Hesperan

Working · 2.7 s

com.hesperan/mcpv0.1.0 Domain verified

Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.

AI & Agents

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://api.hesperan.com/mcp

Authorization (required)

Hesperan API key from https://hesperan.com/console/keys

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

decide Read-only

Ask Hesperan 1 one or more typed questions about a state and get a probability for every possible answer. Types: choice (pick one of named options), noul (probability that a statement is true), score (level on an ordinal scale). Use for decisions with known options: routing, triage, policy or risk checks, "should I proceed?". Not for writing text, summaries or knowledge questions. Ask all questions about the same state in one call: billing is by input tokens (the state once plus each question once), from the user's monthly allowance and then their prepaid balance; failed calls are free.

statestring, required

The situation to judge: free text, or a JSON object (keeps dates, amounts and fields unambiguous). Leave out data that does not matter for the question.

questionsobject, required

Named questions, answered together: { "<name>": { "type": "choice" | "noul" | "score", "instructions": "...", "criteria": ... } }.

Tools (3)

decide

read-only

Argument	Type	Description
state*	any	The situation to judge: free text, or a JSON object (keeps dates, amounts and fields unambiguous). Leave out data that does not matter for the question.
questions*	object	Named questions, answered together: { "<name>": { "type": "choice" \| "noul" \| "score", "instructions": "...", "criteria": ... } }.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "state",
    "questions"
  ],
  "properties": {
    "state": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        }
      ],
      "description": "The situation to judge: free text, or a JSON object (keeps dates, amounts and fields unambiguous). Leave out data that does not matter for the question."
    },
    "questions": {
      "type": "object",
      "description": "Named questions, answered together: { \"<name>\": { \"type\": \"choice\" | \"noul\" | \"score\", \"instructions\": \"...\", \"criteria\": ... } }.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "oneOf": [
          {
            "type": "object",
            "required": [
              "type",
              "instructions",
              "criteria"
            ],
            "properties": {
              "type": {
                "type": "string",
                "const": "choice"
              },
              "criteria": {
                "type": "object",
                "description": "Option key -> plain-language description of what the option means. Mutually exclusive; add an \"other\" option if the list is not complete. Up to about 26 options work best.",
                "propertyNames": {
                  "type": "string"
                },
                "additionalProperties": {
                  "type": "string"
                }
              },
              "instructions": {
                "type": "string",
                "description": "The question, e.g. \"Which team should handle this ticket?\""
              }
            },
            "description": "Pick one of named options. Answer: choice and a probability per option."
          },
          {
            "type": "object",
            "required": [
              "type",
              "instructions"
            ],
            "properties": {
              "type": {
                "type": "string",
                "const": "noul"
              },
              "criteria": {
                "type": "object",
                "properties": {
                  "true": {
                    "type": "string"
                  },
                  "false": {
                    "type": "string"
                  }
                },
                "description": "Optional: what counts as yes and as no."
              },
              "instructions": {
                "type": "string",
                "description": "A statement (not a question), e.g. \"This email is a phishing attempt.\""
              }
            },
            "description": "Probability that a statement is true. Answer: noul = P(yes)."
          },
          {
            "type": "object",
            "required": [
              "type",
              "instructions",
              "criteria"
            ],
            "properties": {
              "type": {
                "type": "string",
                "const": "score"
              },
              "criteria": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "minItems": 2,
                "description": "One description per level, lowest first."
              },
              "instructions": {
                "type": "string",
                "description": "What to rate, e.g. \"How upset is the customer?\""
              }
            },
            "description": "Rate on an ordinal scale you define. Answer: score = expected level, plus a probability per level (\"0\", \"1\", ...)."
          }
        ]
      }
    }
  }
}

decide_with_profile

Run one of the user's decision profiles on a state. A profile is one question calibrated on the user's own labelled cases with a target precision; the answer is a decision, its calibrated confidence and an action: "auto" (confidence reaches the profile's threshold — act on it) or "review" (hand it to a person). Profiles are created in the Hesperan console; ask the user for the profile slug. Keep the returned decision_id to report the correct answer later with report_outcome. Billed by input tokens like decide; pass an idempotency_key to make retries safe (a repeat with the same key returns the first decision without charging again).

Argument	Type	Description
state*	any	The situation to judge: free text, or a JSON object (keeps dates, amounts and fields unambiguous). Leave out data that does not matter for the question.
profile*	string	Slug of the decision profile, e.g. "ticket-routing".
idempotency_key	string	Optional unique key for this decision (1-255 visible ASCII characters, e.g. the ticket id). Reusing it within 24 hours with the same state replays the stored decision.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "profile",
    "state"
  ],
  "properties": {
    "state": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        }
      ],
      "description": "The situation to judge: free text, or a JSON object (keeps dates, amounts and fields unambiguous). Leave out data that does not matter for the question."
    },
    "profile": {
      "type": "string",
      "minLength": 1,
      "description": "Slug of the decision profile, e.g. \"ticket-routing\"."
    },
    "idempotency_key": {
      "type": "string",
      "pattern": "^[\\x21-\\x7e]{1,255}$",
      "description": "Optional unique key for this decision (1-255 visible ASCII characters, e.g. the ticket id). Reusing it within 24 hours with the same state replays the stored decision."
    }
  }
}

report_outcome

Record the correct answer for an earlier decide_with_profile decision, once it is known (e.g. the team that finally handled the ticket). This tracks the live precision of the profile in the console. actual must be one of the profile's option keys. Free of charge.

Argument	Type	Description
actual*	string	The correct option key.
decision_id*	string	decision_id returned by decide_with_profile.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "decision_id",
    "actual"
  ],
  "properties": {
    "actual": {
      "type": "string",
      "minLength": 1,
      "description": "The correct option key."
    },
    "decision_id": {
      "type": "string",
      "minLength": 1,
      "description": "decision_id returned by decide_with_profile."
    }
  }
}