Hesperan

com.hesperanPublished by hesperan.comOfficial publisherv0.1.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Hesperan answers typed decision questions with calibrated probabilities, and runs the user's own decision profiles to return an action plus confidence.

What you can do
Ask probability questions about a state: pick among named options, estimate whether a statement is true, or place a level on an ordinal scale, and get a probability for every possible answer. Run one of the user's decision profiles on a state to get a decision, its calibrated confidence, and an action of auto or review. Record the correct answer for an earlier profile decision so the console can track the profile's live precision.
When to use it
Useful when an assistant must make or route decisions with known options, such as triage, policy or risk calls, and you want probabilities rather than free text. Best suited to teams that have labelled cases and calibrated decision profiles in Hesperan.
Requirements
A Hesperan account and API key, supplied as HESPERAN_API_KEY or as an Authorization bearer header. Runs as a remote endpoint or locally via npx hesperan-mcp; HESPERAN_BASE_URL can override the API base URL. Network access to the Hesperan API.
Before you install
The API key is a secret and grants access to your Hesperan account and decision profiles. States you submit are sent to Hesperan's servers, so avoid including sensitive data you would not share with that third party. report_outcome writes outcome data that affects the profile's tracked precision.

Installation

In SourceWeft

  1. Open Hesperan in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.hesperan%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "hesperan": {
      "type": "http",
      "url": "https://api.hesperan.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

3

decide

Decide with Hesperan

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.

Parametersstaterequiredquestionsrequired

decide_with_profile

Decide with a calibrated 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).

Parametersstaterequiredprofilerequiredidempotency_key

report_outcome

Report the correct answer

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.

Parametersactualrequireddecision_idrequired

Version history

1
  1. v0.1.0LatestSep 25, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.