcp": {
      "type": "http",
      "url": "https://decision-tree.zovo.one/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http zovo-decision-tree-mcp https://decision-tree.zovo.one/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://decision-tree.zovo.one/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "zovo-decision-tree-mcp": {
      "serverUrl": "https://decision-tree.zovo.one/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Zovo Decision Tree MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 7,067

Zovo Decision Tree MCP

Endpoint and access

What its tools do

Read-only (2)

Checks and signals

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other data and analytics servers